Back to Freedom.Tech

AI

RSS

Local LLM runners, open-weight models, agent frameworks, and frontier-lab releases.

1232 releases · 65 sources tracked · latest Oct 22, 2026

AI release Oct 22, 2026

llama.cpp b11808

Llama.cpp adds optional FC input scale loading for improved inference flexibility in quantized models
AI release Oct 22, 2026

Claude Agent Sdk Python 0.2.172

PyPI
AI release Oct 22, 2026

Checkpoint Engine 0.4.3-rc0

Fixes distributed checkpoint handling bugs, adds Intel XPU support, and improves vLLM compatibility for LLM training
AI release Oct 22, 2026

Claude Code Action GitHub 1.0

Claude Code GitHub Action v1.0 unifies configuration into single prompt and claude_args inputs, auto-detects mode, and exposes full CLI capabilities for CI workflows
AI release Oct 22, 2026

OpenAgentCore 0.0.12

Core for Linux, macOS and Windows; Linux amd64 Node distribution from commit
AI release Oct 22, 2026

Claude Agent Sdk Typescript 0.3.308

Claude Agent SDK TypeScript synced to parity with Claude Code v2.1.308
AI release Oct 22, 2026

Claude Code 2.1.308

Bug fixes and reliability improvements
AI release Oct 22, 2026

Ollama 0.40.9

Llama.cpp dependency updated to improve model inference performance and compatibility
AI release Oct 22, 2026

Qwen Code SDK TypeScript 0.1.22

This SDK release bundles CLI version: 0.26.0
AI release Oct 22, 2026

Qwen Code 0.26.0

Qwen Code adds managed-agent deployment reliability features, session-targeted skill refresh, local workspace file references, attachment upload limits to 8 MiB, and turn recovery from execution evidence
AI release Oct 21, 2026

llama.cpp b11803

Added support for Flint model (FlintForCausalLM) to enable inference of this architecture in llama.cpp
AI release Oct 21, 2026

Packages React Native 1.2.32

Updated dependencies @elevenlabs/client@1.30.0; @elevenlabs/react@1.19.1
AI release Oct 21, 2026

langchain== 1.4.7

LangChain 1.4.7 adds tool-call-delta stream consumption and LangChainTracer address configuration, plus dependency updates
AI release Oct 21, 2026

langchain-core== 1.6.13

LangChain Core now streams tool-call-delta events, enabling real-time partial tool invocation data in stream consumers
AI release Oct 21, 2026

Hermes Agent 0.22.4

Hermes Agent 0.22.4 removes composer suggestion pills, skips empty plugin consent prompts, and adds bubblewrap, Apptainer, and MCP server support
AI release Oct 21, 2026

openclaw 2026.10.10-beta.3

Windows startup, upgrade recovery, and agent state management improvements fix concurrent initialization, plugin convergence, and session persistence issues
AI release Oct 21, 2026

Kimi Code 2.3.0

Model switching now prompts for session handling, plugin skills use qualified names, remote control supports 100 MiB transfers, multi-client sessions handle conflicts, and auto-generated titles appear in terminal windows
AI release Oct 21, 2026

Claude Agent Sdk Python 0.2.170

Fixed parallel tool calls being dropped from session message history, ensuring all concurrent tool branches are captured
AI release Oct 21, 2026

Claude Code Action GitHub 1.0

Claude Code GitHub Action v1.0 unifies configuration into simplified prompt and claude_args inputs, auto-detects execution mode, and exposes full CLI capabilities for CI workflows
AI release Oct 20, 2026

Qwen Code 0.25.3-nightly.20261020.82bd240ad0

Daemon now supports session-targeted skill and extension refresh, managed-agent adds local and SSH workspace file references, and attachment input budget raised to 8 MiB
AI release Oct 20, 2026

Packages React Native 1.2.31

Updated dependencies @elevenlabs/client@1.29.0; @elevenlabs/react@1.19.0
AI release Oct 20, 2026

Packages Convai Widget Embed 0.21.0

Convai Widget Embed skips redundant terms acceptance when resuming persistent text conversations, treating prior acceptance as valid
AI release Oct 20, 2026

NanoClaw 2026.10.1-rc.1

Agents can spawn agents from templates, adds Cursor provider support, upgrades to Claude Haiku 5.5, fixes Docker Desktop reliability, Chat SDK moves to 4.41.1 with breaking changes for channel adapters
AI release Oct 20, 2026

OpenAgentCore 0.0.12

Core for Linux, macOS and Windows; Linux amd64 Node distribution from commit
AI release Oct 20, 2026

OpenAI 88.6

Terminal X's Eval Agent now grades outputs against 54 criteria, catching 25% more mandate deviations using GPT-6.1 Sol
AI release Oct 20, 2026

Jan 0.8.7

Minor update adding shell switching and image size limits; Low-priority bump
AI release Oct 20, 2026

Sandbox Runtime 0.0.81

Windows-only fixes; No impact on other platforms
AI release Oct 20, 2026

llama.cpp b11748

SYCL backend warning cleanup only; No functional change
AI release Oct 19, 2026

llama.cpp b11747

Fixes CUDA flash-attention race conditions; Relevant for anyone running GPU inference who's seen instability
AI release Oct 19, 2026

Qwen Code 0.25.3-nightly.20261019.5dcf7c7cb1

Qwen Code adds session-targeted skill refresh, workspace-isolated session warming, local/SSH file references, and improves daemon resilience through better writer-loss recovery and scheduling budgets
AI release Oct 19, 2026

Claude Code Action GitHub 1.0

Claude Code GitHub Action v1.0 unifies configuration into simpler prompt and claude_args inputs, auto-detects execution mode, and exposes full CLI capabilities for CI/CD workflows
AI release Oct 19, 2026

Hugging Face Transformers Patch 5.20.2

Fixes a type-preservation bug in generate() affecting multimodal model inputs; Patch if running multimodal pipelines
AI release Oct 19, 2026

HelixML 2.12.36

Fixes a Mac VM image build failure tied to ZFS install errors
AI release Oct 19, 2026

openclaw 2026.10.5

2,704 commits 2,250 pull requests 638
AI release Oct 19, 2026

Qwen Code SDK TypeScript 0.1.21

Bundles Qwen Code CLI 0.25.3; Sync versions if pinning both
AI release Oct 19, 2026

Qwen Code 0.25.3

Qwen Code 0.25.3 adds snapshot-isolated child agents, persistent Kubernetes workspace sessions, and managed session integration with approval policies and model selection
AI release Oct 19, 2026

InvokeAI 7.0.0

InvokeAI v7 alpha adds board role-based sharing, Qwen-Image-2.1 support, and SageAttention for faster NVIDIA generation, with database migrations that are one-way from v6
AI release Oct 19, 2026

ComfyUI 0.42.1

Fixes crashes in the MOSS image template workflow; Apply if that workflow has been unstable
AI release Oct 18, 2026

Claude Code Action GitHub 1.0

Claude Code GitHub Action v1.0 unifies configuration into simpler prompt and claude_args inputs with automatic mode detection and full CLI capability access
AI release Oct 18, 2026

Claude Code Action 1.0.253

Upstream release notes did not include a readable summary.
AI release Oct 18, 2026

ComfyUI 0.42.0

ComfyUI 0.42.0 adds Krea 3 and MOSS-image nodes, improves Qwen 3.x performance, fixes webcam and text generation cleanup, and expands ARM Linux support
AI release Oct 18, 2026

openclaw 2026.10.5

Improves self-healing updates across devices and platforms, fixing stranded installs from interrupted update processes
AI release Oct 18, 2026

vLLM 0.32.0

Large release, 814 commits; Worth checking changelog for breaking changes before upgrading production inference servers
AI release Oct 18, 2026

llama.cpp b11717

Hexagon quantized inference now supports hadamard operations and flat/tiled row access for Q1_0, Q2_0 quantizations, reducing packet overhead
AI release Oct 18, 2026

Ollama 0.40.7

Ollama 0.40.7 adds Perplexity's 27B decision model, fixes OpenAI-compatible streaming with reasoning models, and cancels remote requests on client disconnect
AI release Oct 17, 2026

Qwen Code 0.25.2-nightly.20261017.39c237af3b

Qwen Code nightly fixes managed-agent interruption handling, SQL timestamp standardization, runtime drain resilience, and adds live trajectory execution views plus static skills configuration
AI release Oct 17, 2026

llama.cpp b11716

Hexagon backend now supports Q1_0 and Q2_0 quantization formats with optimized tiling and vector operations for faster inference
AI release Oct 17, 2026

Elevenlabs Python 2.73.1

Fix tests on Python 3.13+, add 3.13/3.14 to CI, bump to 2.73.1 898
AI release Oct 17, 2026

Cli 1.6.1

Install elevenlabs-cli 1.6.1 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell
AI release Oct 17, 2026

Deepseek Harness 0.2.1-rc.2

Adds support for DeepSeek-V4.1-Flash-1017; Only matters if loading that model
AI release Oct 17, 2026

Deepseek Harness 0.2.1-rc.1

"" @turtle1999; Agent; @ZiyaZhang; ,, @imccyu, @turtle1999
AI release Oct 17, 2026

Cline Desktop 0.0.48

Cline Desktop now supports GPT-6 models on OpenAI/Azure endpoints and refreshes default models across multiple providers
AI release Oct 17, 2026

Cline CLI 3.0.73

Cline CLI adds GPT-6 support token parameter naming, restores Claude Sonnet 5.5 as default, and updates model catalog across multiple providers
AI release Oct 17, 2026

Cline SDK 0.0.95

Cline SDK fixes GPT-6 API compatibility, tracks hub launcher identity for telemetry, and updates 6,952 models with new providers and default model changes
AI release Oct 16, 2026

Qwen Code 0.25.2-nightly.20261016.b4614845f0

Nightly build with managed-agent stability fixes, web-shell UI improvements for file operations and live execution display, and runtime refactoring for better resource isolation
AI release Oct 16, 2026

Ollama 0.40.6

Ollama 0.40.6 adds Q2_0 quantization support, fixes Windows runner cleanup, and improves cloud integration with Clef
AI release Oct 16, 2026

Claude Code Action GitHub 1.0

Claude Code GitHub Action v1.0 unifies configuration through single prompt and claude_args inputs, enabling automated PR reviews, test fixes, and issue triage directly in workflows
AI release Oct 16, 2026

Claude Code Action 1.0.252

Upstream release notes did not include a readable summary.
AI release Oct 16, 2026

Claude Code 2.1.302

Adds a model override for client-side auto mode classification and a toggle for idle compaction
AI release Oct 16, 2026

Sandbox Runtime 0.0.80

Ask callback now only permits a connection when explicitly returning true; Tighten any integrations relying on default-allow behavior
AI release Oct 16, 2026

langchain-core== 1.6.12

Content-block-start events now propagate extras, fixing event metadata handling in streaming chains
AI release Oct 16, 2026

Cli 1.6.0

Install elevenlabs-cli 1.6.0 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell
AI release Oct 16, 2026

HelixML 2.12.35

API now reports sandbox out-of-memory kills with ownership labels, desktop syncs caps lock state per viewer, and sandboxes use confined AppArmor in rootless Docker
AI release Oct 16, 2026

Hugging Face Transformers 5.20.1

Adds support for Reflection AI's Beam model, a coding/agentic model. No impact unless loading that weight
AI release Oct 16, 2026

opencode 1.19.3

Model reasoning configuration now generates reasoning variants, replacing catalog variants while preserving user overrides
AI release Oct 16, 2026

Deepseek Harness 0.2.1-alpha.5

Deepseek Harness fixes skill menu updates, terminal query overhead, PTC mode guidance, and Page Up input handling across SDK, Web, and headless profiles
AI release Oct 16, 2026

Open WebUI 0.12.3

Adds end-to-end encrypted chats, relevant for self-hosters wanting transport-level privacy on their instance
AI release Oct 16, 2026

OpenAgentCore 0.0.12-rc.2

PostgreSQL now pulls from ghcr.io instead of Docker Hub, uninstall and failure recovery commands ship, and installers validate environment before making changes
AI release Oct 16, 2026

Cline 4.1.25

Rolls out Cline Cloud sessions, hosted sandbox runs against a chosen GitHub repo and branch. Opt-in, gradual rollout
AI release Oct 16, 2026

Cline CLI 3.0.72

Plugins now run in isolated workers instead of the hub process, mid-stream provider errors retry automatically, and model catalog refreshes with Gemini 4 Argon as the new default
AI release Oct 16, 2026

llama.cpp b11680

Hexagon tensor repacking reworked to support tiled and flat quantized weights, improving vectorized operations and memory efficiency on Qualcomm hardware
AI release Oct 16, 2026

Cline SDK 0.0.94

Plugin execution now requires explicit worker or sandbox mode with bootstrap validation, provider errors mid-stream retry without multiplying agent retries, and model catalog refreshed with Gemini 4 Argon as new default
AI release Oct 16, 2026

opencode 1.19.2

Pins update checks to the 1.x npm line so 1.x installs stop getting offered 2.x builds. Relevant only if auto-updates are enabled
AI release Oct 16, 2026

openclaw 2026.10.4

Gateway stability improved with fixes for sleep/clock-jump restarts, hung shutdown, owner-impersonation in group DMs, and passkey-handling responsiveness
AI release Oct 15, 2026

Venice MCP Server 0.3.0

Venice MCP Server adds 14 tools for chat, billing, API keys, crypto, and character management while fixing broken endpoints against current APIs
AI release Oct 15, 2026

ComfyUI 0.41.0

ComfyUI 0.41.0 adds ImageSDRToHDR and ReferenceMultiLatent nodes, Flux3-image support, and latent geometry introspection for advanced image generation workflows
AI release Oct 15, 2026

Qwen Code 0.25.2

H4e-b2 the lead's mailbox over Session messages ( 13892 ); A new private extension imports Vitest 3.2 JSON reports and exposes failures, errors, counts, and diagnostics through MCP tools with search and pagination. ( 13854 ); Opt-in headless Mods now support TypeScript authoring
AI release Oct 15, 2026

Claude Agent Sdk Python 0.2.168

PyPI
AI release Oct 15, 2026

Anthropic Cli 1.42.0

Anthropic CLI adds speed parameter to Messages API for request optimization, requires beta header for certain models
AI release Oct 15, 2026

langchain-core== 1.6.11

LangChainTracer now accepts custom addresses for tracing, enabling flexible instrumentation of LLM applications across different deployment environments
AI release Oct 15, 2026

Hugging Face Transformers 5.20.0

Transformers 5.20.0 adds native support for five multimodal and specialized models: Muse Spark Open, Ling 3.0 Flash, Kolibri1, MiniCPM-V 4.7, UnlimitedOcr, and UltraBERT
AI release Oct 15, 2026

openclaw 2026.10.10-beta.1

Moves SQLite and session work off the main thread; Improves responsiveness for busy gateways running large agent fleets
AI release Oct 15, 2026

Deepseek Harness 0.2.1-alpha.4

Deepseek Harness adds UI-driven reasoning configuration for custom API models, custom plugin index discovery, and fixes command handling, Office export, and Linux startup overhead
AI release Oct 15, 2026

Cli 1.5.3

Install elevenlabs-cli 1.5.3 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell
AI release Oct 15, 2026

OpenAgentCore 0.0.10

Faster startup, workspace isolation, automatic suspension, and improved recovery for agent sandbox lifecycle management now in stable release
AI release Oct 15, 2026

Hermes Agent 0.22.2

Hermes Agent 0.22.2 fixes gateway startup after reboot and improves local model resilience on laptops boot state and handling sleep periods
AI release Oct 15, 2026

llama.cpp b11640

Vulkan backend gets L2-friendly workgroup scheduling for matrix multiplication; Relevant for Vulkan GPU inference performance
AI release Oct 15, 2026

openclaw 2026.10.3

90 commits 79 pull requests 99
AI release Oct 15, 2026

Qwen Code 0.25.1-nightly.20261015.415925cbda

Connector and broker robustness from the 12692 R2 review; H4e-b2 the lead's mailbox over Session messages; Settle worktree child runs after their merge ( 13753 I2 follow-up); Add test failure report explorer
AI release Oct 15, 2026

InvokeAI Windows ARM64 wheels (win-arm64-wheels-v1)

Self-built Windows ARM64 wheels; Only relevant to ARM64 Windows users installing InvokeAI
AI release Oct 14, 2026

Hermes Agent 0.22.1

Hermes Agent adds Nemotron 3.5 defaults, Korean and Brazilian Portuguese language packs, multiple model provider plugins, and group attachment controls
AI release Oct 14, 2026

MLX 0.32.4

Adds VJP support for scaled dot product attention, needed for training/backprop workflows using MLX attention layers
AI release Oct 14, 2026

Rslearn 0.1.18

V1.3 renaming
AI release Oct 14, 2026

Open WebUI 0.12.2

Adds support for MinerU 4.x document parsing servers
AI release Oct 14, 2026

Ollama 0.40.5

Ports Metal custom kernels to CUDA, relevant for Nvidia GPU users running mlx-style workloads
AI release Oct 14, 2026

Claude Agent Sdk Python 0.2.167

PyPI
AI release Oct 14, 2026

Anthropic Sdk Csharp GoogleCloud 0.2.0

Added OpenTelemetry tracing support to AnthropicGoogleCloudClient with separate activity source for observability
AI release Oct 14, 2026

langchain== 1.4.6

Adds opt-in per-call interrupts to the human-in-the-loop middleware
AI release Oct 14, 2026

Deepseek Harness 0.2.1-alpha.3

Web app now supports local DeepSeek sign-in, masks API keys in messages, and adds conversation compaction for context management
AI release Oct 14, 2026

Kimi Code 2.2.0

Kimi Code 2.2.0 adds agent progress notifications, Tower mode deterministic orchestration, 90-second task wait caps, and sticky message summaries for faster navigation
AI release Oct 14, 2026

Cli 1.5.1

Install elevenlabs-cli 1.5.1 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell
AI release Oct 14, 2026

langchain-openai== 1.7.2

LangChain OpenAI 1.7.2 fixes streaming response handling when output indices drift across block boundaries
AI release Oct 14, 2026

Nvsentinel Provider Mistral v0.1.2

Prepare v0.1.2: patch dependencies and include runtime licenses 5
AI release Oct 14, 2026

Claude Agent Sdk Python 0.2.166

Adds typed hook output classes, replacing untyped dicts; Relevant for developers building custom hooks against the SDK
AI release Oct 14, 2026

Hermes Agent 0.22.0

Large version bump billed as a major release; Review breaking changes before upgrading production agents
AI release Oct 14, 2026

Claude Code Action GitHub 1.0

Claude Code GitHub Action v1.0 unifies configuration with automatic mode detection and unified prompt/args inputs, enabling AI-assisted PR reviews, CI fixes, and issue triage
AI release Oct 14, 2026

llama.cpp b11608

WebGPU fix for duplicate expert IDs in mixture-of-experts matmul; Relevant only to WebGPU backend users
AI release Oct 13, 2026

Qwen Code 0.25.1-nightly.20261013.6212189f1f

Nightly build fixing agent-broker robustness; Not for production pinning
AI release Oct 13, 2026

ComfyUI 0.40.0

ComfyUI 0.40.0 adds 3D asset export, camera info nodes, metadata attachment to prompts, partner model integrations (Vidu, Kling, Crystal), and VRAM optimizations for LLMs and attention mechanisms
AI release Oct 13, 2026

Packages Types 0.25.0

Adds conversation_history server event and persistent_session_token field to support multi-turn AI conversations with maintained state across sessions
AI release Oct 13, 2026

Packages React 1.18.0

Adds onConversationHistory callback to forward conversation data to ElevenLabs client for AI voice interaction tracking
AI release Oct 13, 2026

AnythingLLM 1.18.0

Fixes Kubernetes health probe path and a crash when removing files with attached images; Relevant for k8s deployments
AI release Oct 13, 2026

Cline Desktop 0.0.46

Cline Desktop adds prompt navigation sidebar, better plugin error messages, fixes scheduled routines, improves reasoning toggle support, and refreshes model catalog with new providers
AI release Oct 13, 2026

Cline 4.1.24

Default model for unconfigured Cline/OpenRouter setups switches to Claude Sonnet 5.5; Check cost implications if running without explicit model selection
AI release Oct 13, 2026

openclaw 2026.10.3

Large contributor-count release; Check changelog before upgrading agent pipelines built on it
AI release Oct 13, 2026

koboldcpp 1.123.1

KoboldCpp 1.123.1 adds Qwen Image 2.1 support, major agent improvements with granular approval modes and session persistence, full sampler/grammar/vision support in batched mode, and fixes macOS GPU usage regression
AI release Oct 13, 2026

koboldcpp 1.123

KoboldCpp 1.123 adds Qwen Image 2.1 support, major agent improvements with approval modes and session management, and batched mode now supports samplers, grammar, tool calls, and vision
AI release Oct 13, 2026

HelixML 2.12.34

Fixes a cross-tenant repo listing and org-create injection issue; Multi-tenant HelixML deployments should patch promptly
AI release Oct 13, 2026

llama.cpp b11580

Extends Hexagon DMA scalar broadcasting for binary ops; Relevant only for Hexagon-accelerated builds
AI release Oct 12, 2026

llama.cpp b11577

Vulkan backend tweaks for CM2 quant block sizing; Relevant only if running Vulkan-accelerated builds
AI release Oct 12, 2026

Qwen Code 0.25.1-nightly.20261012.18f80f5666

Nightly build improving managed-agent connector robustness and worktree cleanup after merges; Expect instability
AI release Oct 12, 2026

Design 0.3.0

Internal design-system tooling update from Allen AI; Limited relevance outside their stack
AI release Oct 12, 2026

langchain== 1.4.5

Adds summarizer support to SummarizationMiddleware; Check if using middleware-based conversation summarization
AI release Oct 12, 2026

Ollama 0.40.4

Updates bundled llama.cpp for decision-model and EmbeddingGemma 2 support, plus faster manifest reuse in inference routes
AI release Oct 12, 2026

langchain-anthropic== 1.7.6

Refreshes model profile data and declares mid-conversation support; Relevant if pinning model profiles explicitly
AI release Oct 12, 2026

Nvsentinel Provider Mistral v0.1.1

Narrow fix for NVSentinel connectivity under default network policies; Only relevant to that integration
AI release Oct 12, 2026

openclaw 2026.10.2

Fixes in-place updates that previously stalled or rolled back, including on Windows and cloned-filesystem setups; Resolves prior upgrade pain
AI release Oct 12, 2026

OpenAgentCore 0.0.10

Ports recent deployment fixes and microsandbox lifecycle work into the published installer
AI release Oct 12, 2026

Hermes Agent 0.21.7

Source installs now track tagged releases instead of every commit, reasoning persists across resumed sessions, and update checks work reliably behind firewalls
AI release Oct 12, 2026

Maple 3.4.4

Adds per-model thinking controls and bundles Maple Proxy 0.4.2; Also improves native sign-in flow
AI release Oct 11, 2026

Qwen Code 0.25.1-nightly.20261011.01d3e6d81a

Nightly build with managed-agent connector and worktree-merge fixes; Expect instability
AI release Oct 11, 2026

llama.cpp b11559

OpenCL GPU decode optimizations for Gemma-4 and improved DK64/DK128 performance with grouped query attention configurations
AI release Oct 11, 2026

Asta Plugins 0.109.0

Adds Overleaf pull/publish support and fork-PR handling
AI release Oct 11, 2026

openclaw 2026.10.1

3,055 commits 2,425 pull requests 402
AI release Oct 11, 2026

Qwen Code SDK TypeScript 0.1.19

Bundles Qwen Code CLI 0.25.1; Check compatibility if pinning CLI versions separately
AI release Oct 11, 2026

InvokeAI 7.0.0

InvokeAI 7.0.0 alpha adds multi-board projects, MySQL/MariaDB backends, expanded GGUF transformer support, improved video handling, and VRAM tuning for reduced OOM errors
AI release Oct 11, 2026

opencode 1.19.0

Adds an upgrade path to OpenCode 2 via opencode upgrade --major; Review breaking changes before running it
AI release Oct 11, 2026

Ollama 0.40.3

Cleans up warning messages for Claude and Codex launch commands; No functional change for most setups
AI release Oct 10, 2026

openclaw 2026.10.1

Large consolidated release spanning thousands of commits; Check changelog before upgrading production agents
AI release Oct 10, 2026

Qwen Code 0.25.0-nightly.20261010.9763580b84

Nightly build with host-binding and dialog test fixes; Skip unless tracking Qwen Code nightlies closely
AI release Oct 10, 2026

Open WebUI 0.12.0

Adds realtime voice calls to the chat interface
AI release Oct 10, 2026

llama.cpp b11552

Fixes a server bug where busy slots ran prompt cache updates before deferring; Relevant for multi-slot server deployments
AI release Oct 9, 2026

llama.cpp b11539

SYCL backend gets Q5_K reorder-layout MMVQ and fused GLU; Relevant mainly for Intel GPU inference setups
AI release Oct 9, 2026

Qwen Code 0.25.0-nightly.20261009.085a44f336

Qwen Code fixes agent host binding preservation, improves managed-agent SSE handling and extension loading performance, and adds experimental Kubernetes CSI runtime support
AI release Oct 9, 2026

Claude Code Action GitHub 1.0

Claude Code GitHub Action v1.0 simplifies AI-assisted CI/CD workflows with automatic mode detection, unified configuration, and full CLI capabilities access
AI release Oct 9, 2026

Claude Code Action 1.0.248

Upstream release notes did not include a readable summary.
AI release Oct 9, 2026

Claude Code 2.1.296

Adds a code policy key enabling Claude Desktop gateway mode and new subagent frontmatter options for custom agents
AI release Oct 9, 2026

Cli mistral 0.8.0

Breaking change: binaries stop auto-loading.env/bunfig.toml from the working directory; Check scripts that relied on this
AI release Oct 9, 2026

Mistral Vibe 2.26.1

Adds session-handoff visibility across processes and a /proxy-setup command for configuring proxy and SSL certs in the Rust CLI
AI release Oct 9, 2026

Deepseek Harness 0.2.1-alpha.2

Deepseek Harness adds experimental plugins for reasoning translation, Git worktrees, and session state APIs, plus TypeScript/Python SDKs for agent development
AI release Oct 9, 2026

NanoClaw 2026.10.0

Switches to calendar versioning and changes default update behavior to track published releases instead of main branch tip
AI release Oct 9, 2026

Jan 0.8.6

Hotfix only, patches issues introduced in 0.8.5
AI release Oct 9, 2026

Qwen Code 0.25.1-preview.1

Preview.1 fixes agent host binding, adds Kubernetes CSI runtime support, improves mobile accessibility, and defers agent declarations for better performance
AI release Oct 9, 2026

MiniMax Code 0.6.5

Built from public source commit
AI release Oct 8, 2026

langchain== 1.4.4

SummarizationMiddleware now retries on context overflow instead of failing, improving reliability for long-form summarization tasks
AI release Oct 8, 2026

Rslearn 0.1.17

Rslearn adds Sentinel-3 OLCI/SLSTR sources, ECOSTRESS data, per-pixel timestep prediction, and fixes image formatting bugs
AI release Oct 8, 2026

llama.cpp b11514

Removes duplicate SYCL block-size defines; Minor backend cleanup, no functional change for most users
AI release Oct 8, 2026

Claude Code 2.1.295

Blocks failing hooks, adds upstream timeout limits and request tracking, fixes MCP reconnection issues and file extension handling, improves gateway failover and plugin validation
AI release Oct 8, 2026

Claude Agent Sdk Python 0.2.165

Updated bundled Claude CLI to version 2.1.294 and improved release monitoring with Slack alerts for build failures
AI release Oct 8, 2026

Ollama 0.40.2

Ollama 0.40.2 upgrades downloaded models for llama.cpp compatibility while keeping backups, and fixes duplicate entries in model listings
AI release Oct 8, 2026

langchain-openai== 1.7.0

Langchain-openai 1.7.0 adds support for OpenAI's Decisions API, enabling structured decision-making in AI agent workflows
AI release Oct 8, 2026

Hermes Agent 0.21.6

Hermes Agent 0.21.6 consolidates 2,106 merged PRs including streaming speech-to-text, isolated third-party plugins, local model support, and four dashboard authentication security fixes
AI release Oct 8, 2026

openclaw 2026.9.9

185 commits 112 pull requests 92
AI release Oct 8, 2026

Jan 0.8.5

Bundled llama.cpp engine, dropped Intel Mac support, separated CLI from desktop app, added first-run wizard, and tightened Local API Server host validation
AI release Oct 8, 2026

Cline Desktop 0.0.45

Fixes SSH remote startup failures
AI release Oct 8, 2026

Cline CLI 3.0.70

Fixes 400 errors on commit-message generation with reasoning off for several models, and stops premature exits on MCP server/hook failures
AI release Oct 8, 2026

Claude Code 2.1.294

Fixes prompt/agent hooks written as natural-language instructions not being enforced correctly, including Stop and SubagentStop hooks
AI release Oct 8, 2026

Claude Agent Sdk Typescript 0.3.294

Version-matched to Claude Code 2.1.294; Update together if pinning both
AI release Oct 8, 2026

Anthropic Sdk Python 1.12.1

Python SDK adds changelog enforcement in CI and documents Claude Console spend-limit listing as early access
AI release Oct 8, 2026

MiniMax Code 0.6.3

Built from public source commit
AI release Oct 8, 2026

Anthropic Sdk Java 2.70.0

Anthropic Java SDK adds getters and builders to structured output classes, fixes empty path parameter handling
AI release Oct 8, 2026

openclaw 2026.10.1-beta.2

Beta fixes update recovery, messaging handoffs, and plugin persistence across restarts without losing Gateway availability or agent state
AI release Oct 7, 2026

Ollama 0.40.1

Adds proxy cloud usage/balance APIs and fixes a Windows memory-read bug past 2GiB in llama backend
AI release Oct 7, 2026

Qwen Code 0.25.0-nightly.20261007.8003d28042

Qwen Code adds Kubernetes CSI runtime support, H3 background Shell/Monitor, deferred agent declarations, and fixes remote host binding, SSE subscription handling, and memory indexing
AI release Oct 7, 2026

langchain-fireworks== 1.7.1

Fireworks integration now preserves reasoning output during streaming and tool use, fixing a data loss issue in agentic workflows
AI release Oct 7, 2026

langchain-huggingface== 1.2.3

Langchain-huggingface 1.2.3 hides API tokens from repr output, switches to torch.accelerator for device detection, and updates dependencies including transformers to 5.10.1
AI release Oct 7, 2026

Qwen 1.3.0

Release-PR: 94 Requested-From: 93 Source-Commit: Distribution: 1.1.11 Previous-Tag: qwen-mm-plugins-api-v1.2.0
AI release Oct 7, 2026

Cline 4.1.23

Cline 4.1.23 adds model catalog updates, fixes Claude custom endpoints, handles model-specific reasoning levels, and improves MCP tool output pagination and task UI state
AI release Oct 7, 2026

Cline Desktop 0.0.44

Mermaid diagrams render inline with interactivity, session auto-reconnect on Hub drops, local providers and Windows MCP servers work again, and model compatibility fixes
AI release Oct 7, 2026

Cline CLI 3.0.69

Fixes MCP servers launched via npx or uvx failing to load on Windows
AI release Oct 7, 2026

Cline SDK 0.0.91

Cline SDK adds unknown finish reason handling, extends MCP server timeouts to 10s, fixes Anthropic endpoint compatibility, and updates model catalogs across providers
AI release Oct 7, 2026

HelixML 2.12.33

HelixML fixes macOS GPU crashes Chromium with ANGLE-Vulkan instead of native Metal
AI release Oct 7, 2026

llama.cpp b11459

WebGPU backend now works on WASI without requiring Dawn native features, enabling GPU acceleration for llama.cpp in WebAssembly environments
AI release Oct 7, 2026

Open Interpreter 0.0.56

Added GPT-6.1 Sol and Claude Sonnet 5.5 model support, fixed shell environment rebinding on thread resume
AI release Oct 7, 2026

HelixML 2.12.32

Mac updates now clear restart prompts properly and shut down the VM cleanly on quit
AI release Oct 6, 2026

Claude Agent Sdk Python 0.2.164

PyPI
AI release Oct 6, 2026

llama.cpp b11456

Fixes a k-pool scatter data race affecting shared sequences; Relevant for multi-session inference setups
AI release Oct 6, 2026

opencode 1.18.35

Added canonical redirects and agent-readable data formats for stats, fixed xAI tool results to properly handle supported image formats
AI release Oct 6, 2026

Claude Code Action GitHub 1.0

Claude Code's GitHub Action hits 1.0 and general availability, the stabilization point for CI workflows built on it
AI release Oct 6, 2026

Qwen Code 0.25.1-preview.0

Preview adds Kubernetes CSI runtime support, fixes agent bindings and memory indexing, and improves mobile/CLI stability
AI release Oct 6, 2026

whisper.cpp 1.9.5

Whisper.cpp 1.9.5 updates to ggml v0.26.0, bringing GPU optimizations across CUDA, Vulkan, Metal, and WebGPU for faster speech-to-text inference
AI release Oct 6, 2026

Hugging Face Transformers 5.19.0

Adds EmbeddingGemma 2, a multimodal embedding model on the Gemma 4 architecture. Relevant for anyone building retrieval or embedding pipelines on Transformers
AI release Oct 6, 2026

Client Python 3.1.0

Removed unstable Runs and Records APIs, restructured authentication types, and unified workflow reference handling in Python SDK
AI release Oct 6, 2026

langchain-core== 1.6.7

Bedrock converse now includes OpenAI redacted_content in v1 output; Python 3.14 compatibility hardened
AI release Oct 6, 2026

Packages React Native 1.2.29

Updated dependencies; Updated dependencies @elevenlabs/client@1.27.0; @elevenlabs/react@1.17.0
AI release Oct 6, 2026

Mistral Vibe 2.26.0

Mistral Vibe 2.26.0 adds Rust CLI with onboarding, MCP connector management, skills/file mentions, voice mode, recurring prompts, and per-model context limits
AI release Oct 6, 2026

Diffusers 0.41.0

Adds the Qwen-Image 2.1 pipeline: text-to-image, editing, native transparency, LoRA training. Relevant for image-gen workflows on Diffusers
AI release Oct 6, 2026

Claude Code Action 1.0.243

Upstream release notes did not include a readable summary.
AI release Oct 6, 2026

Claude Agent Sdk Typescript 0.3.291

Claude Agent SDK TypeScript now matches Claude Code v2.1.291 capabilities for agent development
AI release Oct 5, 2026

llama.cpp b11433

CUDA kernel change tiles the lightning indexer for low-head-count cases; Relevant for custom inference tuning, not a default-path change
AI release Oct 5, 2026

ComfyUI 0.39.0

Adds Minimax-H3 VAE support and higher-quality defaults for video encoding
AI release Oct 5, 2026

Maple 3.4.3

Improves chat usability and fixes iOS subscription recovery plus device clock error handling
AI release Oct 5, 2026

openclaw 2026.10.1-beta.1

Fixes session/memory handling across registry changes and stalled transcript aliases; Beta for active-turn stability
AI release Oct 5, 2026

llama.cpp 0.6.0

Adds extended batch API for mixed token/embedding inputs, supports GLM-5.3-Flash and decision models, enables MTP speculative decoding and Metal flash attention optimizations
AI release Oct 5, 2026

Elevenlabs Js 2.71.0

Only, no functional changes noted
AI release Oct 5, 2026

Elevenlabs Python 2.71.0

Only, matching the JS release
AI release Oct 5, 2026

NanoClaw 2026.10.0-rc.2

Second RC for the first calendar-versioned NanoClaw release; Update flow now tracks published releases instead of main
AI release Oct 5, 2026

Qwen Code Desktop 0.25.0

Adds a managed runtime attestation client and a time-range selector for trajectory overviews; Mostly tooling plumbing
AI release Oct 5, 2026

Qwen Code SDK TypeScript 0.1.18

Bundles CLI 0.25.0; Routine SDK/CLI version alignment update
AI release Oct 5, 2026

Qwen Code 0.25.0

Qwen Code adds local agent collaboration, managed workspace infrastructure, persistent file history, and concurrent bash execution in Code Mode
AI release Oct 5, 2026

vLLM 0.31.0

Large release, 717 commits from 307; Review changelog before upgrading production inference servers
AI release Oct 4, 2026

Qwen Code 0.24.7-nightly.20261004.9915c7ff8f

Nightly build fixes cross-directory tool-call permissions and a CLI input bug; Relevant if running nightlies in automation
AI release Oct 4, 2026

llama.cpp b11398

CI/build-pipeline fix for tag pushing; No functional change for end users
AI release Oct 4, 2026

NanoClaw 2026.10.0-rc.1

First calendar-versioned release and first one auto-installed by /update-nanoclaw; Updates now track published releases instead of main
AI release Oct 4, 2026

InvokeAI 7.0.0

Pointing v7 at an existing root directory upgrades the database irreversibly; Back up before installing, v6 compatibility is lost
AI release Oct 3, 2026

Claude Agent Sdk Typescript 0.3.289

Brings SDK to parity with Claude Code v2.1.289; Upgrade if pinning to matching versions
AI release Oct 3, 2026

Qwen Code 0.24.7-nightly.20261003.2c591ecc08

Nightly fixes for tool permissions and CLI input handling; Relevant only if tracking the nightly channel
AI release Oct 3, 2026

llama.cpp b11379

Fixes a soft-max-back output bug triggered aliasing; Affects custom ggml backprop usage
AI release Oct 3, 2026

Deepseek Harness 0.2.1-alpha.1

Alpha release of the Claude Code-based coding harness; Expect rough edges
AI release Oct 3, 2026

openclaw 2026.9.8

58 commits 43 pull requests 21
AI release Oct 2, 2026

Qwen Code 0.24.7-nightly.20261002.a011f66944

Nightly fixes for tool-discovery text alignment, cross-directory permission approval, and CLI Enter-key handling
AI release Oct 2, 2026

LocalAI 4.11.0

LocalAI 4.11.0 adds audio scene understanding with speaker diarization, model failover chains for resilience, decision models via /v1/systemone, signed OCI galleries, and text-to-animation
AI release Oct 2, 2026

Cline Desktop 0.0.43

Introduces Connectors with a one-time onboarding dialog; Existing users will see a new UI prompt
AI release Oct 2, 2026

Claude Agent Sdk Typescript 0.3.288

Brings the TypeScript SDK to parity with Claude Code v2.1.288; Update via npm/yarn/pnpm/bun as usual
AI release Oct 2, 2026

HelixML 2.12.30

Added project settings shortcut to chat sidebar and fixed macOS QEMU pinning to resolve stuck app upgrades
AI release Oct 2, 2026

langchain-text-splitters== 1.1.3

Dependency bumps only; No functional change to splitter behavior
AI release Oct 2, 2026

Hermes Plugin Byterover 1.0.1

Byterover memory plugin extracted to standalone package under Nous Research maintenance with cross-platform CI and backward-compatible config migration
AI release Oct 2, 2026

Cline CLI 3.0.68

Agent teams now auto-compact inflated state databases during long sessions, preventing gigabyte bloat and performance degradation
AI release Oct 2, 2026

llama.cpp b11335

Fixes CUDA MMVQ routing for Volta (sm70) GPUs, relevant only to that hardware generation
AI release Oct 2, 2026

MiniMax Code 0.6.2

Built from public source commit
AI release Oct 2, 2026

openclaw 2026.8.34

Gateway-only extended-stable build, openclaw's LTS equivalent. Operators prioritizing stability over features should track this line
AI release Oct 1, 2026

AnythingLLM 1.17.0

AnythingLLM 1.17.0 fixes spreadsheet parsing, agent web-browsing, vector scoring inconsistencies, and adds Gemini image generation and Firecrawl web-search support
AI release Oct 1, 2026

Qwen Code 0.24.7-nightly.20261001.a7deb01bcb

Qwen Code adds local workspace-agent collaboration, bundles Mem0 memory system, fixes tool permissions and CLI input handling, and improves daemon isolation and session uploads
AI release Oct 1, 2026

HelixML 2.1.28

Adds an idle-class CPU tier for desktop agent work alongside build reliability fixes
AI release Oct 1, 2026

HelixML 2.12.27

Restores debug-shell TTY in desktop setup and unarchive on spec task tabs; Fixes for recent regressions
AI release Oct 1, 2026

llama.cpp b11311

Replaces alloca() with std::vector in ggml-opencl
AI release Sep 30, 2026

Open Interpreter 0.0.55

Fixes offline model listing for non-OpenAI providers
AI release Sep 30, 2026

opencode 1.18.34

Sends namespaced session headers with model requests
AI release Sep 30, 2026

Qwen Code 0.24.7-nightly.20260930.57e720bc97

Aligns Code Mode text with lazy tool discovery; Honors approved cross-directory tool calls
AI release Sep 30, 2026

Claude Agent Sdk Python 0.2.163

Updates bundled Claude CLI to 2.1.286; Pins CI model version to avoid default-model triage failures
AI release Sep 30, 2026

Claude Code Action 1.0.238

Security hardening for GitHub Actions workflows that invoke Claude
AI release Sep 30, 2026

Vla Evaluation Harness 0.8.0

Shared episode scheduling; Clearer shard failures; More reliable RoboTwin and container execution
AI release Sep 30, 2026

Anthropic Sdk Java 2.67.0

Adds refusal stop reason, session idle events, and Claude Enterprise analytics
AI release Sep 30, 2026

Anthropic Sdk Ruby 1.75.0

Adds refusal stop reason, session idle events, and Claude Enterprise analytics
AI release Sep 30, 2026

Hugging Face Transformers 5.18.0

Adds Nemotron 3 Diarization model for streaming speaker diarization
AI release Sep 30, 2026

langchain-openai== 1.6.7

Discovers Azure OpenAI models; Refreshes model profile data
AI release Sep 30, 2026

MiniMax Code 0.5.10

Built from public source commit
AI release Sep 30, 2026

openclaw 2026.9.7

Updates now back up state and agent databases before migrations, restore on rollback, take consistent snapshots while Gateway writes, and halt before schema changes when snapshot cleanup fails
AI release Sep 30, 2026

Cline 4.1.22

Adds two new providers: Bee and Pareto Inference
AI release Sep 30, 2026

llama.cpp b11270

Optimizes hexagon concat op. Reduces packets in gather/transpose hot loop. Uses fastdiv to replace software divide. Optimizes DMA-HVX pipeline
AI release Sep 30, 2026

Cline SDK 0.0.88

Direct Anthropic requests now ask Claude API for server-side refusal fallback. OpenRouter and Cline requests for Anthropic models allow provider failover
AI release Sep 29, 2026

Qwen Code 0.24.7

Qwen Code 0.24.7 adds managed workspace execution, tool-result contracts, cross-engine session routing, and AI-drafted commit messages
AI release Sep 29, 2026

ComfyUI 0.38.0

Improves Qwen 2.1 KV cache location logic. Compiles Qwen Image 2.1 transformer blocks. Model files can now contain attention implementation hints
AI release Sep 29, 2026

Ollama 0.35.1

Now allows ten web searches per response. Includes llama.cpp and MLX version bumps
AI release Sep 29, 2026

Claude Agent Sdk Typescript 0.3.285

Adds optional read.title to Artifact tool structured read result. Fixes sessions with CLAUDE CODE FORK SUBAGENT=1. Adds provider not allowed to startup failure reason and allowedProviders to Settings type
AI release Sep 29, 2026

MiniMax Code 0.5.9

Built from public source commit
AI release Sep 29, 2026

langchain-anthropic== 1.7.5

Supports Claude Sonnet 5.5 compatibility. Serializes invalid tool calls as tool use on replay
AI release Sep 29, 2026

HelixML 2.12.25

Accepts future GPT models for Codex agents. Recovers disconnected desktops and adds bound prompt retries
AI release Sep 29, 2026

Cli 1.0.27

Aligns agent setup with MiniMax M3.1 Flash Preview
AI release Sep 29, 2026

Deepseek Harness 0.2.0-rc.2

Bundles dsh command with macOS and Windows Desktop, fixes shell issues and Agent presets, adds model search, and improves environment handling
AI release Sep 29, 2026

llama.cpp b11246

Fixes Muse Glimmer ignoring response format json schema when using --jinja
AI release Sep 29, 2026

openclaw 2026.8.33

First gateway-only extended-stable build; Treats 2026.8.33 as LTS equivalent
AI release Sep 28, 2026

llama.cpp b11240

Llama.cpp now supports vision, audio, and video inputs for the /v1/embeddings endpoint using OpenAI-compatible multimodal content arrays
AI release Sep 28, 2026

langchain== 1.4.3

Sanitizes cache settings for fallback models, supports Bedrock Mantle chat init, recognizes GPT-6 structured output
AI release Sep 28, 2026

Client Python 3.0.0

Python SDK 3.0.0 removes 24 deployment and worker configuration APIs while refactoring 143 response types for stricter null handling, breaking existing integrations
AI release Sep 28, 2026

Claude Code 2.1.284

Adds Claude Sonnet 5.5 as default Sonnet model; 1M context, $2/$10 per Mtok with $0.20 cache reads
AI release Sep 28, 2026

Claude Agent Sdk Typescript 0.3.284

Renames skill directory to SlashCommand alias when name is plain and no shipped command exists; Adds ultracodeAvailable and ultracodeRequested to getSettings
AI release Sep 28, 2026

Deepseek Harness 0.2.0-rc.1

Rc.1 improves UI reliability, fixes tool-scheduling failures, adds web search for account models, and refactors automation into optional plugins
AI release Sep 28, 2026

MiniMax Code 0.5.8

Built from public source commit
AI release Sep 28, 2026

MiniMax Code 0.5.6

Built from public source commit
AI release Sep 28, 2026

opencode 1.18.33

Cloudflare AI Gateway models now respect provider response and stream timeouts
AI release Sep 27, 2026

InvokeAI Version 6.14.2

Bug fixes from 6.14.1 plus unspecified new features
AI release Sep 27, 2026

llama.cpp b11222

Server now supports RANK pooling batch splitting for causal LLM rerankers
AI release Sep 27, 2026

Deepseek Harness 0.1.7-rc.2

Deepseek Harness adds scheduled task management with persistence, improved onboarding, keyboard shortcut customization, and dynamic tool loading without cache invalidation
AI release Sep 27, 2026

MiniMax Code 0.5.5

Built from public source commit
AI release Sep 26, 2026

Qwen Code 0.24.6

Qwen Code 0.24.6 adds Managed Runtime v2 tool operations, durable session failover, native advisor tool, and Batch API workflow support for production deployments
AI release Sep 26, 2026

llama.cpp b11205

Added CUDA support for Nemotron 3 Puzzle state size 96 SSM scan operations
AI release Sep 26, 2026

koboldcpp 1.122.1

KoboldCpp adds an integrated agent with 9 built-in tools and 2k token system prompt for autonomous task execution across compatible backends
AI release Sep 26, 2026

Cline Desktop 0.0.37

Adds About page in Settings
AI release Sep 26, 2026

Qwen Code Desktop 0.24.6

Adds managed runtime attestation client; Web-shell can select time range on trajectory overview to narrow table
AI release Sep 25, 2026

llama.cpp b11191

Fixes unicode path handling on Windows; Directory creation now creates last directory when no trailing separator is present
AI release Sep 25, 2026

Ollama 0.40.0

MLX-compatible models run on Apple Silicon
AI release Sep 24, 2026

llama.cpp b11172

Rejects MUL_MAT_ID when src1 precision is F32 on Hexagon
AI release Sep 24, 2026

HelixML 2.12.22

Keeps scoped embeds out of login, enables browser from first turn for DSH
AI release Sep 24, 2026

Qwen Code 0.24.5

Qwen Code adds runtime attestation for managed environments, channel access controls, tool-call timing, and web shell trajectory visualization with time-range filtering
AI release Sep 24, 2026

Claude Agent Sdk Typescript 0.3.282

Adds support for strictKnownMarketplaces and blockedMarketplaces in host-supplied managedSettings; Allowlist applies where admin policy sets none, blocklist adds to admin's
AI release Sep 24, 2026

Claude Code 2.1.282

Adds maxProseWidth setting capping prose width in wide terminals
AI release Sep 24, 2026

Cline 4.1.21

Adds ai& provider, an OpenAI-compatible endpoint serving open-weight models from Japan
AI release Sep 24, 2026

Deepseek Harness 0.1.7-rc.2

Deepseek Harness adds scheduled task management, keyboard shortcut customization, background task persistence, and manual approval overrides for auto-review denials
AI release Sep 24, 2026

Hermes Agent 0.21.5

Hermes Agent 0.21.5 consolidates 460 PRs with desktop plugin SDK, French/German/Spanish catalogs, performance improvements, and new model integrations for stable downstream consumption
AI release Sep 24, 2026

Elevenlabs Python 2.69.0

Strips residency suffix from API key before JWT verification, raises when ffplay exits with error
AI release Sep 24, 2026

Elevenlabs Js 2.69.0

Strips residency suffix from API key before JWT verification, adds transcriptEdit to realtime speech-to-text wrapper
AI release Sep 24, 2026

MiniMax Code 0.5.4

Built from public source commit
AI release Sep 24, 2026

MiniMax Code 0.5.3

Built from public source commit
AI release Sep 24, 2026

Cline CLI 3.0.65

Long sessions on local models no longer die mid-answer at the output-token limit
AI release Sep 24, 2026

Cline SDK 0.0.86

Text-only turns truncated at the output-token limit now get one compact-and-retry attempt before nudge-and-retry recovery
AI release Sep 24, 2026

Rslearn 0.1.16

Loads released bundle with full olmoearth pretrain loader and supports overriding ground control point handling
AI release Sep 23, 2026

Qwen Code 0.24.4-nightly.20260923.d0cd622a68

Qwen Code fixes deferred-tool bridge staleness, optimizes Agent tool prompting via bundled skills, and adds runtime attestation with CLI improvements for clipboard and editor availability
AI release Sep 23, 2026

llama.cpp b11149

HIP optimization for IQ2 and IQ3 using SWAR bit manipulation for vcmpne4 and vsub4
AI release Sep 23, 2026

llama.cpp 0.5.0

CUDA convolution acceleration, Metal MoE/SSM fusion, multi-address server binding, expanded model support including HunyuanOCR, and improved tensor-parallel handling for fused QKV architectures
AI release Sep 23, 2026

Claude Code 2.1.281

Adds Claude apps gateway support for newer desktop policy blocks and Bedrock assume-role on upstreams
AI release Sep 23, 2026

langchain-anthropic== 1.7.4

Adds Opus 5.5 and GPT-6 profile augmentations, plus mid-conversation tool changes on SystemMessage
AI release Sep 23, 2026

NanoClaw 2.4.0

Adds credential gateways via skills, community-portal setup for Echo, install-wide and per-group model controls, and Mattermost channel integration
AI release Sep 23, 2026

Claude Code Action 1.0.232

Pins integration tests to claude-opus-5
AI release Sep 23, 2026

Deepseek Harness 0.1.7-rc.1

Web,Shell @LegGasai; :, @tianyicui, @Yifffan, @LegGasai; MCP URI Profile MCP @tianyicui; Headless, --session-id, --json JSON @lsdsjy
AI release Sep 23, 2026

langchain-openai== 1.6.5

Adds Opus 5.5 and GPT-6 profile augmentations, plus mid-conversation tool changes on SystemMessage
AI release Sep 23, 2026

Mistral Vibe 2.25.8

Supports configuring Vibe Code remote projects in Rust CLI, archives local sessions, and shows unseen indicators for Code sessions needing attention
AI release Sep 23, 2026

Qwen Code cua-driver-rs 0.20.11

Qwen Code CUA Driver 0.20.11 adds relative coordinate support, MCP payload filtering, and fixes coverage tracking, notebook pagination, and workspace browsing across desktop and mobile clients
AI release Sep 23, 2026

Ollama 0.34.4

Fixes intermittent model-not-found errors on the server side
AI release Sep 23, 2026

Claude Agent Sdk Python 0.2.158

Adds ClaudeAgentOptions.verbatim_prompts option, defaults to False
AI release Sep 22, 2026

langchain-openai== 1.6.4

Refreshes OpenAI model profile data
AI release Sep 22, 2026

Qwen Code 0.24.4

Qwen Code 0.24.4 adds monitor tool guidance, batched workspace catalogs, SSH workspace support without daemons, encrypted mobile connection profiles, and tool execution sandboxing with managed runtime attestation
AI release Sep 22, 2026

llama.cpp b11114

New HMX-optimized GATED DELTA NET with pipelining
AI release Sep 22, 2026

Cline Desktop 0.0.34

Composio connectors now load all available tools instead of stopping at the first 20
AI release Sep 22, 2026

Cline 4.1.20

Sub-agents spawned in the same step now execute tool calls concurrently instead of sequentially
AI release Sep 22, 2026

AnythingLLM 1.16.2

AnythingLLM 1.16.2 adds Google Vertex AI and LLMman local LLM providers, image generation skill, You.com web search, and agent flow variables, plus improved document handling and model loading visibility
AI release Sep 22, 2026

llm CLI 0.36

Adds support for gpt-6-sol and gpt-6-luna endpoints
AI release Sep 22, 2026

Rslearn 0.1.15

Makes WorldCereal downloads resumable with checksum verification, adds sdpa option, and selects distilled register student for embedding extraction
AI release Sep 22, 2026

Anthropic Cli 1.35.0

Added Claude Opus 5.5 support, inline tool definitions, and MCP tool-list pinning in beta
AI release Sep 22, 2026

Deepseek Harness 0.1.7-alpha.2

Alpha.2 stabilizes conversation UI, fixes agent session stalling, and improves file handling and model discovery
AI release Sep 22, 2026

Mistral Common 1.12.0

Adds agnostic validation mode, allows overriding auto-detected plain thinking support in chat templates, and sets reference audio filename for voice tasks
AI release Sep 22, 2026

HelixML 2.12.20

HelixML fixes terminal agent retry logic, recovers sandbox desktop metadata, and improves bot navigation flow
AI release Sep 22, 2026

MiniMax Code 0.5.2

Built from public source commit
AI release Sep 22, 2026

vLLM 0.30.0

762 commits from 315
AI release Sep 22, 2026

Qwen Code 0.24.3-nightly.20260922.c5920f479b

Qwen Code adds monitor tool guidance to system prompts, batched workspace sessions, and plan drift detection for code review
AI release Sep 22, 2026

langchain-deepseek== 1.1.1

Fixes compatible minimum OpenAI dependencies
AI release Sep 22, 2026

Cline CLI 3.0.63

Context compaction no longer degrades to truncation on OAuth providers
AI release Sep 21, 2026

llama.cpp b11090

Fixed CUDA SM_70 tile compilation error load_ldmatrix shape handling for Volta architecture compatibility
AI release Sep 21, 2026

opencode 1.18.32

Bedrock image attachments now hoisted only for Claude, Nova, Llama 4
AI release Sep 21, 2026

Qwen Code 0.24.3

Web Shell gains structured results and metrics, Live Voice moves to AudioWorklet, and JDBC persistence enables shared runtime state across processes
AI release Sep 21, 2026

Open WebUI 0.11.4

Adds smaller slim image
AI release Sep 21, 2026

langchain-openai== 1.6.3

Exposes inferred Responses API routing at initialization, supports GPT-6 request constraints
AI release Sep 21, 2026

Hermes Agent 0.21.4

Hermes Agent 0.21.4 stabilizes 1,800 merged PRs including desktop improvements, structured CLI output, MCP discovery controls, new video models, and community plugins
AI release Sep 21, 2026

LlamaIndex 0.14.25

Resolves security alerts across multiple agent and callback packages
AI release Sep 21, 2026

Kimi Cli 1.51.0

Archived; Points users to Kimi Code CLI
AI release Sep 21, 2026

openclaw 2026.7.35

Gateway-only extended-stable branch, equivalent to LTS
AI release Sep 21, 2026

MiniMax Code 0.5.1

Built from public commit
AI release Sep 21, 2026

ComfyUI 0.37.0

Auto-detects and enables --fast-disk when disk is fast. Ships Aimdo 0.5.5
AI release Sep 20, 2026

langchain-typesafe== 0.0

LangChain TypeSafe adds typed routing and classification for AI agents via experimental middleware for safer model selection and tracing
AI release Sep 20, 2026

Qwen Code 0.24.2

Qwen Code 0.24.2 adds Linux sandbox execution, concurrent browser sessions, cross-session messaging, prompt cache preservation, and Live Voice improvements
AI release Sep 20, 2026

MiniMax Code 0.5.0

Built from public source commit
AI release Sep 20, 2026

llama.cpp b11060

CUDA path: enables sparse flash attention for Qwen4 models
AI release Sep 20, 2026

Open Interpreter 0.0.45

DeepSeek Flash and V4 Pro now appear in the model picker
AI release Sep 19, 2026

llama.cpp b11057

Llama.cpp added specialized Ling 3.0 parser handling tool calls and reasoning blocks correctly in streaming chat templates
AI release Sep 19, 2026

Cli 1.3.2

Install elevenlabs-cli 1.3.2 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell
AI release Sep 19, 2026

Qwen Code 0.24.1

Qwen Code adds Playwright browser automation, per-model OpenAI API selection, container execution for subagents, and workflow checkpointing
AI release Sep 19, 2026

Cli 1.0.26

Adds speech-to-text transcription with language hints, multiple output formats, timestamps, and streaming support via mmx speech transcribe
AI release Sep 19, 2026

Kimi Code 2.0.2

Kimi Code 2.0.2 fixes conversation state bugs, context window switching failures, working directory detection, and duplicate message display issues
AI release Sep 19, 2026

Vla Evaluation Harness 0.7.0

More reliable recording and concurrent container runs, with CPU rendering for additional benchmarks
AI release Sep 19, 2026

Claude Agent Sdk Typescript 0.3.278

Updated to parity with Claude Code v2.1.278
AI release Sep 19, 2026

openclaw 2026.9.5

OpenClaw v2026.9.5 ships 64 commits across 4,179 pull requests from 503
AI release Sep 19, 2026

Ollama 0.34.3

GET /api/show now advertises each model's thinking controls and default values
AI release Sep 18, 2026

llama.cpp b11045

Added OpenCL support for bin kernel flash attention f32 f16
AI release Sep 18, 2026

Sandbox Runtime 0.0.77

Fixed multiple path-denial enforcement bugs on Linux and macOS, improved npm resolution performance, and added startup checks for required capabilities
AI release Sep 18, 2026

Claude Code 2.1.277

Claude Code adds AGENTS.md project instruction support, fixes conversation failures from empty text blocks, resolves hangs in CLI sessions after errors, and patches multiple tool and state management bugs
AI release Sep 18, 2026

langchain== 1.4.2

Preserves model-generated tool calls in human-in-the-loop tool call edits, adds notice to ToolMessage
AI release Sep 18, 2026

Kimi Code 2.0.1

Kimi Code 2.0.1 improves CLI startup and session loading performance, adds environment variable API key support, and fixes media tool listings and session message duplication
AI release Sep 18, 2026

Mistral Vibe 2.25.5

Subagent conversation history now readable through owning parent session. Configurable live subagent status and read-only transcript switching from the interactive prompt. Experimental harness sessions can track todos
AI release Sep 18, 2026

openclaw 2026.7.33

July 2026 Extended Stable covering Gateway, official npm plugins, and matching Docker images
AI release Sep 18, 2026

qwen-mm-plugins-omni-video2note 1.0.2

Omni video-to-note plugin now defaults to qwen3.8-omni-flash model, simplifies PDF pipeline, and fixes CI dependencies
AI release Sep 18, 2026

qwen-mm-plugins-omni-skill-creator 1.0.1

Defaults the Omni model to qwen3.8-omni-flash; Lazy imports yaml and installs it for test step on macOS CI
AI release Sep 18, 2026

Claude Agent Sdk Typescript 0.3.276

Updated to parity with Claude Code v2.1.276
AI release Sep 17, 2026

Cli 1.3.1

Install elevenlabs-cli 1.3.1 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell
AI release Sep 17, 2026

langchain-typesafe== 0.0

Initial release with experimental AutoModeMiddleware, ModelRouterMiddleware, and TypeSafeClassifier; Fixes trace usage metadata
AI release Sep 17, 2026

Cline Desktop 0.0.31

Can now work on a remote machine over SSH with the app staying local
AI release Sep 17, 2026

LocalAI 4.10.0

Fleet dashboard, credentials file for private model sources, and local-ai benchmark CLI join vllm-cpp LoRA fusion, ds4 CUDA fixes, and four CVE patches
AI release Sep 17, 2026

llama.cpp b11026

Skips gate-up exps if TENSOR_SKIP is set; Required for qwen35moe when MTP tensors are fused but not loaded
AI release Sep 17, 2026

Deepseek Harness 0.1.6-alpha.2

,, @LegGasai, @turtle1999; , @CreatixChu; Office, WordExcel PowerPoint @yudshj; URL @imccyu
AI release Sep 17, 2026

HelixML 2.12.17

Returns 413 for oversized chat requests; Bounds image history in opencode
AI release Sep 17, 2026

Claude Agent Sdk Python 0.2.154

Bundles Claude CLI version 2.1.274
AI release Sep 16, 2026

Olmoearth Pretrain Minimal 0.0.9

Fixes inconsistent CompositeEncodings pos embed handling
AI release Sep 16, 2026

Qwen Code 0.24.0-nightly.20260916.b8def02aad

Qwen Code fixes daemon credential handling, restores auto-memory extraction, and improves CI packaging for the export renderer
AI release Sep 16, 2026

llama.cpp b11009

Fixed fused QKV attention layer calculations for Gemma-4 and Qwen-3.5, enabling correct tensor parallelism splits when embedding dimensions don't match head counts
AI release Sep 16, 2026

Qwen Code 0.23.5-preview.0

Qwen Code adds web search rate-limiting, hook progress events, dynamic extension workflows, DingTalk output sharing, and fixes Linux input handling and web terminal bundling
AI release Sep 15, 2026

Cli 1.3.0

Install elevenlabs-cli 1.3.0 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell
AI release Sep 15, 2026

ComfyUI 0.36.0

New model blueprints; AMD Windows VA quota bumped to 4TB
AI release Sep 15, 2026

Ollama 0.34.2

Llama.cpp updates only
AI release Sep 15, 2026

llama.cpp b10988

OpenCL MoE expert matmul selection size for speculative decoding; Gated prebuilt q4_0 MoE GEMM on routing count
AI release Sep 15, 2026

llamafile 0.10.6

Llama.cpp update to b10441; Zip entry window validation; Guard against malformed zips
AI release Sep 15, 2026

Kimi Code 0.43.1

Fixes memory leaks, rendering performance, and subagent lifecycle issues while improving terminal UI and clipboard support on Linux
AI release Sep 15, 2026

Cline CLI 3.0.62

Cline Desktop native app ships with Agent Plugin hub management, transient error retry, checkpoint snapshots for large workspaces, and fixes for streaming throttle, command backgrounding, and API key corruption
AI release Sep 15, 2026

Cline SDK 0.0.83

Adds hub-managed Agent Plugins
AI release Sep 15, 2026

Qwen Code cua-driver-rs 0.20.9

Qwen CUA Driver 0.20.9 ships codesigned binaries, relative coordinate support, and MCP payload filtering for AI code agents across macOS, Linux, Windows
AI release Sep 15, 2026

Deepseek Harness 0.1.6-alpha.1

Adds MCP URI profiles, headless mode with session-id and JSON output, and browser-use support via Playwright MCP and Stagehand
AI release Sep 15, 2026

Maple 3.4.1

Fixes Google and GitHub sign-in in native apps, desktop Apple sign-in through browser, and sign-in cancellation
AI release Sep 15, 2026

Claude Agent Sdk Typescript 0.3.272

Parity with Claude Code v2.1.272
AI release Sep 14, 2026

Maple 3.4.0

New encrypted Transport V2 client; Queued chat follow-ups; Agent Mode and account management improvements
AI release Sep 14, 2026

Ollama 0.34.1

Token repeat limit raised to 100. MLX runner checks free memory before loading models and evicts prefix cache from active conversations
AI release Sep 14, 2026

Claude Agent Sdk Typescript 0.3.271

Subagents can now run without user, project, and local CLAUDE.md files via omitClaudeMd flag. Fixes listSessions
AI release Sep 14, 2026

Qwen Code 0.23.4-nightly.20260914.f024b37689

Caps web search calls per session. Preserves Linux observations and REPL diagnostics in CUA mode
AI release Sep 14, 2026

llama.cpp b10970

Flash-attention on CDNA MFMA devices now uses fp32 accumulators
AI release Sep 14, 2026

Molmospaces 0.2.9

Stable release tagged before major update
AI release Sep 14, 2026

llama.cpp 0.4.1

Llama.cpp 0.4.1 adds Maple/Hy/Spark2.5 model support, fixes MoE/normalization bugs, refactors JSON schema handling, and updates ggml to v0.24.0
AI release Sep 14, 2026

opencode 1.18.31

Fixes ACP session state persistence when loading, resuming, or forking sessions
AI release Sep 14, 2026

Hermes Agent 0.21.3

Patch fixes remote session expiration on refresh bursts and state.db handle leaks in long-lived processes, rolling 338 PRs for Cloud agent auto-updates
AI release Sep 14, 2026

Qwen Code cua-driver-rs 0.20.8

Qwen Code CUA Driver 0.20.8 adds relative coordinate support, adaptive Linux input delivery, and MCP payload filtering for agent control workflows
AI release Sep 14, 2026

Kimi Code 0.43.0

AI sessions now auto-generate titles, session deletion added, and UI stability improved for long conversations and complex content rendering
AI release Sep 14, 2026

Open Interpreter 0.0.43

Syncs to upstream Codex rust-v0.154.0
AI release Sep 13, 2026

Qwen Code 0.23.3-nightly.20260913.faa395885e

Nightly build with DingTalk background response cleanup and message prefix removal
AI release Sep 13, 2026

llama.cpp b10947

Refactored JSON schema handling to use common internal representation; Updated json-schema-to-grammar
AI release Sep 12, 2026

llama.cpp b10932

Updates ggml-webgpu to a recent Dawn version
AI release Sep 12, 2026

Qwen Code 0.23.3-nightly.20260912.54aa66834b

Qwen Code adds cross-session messaging via peer endpoint, improves web-shell scheduling and notifications, and fixes channel persistence and PTY resource cleanup
AI release Sep 12, 2026

Claude Agent Sdk Typescript 0.3.270

Updated to parity with Claude Code v2.1.270
AI release Sep 12, 2026

Mistral Vibe 2.25.4

Connector discovery now excludes raw HTTP connectors without MCP tool support
AI release Sep 11, 2026

Qwen Code 0.23.3-nightly.20260911.aaa6a32aae

Remove obsolete background response aggregation; Feat(channels)!: remove message prefix filtering; Widen the replayed supersede-cede timeline margin to deflake Scripts
AI release Sep 11, 2026

Hermes Agent 0.21.2

Patch release targeting state.db
AI release Sep 11, 2026

Elevenlabs Python 2.68.0

Accepts every music model ID and composition plan type in compose detailed
AI release Sep 11, 2026

Mistral Vibe 2.25.3

Adds /branch command to fork current conversation into new resumable session
AI release Sep 11, 2026

llama.cpp b10907

Fixed KV cache allocation for MTP context in DeepSeek2, GLM4MoE, and Cohere2MoE model architectures
AI release Sep 11, 2026

whisper.cpp 1.9.4

Whisper.cpp 1.9.4 fixes encoder callback timing, decoder state management, and syncs GGML 0.23.0 with multi-platform backend improvements
AI release Sep 11, 2026

Kernel Fun 0.2.0

First PyPI upload; V0.2.0.dev0 workflow could not resolve setup-uv so build never ran
AI release Sep 11, 2026

openclaw 2026.9.4

Recover from compatible failed updates: retain and restore previous package when schema and config checks prove rollback safe; Database migrations still need verified pre-update backup
AI release Sep 10, 2026

Sandbox Runtime 0.0.76

CLI exits after command when control-fd is a pipe; Root caller capabilities dropped in both sandbox modes
AI release Sep 10, 2026

Qwen Code 0.23.3

Qwen Code adds reasoning model presets, OpenAI Responses API support, cross-agent delegation, and improves session management and web UI stability
AI release Sep 10, 2026

Claude Code 2.1.268

Claude apps gateway pricing set in gateway.yaml flows to signed-in clients via managed settings so cost and telemetry match spend meter; Startup warning for gateways when access-control allow cidrs present
AI release Sep 10, 2026

llama.cpp b10899

Vulkan small M matrix optimizations for qwen: optimize m=1 mul mat A/B, allow split k with small M
AI release Sep 10, 2026

Anthropic Sdk Csharp 12.47.0

Anthropic C# SDK adds Managed Agents tool permissions, web_fetch error handling, and public GitHub repository mounting without tokens
AI release Sep 10, 2026

Anthropic Sdk Java 2.62.0

Anthropic SDK Java adds Managed Agents auto-mode tool permissions, public GitHub mounting, content_too_large error handling, and streaming performance improvements
AI release Sep 10, 2026

Anthropic Sdk Ruby 1.70.0

Adds auto-mode tool permissions for Managed Agents, content-too-large web fetch error code, user-profiles-2026-09-04 beta value
AI release Sep 10, 2026

Mistral Vibe 2.25.2

VS Code extension debug submenu with log-level picker, open log file, togglable session status panel showing agent stats
AI release Sep 10, 2026

HelixML 2.12.13

Org bots now separate from people and apps, tenant quotas applied to agents, admin org list paginated for performance
AI release Sep 10, 2026

Dify 1.17.1

Self-hosted bundled Weaviate deployments must complete manual staged upgrade before starting 1.17.1
AI release Sep 10, 2026

openclaw 2026.6.35

Final June 2026 LTS release
AI release Sep 10, 2026

Cline Desktop 0.0.25

ChatGPT Subscription now filters models access
AI release Sep 10, 2026

Deepseek Harness 0.1.5-rc.1

DeepSeek DeepSeek-V41-Flash ( deepseek-flash ), @LegGasai; Web:,, @CreatixChu; Steer; "", Steer @Dudu-0223, @LegGasai
AI release Sep 9, 2026

Qwen Code 0.23.2

Qwen Code 0.23.2 adds remote one-command startup with token auth, improves split-view navigation, enables web search, and fixes agent failure handling
AI release Sep 9, 2026

langchain-openai== 1.6.2

Adds GPT-6 Astra reasoning efforts and bumps httpx2 to 2.12.0
AI release Sep 9, 2026

Claude Agent Sdk Typescript 0.3.267

Added browser SSE transport query and sequence tracking, system prompt recording now persists mid-session changes
AI release Sep 9, 2026

ComfyUI 0.35.0

Drops retiring Veo 2 and 3.0 models; Adds Recraft V4 Styles
AI release Sep 9, 2026

HelixML 2.12.12

Wakes stopped agents on message receipt; Fixes light-mode text visibility
AI release Sep 9, 2026

Hugging Face Transformers 5.17.0

Adds HYV4, a 780B MoE model activating 49B parameters per token
AI release Sep 9, 2026

Client Python 2.10.0

Removes 19 methods including campaigns and chatcompletionevents
AI release Sep 9, 2026

llama.cpp b10877

Converts FILL to 2D workgroup distribution to avoid exceeding maxComputeWorkGroupCount on Intel GPUs
AI release Sep 9, 2026

vLLM 0.29.0

594 commits from 277
AI release Sep 9, 2026

Kimi Code 0.42.0

Subagent model pool now always enabled, experimental Updates panel added, media previews in composer, and tool-call output collapsing for cleaner transcripts
AI release Sep 9, 2026

opencode 1.18.30

Adds Astra system prompt for GPT-6 models
AI release Sep 8, 2026

Claude Agent Sdk Typescript 0.3.266

Updated to parity with Claude Code v2.1.266
AI release Sep 8, 2026

Qwen Code 0.23.1

Qwen Code 0.23.1 retires the webui, adds workflow visualization, session management, and improved IPC messaging for multi-agent coordination
AI release Sep 8, 2026

Deepseek Harness 0.1.5-alpha.1

KV Cache now preserves across dynamic system prompt updates, sidebar redesign adds tabbed panes, and Agent API refactored for explicit agent passing
AI release Sep 8, 2026

llama.cpp b10864

Reverts HIP build prop.integrated change
AI release Sep 8, 2026

langchain-openai== 1.6.1

Supports Azure AD auth with OpenAI 3.8; Bumps max completion tokens in cache test
AI release Sep 8, 2026

Elevenlabs Python 3.0.0-alpha.1

Alpha release with agents rename, orchestrator config changes, and generated websocket clients
AI release Sep 8, 2026

Open Interpreter 0.0.42

Improves provider discovery and adds Ollama-Qwen tool-use diagnostics
AI release Sep 7, 2026

llm CLI 0.35

Adds GPT-6 Astra model support
AI release Sep 7, 2026

Hermes Agent 0.21.1

Hermes Agent v0.21.1 rolls up 5,139 commits with codebase modularization, performance improvements, MCP authorization, and delegation reliability fixes
AI release Sep 7, 2026

Qwen Code 0.23.0-nightly.20260907.f1ed3bc31a

Workflow visualization and session projection performance
AI release Sep 7, 2026

llama.cpp b10850

Fixed L2_NORM batch array initialization to resolve GCC compiler warnings in aarch64 Release builds
AI release Sep 7, 2026

Elevenlabs Python 2.67.0

Stops the OMIT sentinel from reaching the realtime TTS connection
AI release Sep 7, 2026

Cli 1.2.0

Install elevenlabs-cli 1.2.0 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell
AI release Sep 7, 2026

Qwen Code cua-driver-rs 0.20.4

CUA driver binaries now support relative coordinates and textual MCP payload filtering via environment flags, with platform-specific signing and architecture coverage
AI release Sep 7, 2026

Qwen Code 0.23.1-preview.2

Adds workflow-run visualization and management in the web shell; Synchronizes mid-turn quit completion in integration tests
AI release Sep 6, 2026

llama.cpp b10828

Fixes GDN normalization to use rsqrt instead of max for gated delta net q/k, matching flash-linear-attention spec
AI release Sep 6, 2026

Qwen Code 0.23.0-nightly.20260906.92a8a8d179

Qwen Code adds dynamic workflow visualization, IPC message expiration, session resource catalog, live subagent status display, and clickable OSC 8 links in VP mode
AI release Sep 6, 2026

InvokeAI Version 6.14.1

Bug fixes for 6.14; Adds minor features that missed the prior cut
AI release Sep 6, 2026

Qwen Code 0.23.0-nightly.20260905.0c945a6136

Nightly build adding workflow visualization and session-projection performance work
AI release Sep 5, 2026

Ollama 0.34.0

Ollama adds ChatGPT Desktop integration, improves structured output on Apple Silicon, and supports OpenAI-compatible client tool search
AI release Sep 5, 2026

openclaw 2026.9.2

Chat and dashboard responsiveness improvements during long-transcript processing
AI release Sep 5, 2026

llama.cpp b10818

SYCL backend fixes and Kronecker FWHT support restored
AI release Sep 5, 2026

Qwen Code 0.23.0

Qwen Code 0.23.0 adds git state hints in branch picker, scoped workspace memory with permission boundaries, enterprise Git host extension installs, and improved session routing for multi-agent workflows
AI release Sep 4, 2026

opencode 1.18.29

Fixes OAuth model filtering for integer GPT versions; Gpt-6-astra now shows for OpenAI subscription users
AI release Sep 4, 2026

Asta Autodiscovery 1.0.1

Published to PyPI: asta-autodiscovery 1.0.1
AI release Sep 4, 2026

Anthropic Sdk Typescript 0.124.0

Adds Claude Tag category and user breakdowns to usage reports, workspace ID support, named types for compliance settings
AI release Sep 4, 2026

langchain-core== 1.6.2

Adds async tools support and avoids mutation in certain code paths
AI release Sep 4, 2026

Claude Agent Sdk Typescript 0.3.261

Plugin delivery over stdin; Fixes Windows start failures with many plugins
AI release Sep 4, 2026

Claude Code 2.1.261

Plugin delivery over stdin to avoid Windows command-line length failures
AI release Sep 4, 2026

llama.cpp 0.4.0

Adds Qwen3.8-Flash-Next and Nemotron-3-Puzzle support, on-demand tensor reading, per-slot context limits, video input, GGML 0.23.0 with sparse attention and RDMA
AI release Sep 4, 2026

llama.cpp b10813

Build 10794 refactors SYCL to use global var for GGML SYCL ENABLE MKL FA
AI release Sep 4, 2026

Deepseek Harness 0.1.3-alpha.1

Web file uploads, proxy support, macOS Python SDK runtime, image rendering, and model discovery improvements enable richer agent interactions and cross-platform tooling
AI release Sep 4, 2026

Kimi Code 0.41.0

Kimi Code adds multi-agent collaboration mode, enables turn-level file history, and improves context management and background agent workflows
AI release Sep 4, 2026

Mistral Vibe 2.25.0

Adds /skills browser with search and filter; Shared skills sync on session start
AI release Sep 4, 2026

Deepseek Harness 0.1.2-rc.1

Oh-my-dsh DSH skill
AI release Sep 4, 2026

Anthropic Cli 1.30.0

Adds ant apply for managing agents, skills, environments, memory stores, and deployments as code; Adds Claude Tag category and user breakdowns to usage reports
AI release Sep 3, 2026

llama.cpp b10791

Fixes idefics3 preprocessing in mtmd module
AI release Sep 3, 2026

Asta Autodiscovery 1.0.0

Published to PyPI: asta-autodiscovery 1.0.0
AI release Sep 3, 2026

langchain== 1.4.0

Introduces langchain.mcp namespace and MCPAdapter, omits middleware trace inputs for performance
AI release Sep 3, 2026

langchain-anthropic== 1.7.1

Adds Claude Fable 5.1 support, omits middleware trace inputs
AI release Sep 3, 2026

HelixML 2.12.10

Preserves server-owned secret fields on PUT, shows project creation errors, always displays new chat action
AI release Sep 3, 2026

Qwen Code 0.23.0

Qwen Code 0.23.0 adds scoped workspace memory, deterministic review workflows, enterprise Git host support, and improved session routing for multi-agent coordination
AI release Sep 3, 2026

Cli mistral 0.4.1

Apps capability now three-way merges generated files instead of overwriting, preserving manual edits to Helm values and compose overlays
AI release Sep 3, 2026

Deepseek Harness 0.1.2-rc.1

,System prompt @07akioni, @lsdsjy; @yixiangihsiang; Token, @hypatiamay, @ZiyaZhang, @Yifffan; , @LegGasai
AI release Sep 3, 2026

Qwen Code Live Host 0.2.0

OpenTUI migration batch covering dialogs, commands, session-rewind; Model-proposed Goal approval dialog
AI release Sep 3, 2026

Cline Desktop 0.0.22

Cline Desktop adds session import from Claude Code and other tools, organizes scheduled runs, enables macOS voice input, and updates model defaults across 36 providers
AI release Sep 2, 2026

opencode 1.18.27

Raises default provider header timeout to five minutes to reduce startup failures for slow models
AI release Sep 2, 2026

llm CLI 0.34

Llm logs --usage Markdown output now includes response duration in milliseconds and human-readable form
AI release Sep 2, 2026

HelixML 2.12.9

Frontend waitlist routing fix, OpenRouter pricing refresh, and stale sandbox reconciliation
AI release Sep 2, 2026

Elevenlabs Python 2.66.0

Adds file IDs to sendMultimodalMessage method
AI release Sep 2, 2026

Elevenlabs Js 2.66.0

Adds fileIds to sendMultimodalMessage method
AI release Sep 2, 2026

Deepseek Harness 0.1.2-alpha.5

Fixes upgrade regression that prevented app startup and lost session titles after updating from prior versions
AI release Sep 2, 2026

llama.cpp b10754

Fixes out-of-bounds reads in Adreno OpenCL image kernels; Clamps q4 K decode GEMV fetch row on padded grids
AI release Sep 2, 2026

Kimi Code 0.40.0

Kimi Code 0.40.0 enables secondary model pool, adds plugin marketplace in web settings, blocks dangerous shell commands in Auto mode, and fixes config preservation and UI rendering issues
AI release Sep 2, 2026

langchain== 1.4

LangChain 1.4 adds Model Context Protocol integration with FastMCP 4.0.1, enabling structured tool calling across multiple MCP servers via LangGraph interrupts
AI release Sep 2, 2026

Cline Desktop 0.0.22

Import history from Claude Code, Codex, and opencode
AI release Sep 2, 2026

Ollama 0.33.3

Honors GGUF model-defined default parameters; Updates MLX and llama.cpp
AI release Sep 1, 2026

Cline Desktop 0.0.22-beta.1

Composio connectors now register tools directly in desktop runtime with safer OAuth revocation, web search enabled, improved agent cancellation and marketplace explorer
AI release Sep 1, 2026

Claude Agent Sdk Typescript 0.3.258

Updated to parity with Claude Code v2.1.258
AI release Sep 1, 2026

opencode 1.18.26

Claude 5 sessions tolerate stale thinking blocks instead of failing after prompt or tool changes
AI release Sep 1, 2026

Elevenlabs Swift Sdk 4.0.0-alpha.1

Redesigns the SDK public API
AI release Sep 1, 2026

llama.cpp b10750

Adds recurrent-state rollback support for MTP speculative decoding in Qwen4 experimental models
AI release Sep 1, 2026

Anthropic Cli 1.29.0

User profiles add external_user_onboarded_at tracking, organization compliance settings, and memory-store schema updates
AI release Sep 1, 2026

Anthropic Sdk Typescript 0.123.0

SDK adds external_user_onboarded_at to user profiles, organization compliance settings, and fixes credential file bundling in non-Node environments
AI release Sep 1, 2026

Anthropic Sdk Python 1.3.0

SDK adds user profiles with access type tracking, organization compliance settings, memory-store schema updates, and fixes AWS region resolution, batch result streaming, and multipart file uploads
AI release Sep 1, 2026

langchain== 1.4

LangChain 1.4.0a3 adds langchain.mcp namespace for adapting MCP servers as tools with discovery, caching, and human-in-the-loop interrupt support
AI release Sep 1, 2026

Deepseek Harness 0.1.2-alpha.4

Deepseek Harness adds bidirectional agent messaging, enables web_fetch across SDKs, and refactors session event APIs with stronger typing
AI release Sep 1, 2026

Kimi Cli 1.50.0

Deprecation-aware update flow with one-key migration to Kimi Code
AI release Sep 1, 2026

openclaw 2026.8.2

Open Home in right or bottom dock; Preview or remove work-context snapshot; Attach selected text to messages
AI release Sep 1, 2026

Qwen Code cua-driver-rs 0.20.3

Qwen Code CUA driver adds macOS/Linux/Windows prebuilt binaries with relative coordinate support, MCP payload filtering, and fixes permission decoupling plus Anthropic stream hangs
AI release Aug 31, 2026

llama.cpp b10726

Adds Vulkan top-k radix sort shader for Qwen 3.8 Flash Next
AI release Aug 31, 2026

Hermes Agent 0.21.0

Bot Mode bundles multi-agent collaboration into desktop app with group chats, cron jobs gain persistent memory, and agents can steer subagents live mid-flight
AI release Aug 31, 2026

Qwen Code 0.22.3-nightly.20260831.3a0c4c6108

Qwen Code adds scoped workspace memory tasks, fixes Anthropic stream hangs and agent model routing, and improves review convergence with circuit breaker logic
AI release Aug 31, 2026

Open WebUI 0.11.3

Open WebUI 0.11.3 fixes database upgrade failures that blocked migrations from prior versions, repairs chat branch persistence, and improves accessibility contrast across menus and dropdowns
AI release Aug 31, 2026

Cli 1.0.24

Windows stdin file support, coding agent setup command, and quota display fixes for accurate usage tracking
AI release Aug 31, 2026

OpenClaw 2026.8.1

OpenClaw 2026.8.1 adds conversation search, cross-device session mobility, durable progress tracking, structured agent responses, interactive dashboards, masked credential requests, recurring work approval, and richer media handling
AI release Aug 30, 2026

Deepseek Harness 0.1.2-alpha.2

Deepseek Harness adds connection-failure visibility, Agent Preset switching, token usage display, and fixes Node.js 24 compatibility issues
AI release Aug 30, 2026

llama.cpp b10689

Allows passing alloc dependencies in graph optimize; Adds alloc dependency tests
AI release Aug 29, 2026

llama.cpp b10687

Optimized Adreno GPU matrix multiplication kernels, improving prefill performance% on X2E and 9% on A7X generations through better GEMM routing
AI release Aug 29, 2026

koboldcpp 1.120

Adds DirectIO model load mode; Fixes assistant gen prefill trigger and failsafe mode bug. Mlock and mmap can now be combined
AI release Aug 29, 2026

Qwen Code 0.22.3-nightly.20260829.e5cb60ad48

Web shell now displays git state hints beside branch actions, review workflows emit as generated scripts, and user prompts respect allow rules with auto-approval
AI release Aug 28, 2026

llama.cpp b10678

Reduces number of graph splits for Qwen4Exp model
AI release Aug 28, 2026

Deepseek Harness 0.1.2-alpha.1

Deepseek Harness adds collapsible system prompts, resizable conversation streams, token usage visibility, and plugin-driven provider authentication controls
AI release Aug 28, 2026

Claude Agent Sdk Python 0.2.147

Bundles Claude CLI version 2.1.250
AI release Aug 27, 2026

Claude Code 2.1.248

Restricted mode removes built-in command and code tools, keeps file tools inside working directory, refuses bypassPermissions, ignores user and project settings
AI release Aug 27, 2026

langchain-fireworks== 1.6.1

Drops reasoning history blocks
AI release Aug 27, 2026

llama.cpp b10662

Adds nanbeige4.2-3B model support
AI release Aug 27, 2026

Maple 3.3.9

Maple 3.3.9 consolidates SDK and proxy into the main repo, makes Quick the default chat model, and ships native proxy binaries for all platforms
AI release Aug 27, 2026

Anthropic Sdk Typescript 0.122.0

Beta files and skills namespaces now use GA shapes, drops dated beta header pins
AI release Aug 27, 2026

Ollama 0.33.2

Ollama fixes dark mode support, prevents duplicate macOS instances, and stops interrupting Claude Desktop requests during model catalog updates
AI release Aug 27, 2026

Anthropic Sdk Python 1.2.0

Files and skills namespaces now use GA shapes; Fixes binary file uploads for AWS Bedrock signing
AI release Aug 27, 2026

AnythingLLM 1.16.1

Overhauls UI for long-horizon agentic tasks into single collapsible element
AI release Aug 27, 2026

Mistral Vibe 2.24.5

Mistral Vibe adds fuzzy search for MCP servers, optimizes startup speed with lazy loading, and fixes trust prompts, link normalization, theme application, and connection pool handling
AI release Aug 27, 2026

langchain-anthropic== 1.7.0

Adds top-level param for skills via container, updates thinking display mode, supports 1.0 SDK, auto-appends advisor-tool-2026-03-01
AI release Aug 27, 2026

HelixML 2.12.7

HelixML 2.12.7 fixes model routing for org providers, masks MCP environment variables, enables image reading for vision models, and improves trigger visibility and task polling efficiency
AI release Aug 27, 2026

Hermes Agent 0.20.6

Hermes Agent 0.20.6 bundles 525 PRs with consent-gated profile browsing, desktop window isolation, remote MCP catalog expansion, TTL caching, OS-keychain encryption, and new model support
AI release Aug 26, 2026

Ollama 0.33.1

Ollama 0.33.1 adds Qwen3.8 Flash support, structured output for MLX models, and fixes Metal GPU timeouts during model loading
AI release Aug 26, 2026

Anthropic Sdk Php 0.44.0

Adds Admin API organization resources under client.beta.admin and SessionThreadAgentEntry type; Expands AnthropicBeta enum
AI release Aug 26, 2026

Anthropic Sdk Ruby 1.66.0

Adds thinking display mode beta, organization usage support, discriminated union module enums
AI release Aug 26, 2026

Mistral Vibe 2.24.4

Mistral Vibe adds LLM-generated session titles, queued message editing, reused model connections for speed, and fixes auth routing, rate-limit retries, and connection pooling issues
AI release Aug 26, 2026

Hugging Face Transformers 5.16.1

Adds GLM model support
AI release Aug 26, 2026

Qwen Code 0.22.2

Qwen Code 0.22.2 ships Node.js MCP server for persistent REPL, improved code review with temporal analysis and test criteria, and Computer Use SDK v0.20.0 with stable element tokens
AI release Aug 26, 2026

Cli 1.1.0

Install elevenlabs-cli 1.1.0 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell -ExecutionPoli
AI release Aug 26, 2026

llama.cpp b10636

Ui: disable the npm UI build (LLAMA BUILD UI=OFF)
AI release Aug 26, 2026

Hugging Face Transformers Release 5.16.0

Adds Qwen4-Exp model with GatedResidual, Qwen Sparse Attention, and Per-Layer Embedding components
AI release Aug 26, 2026

vLLM 0.28.0

584 commits from 270
AI release Aug 26, 2026

Cline SDK 0.0.80

Cline SDK fixes file handling crashes, redacts git credentials from prompts, adds seven model providers, and updates defaults across multiple platforms
AI release Aug 26, 2026

Cline 4.1.16

Cline 4.1.16 fixes cost display for subscription providers, workspace hook resolution across multiple VS Code windows, and credentials leakage to models
AI release Aug 26, 2026

Qwen Code 0.22.2-preview.1

Preview.1 adds explicit user opt-in for workflows, containerizes code review execution, and improves workflow safety with pre-spend validation
AI release Aug 25, 2026

InvokeAI 6.14.0

InvokeAI 6.14 adds video generation via Wan 2.2, supports Flux.2 Dev, Krea.2, Ernie, Ideogram 4, and enables multi-GPU, Intel XPU, and FP8 optimizations
AI release Aug 25, 2026

Claude Code Action 1.0.206

Use paths in delete files prompt example; Allow parentheses in valid branch names; Bound download job log against a stalled log fetch
AI release Aug 25, 2026

Claude Agent Sdk Typescript 0.3.246

Claude Agent SDK adds message tracing, cost basis reporting, managed pricing controls, and per-task interrupt handling for multi-agent workflows
AI release Aug 25, 2026

Open WebUI 0.11.1

Adds human-in-the-loop tool approval
AI release Aug 25, 2026

llama.cpp b10625

Scopes Qwen3-coder chat workarounds
AI release Aug 25, 2026

Maple 3.3.8

Agent Mode updated to Goose 1.47.0, desktop updates now route through protected Maple endpoint, release verification hardened
AI release Aug 25, 2026

Rslearn 0.1.14

Enhances EarthDaily integration with asset key resolution, per-pixel regression metrics bugfix, logger config saving fix
AI release Aug 25, 2026

Packages React 1.14.0

Adds external agent disconnected client event support
AI release Aug 25, 2026

Dify 1.17.0

E2B cloud sandbox backend for agent shell and code execution, home snapshots, skill management
AI release Aug 25, 2026

llama.cpp 0.3.0

Llama.cpp 0.3.0 adds dots3-note multimodal support, tensor-split for DeepSeek 4, multi-token prediction for GLM-4.5-Air, and WebP image decoding
AI release Aug 25, 2026

opencode 1.18.23

Fixed Cloudflare AI Gateway routing for Anthropic and third-party providers, plus GitHub OIDC auth in the TUI
AI release Aug 25, 2026

Claude Agent Sdk Typescript 0.3.245

Claude Agent SDK TypeScript synced to Claude Code v2.1.245, tracking latest model capabilities for agent development
AI release Aug 25, 2026

Qwen Code 0.22.0-nightly.20260825.22bb5e8b9f

Nightly build fixes shell session workspace handling, review comment logic, and autofix budgeting, plus adds token accounting and dynamic workflows
AI release Aug 24, 2026

qwen-mm-plugins-core 1.0.5

Added NIfTI volume visualization and 4D volume selection support for medical imaging workflows
AI release Aug 24, 2026

HelixML 2.12.5

HelixML adds OpenRouter provider support, project-scoped artifact hosting, editable model enforcement, trigger-based workflows, and mobile UI fixes
AI release Aug 24, 2026

Cli 1.0.0

Install elevenlabs-cli 1.0.0 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershell -ExecutionPoli
AI release Aug 24, 2026

llama.cpp b10610

Metal flash-attention tuning: 53 new f16 instantiations, per-device dispatch tables
AI release Aug 24, 2026

Elevenlabs Swift Sdk 3.3.0

Client-error parsing, type-safe tool results, realtime-thread allocation dropped from audio processor
AI release Aug 24, 2026

NanoClaw 2.3.0

Breaking change: classic single-bot Slack installs must migrate to per-agent provisioned apps
AI release Aug 24, 2026

Cli 1.0.0-alpha.3

Alpha.3 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershel
AI release Aug 24, 2026

OpenClaw 2026.8.1-beta.3

Adds GPT-5.6 reasoning support, Puppeteer CDP relay, Gateway lifecycle supervision, SQLite backup/restore, and durable ingress monitors
AI release Aug 24, 2026

Qwen Code cua-driver-rs 0.20.0

Prebuilt binaries for Qwen CUA Driver
AI release Aug 24, 2026

Qwen Code 0.22.0-nightly.20260824.3a1f86d805

Qwen Code fixes shell session context passing, review lenses, and autofix repair budgets while adding token accounting and dynamic workflow support
AI release Aug 23, 2026

llama.cpp b10603

GLM-4.5-Air MTP support added to llama.cpp for improved model inference efficiency
AI release Aug 23, 2026

Cline 4.1.14

Cline 4.1.14 updates model catalog with Claude Fable 5, Grok 4.6, DeepSeek V4 variants, and fixes telemetry for interactive session completion
AI release Aug 23, 2026

Qwen Code 0.22.0

Web shell now bounds transcript retention and trims oversized replays to prevent out-of-memory crashes
AI release Aug 23, 2026

Claude Agent Sdk Typescript 0.3.241

Claude Agent SDK TypeScript now matches Claude Code v2.1.241 capabilities
AI release Aug 23, 2026

Qwen Code 0.22.0-nightly.20260823.1007bcacfc

Qwen Code adds test validation for code fixes, temporal incident replay in reviews, and daemon session model persistence with shell and workflow parsing improvements
AI release Aug 22, 2026

llama.cpp b10588

Fixes clang LTO build issue
AI release Aug 22, 2026

Maple Proxy 0.3.2

Maple Proxy v0.3.2; All binaries include
AI release Aug 22, 2026

Cline 4.1.13

Cline 4.1.13 restores tool calling for custom OpenAI-compatible models, fixes Hub session persistence across restarts, and adds session identity to Langfuse traces
AI release Aug 22, 2026

llm CLI 0.33

Migrates to OpenAI Python library 3.x, switches HTTP client from httpx to httpx2
AI release Aug 22, 2026

Qwen Code 0.21.14-nightly.20260822.7a4566cb3b

Code review loop now explains settlement failures, web shell bounds transcript retention to prevent crashes, and autofix audits approaches instead of stopping on budget breaches
AI release Aug 21, 2026

llama.cpp b10568

CI switches to LLVM OpenMP on Windows; Drops non-redist debug build
AI release Aug 21, 2026

Ollama 0.33.0

Claude Desktop integration: toggle individual Ollama models on and off from the menu bar, choose models directly within Claude
AI release Aug 21, 2026

Maple 3.3.6

Agent Mode now supports image attachments, Goose runtime upgraded to 1.46.0, Linux package updates require confirmation, and RustSec advisory checks enforced daily
AI release Aug 21, 2026

Cline 4.1.12

Fixed enterprise MCP marketplace controls and restored tool calling for custom OpenAI-compatible models with empty capability lists
AI release Aug 21, 2026

Design.Md 0.2.0

Design.Md now records OlmoEarth subtitle roles and prevents duplicate version tags during releases
AI release Aug 21, 2026

Design.Md 0.1.0

Design.md publishes Skylight and EarthRanger design systems with agent skills framework to npm
AI release Aug 21, 2026

Claude Code Action 1.0.199

Fixes GraphQL URL handling, MCP server initialization, and tool allowlist validation in GitHub Actions integration
AI release Aug 21, 2026

Claude Agent Sdk Typescript 0.3.239

Claude Agent SDK now correctly applies US inference cost multipliers, fixes system prompt boundaries on multi-cloud providers, and improves background task visibility on reconnect
AI release Aug 21, 2026

llama.cpp 0.2.0

Llama.cpp 0.2.0 syncs ggml to 0.21.0, adds backend optimizations for CUDA/Metal/SYCL/OpenCL, and improves quantization kernel performance across hardware
AI release Aug 21, 2026

llm CLI 0.32.1

Pins OpenAI Python dependency to pre-3.0 to avoid requiring httpx on fresh installs
AI release Aug 21, 2026

opencode 1.18.21

Fixes unknown finish reason handling in model responses and improves Vertex AI multi-region routing; Desktop fixes include persistent file search results during loading
AI release Aug 21, 2026

langchain-perplexity== 1.4.1

Perplexity integration fixes message type handling, preserves caller parameters, and updates dependencies for compatibility
AI release Aug 21, 2026

Deepseek Harness 0.1.1-rc.2

DeepSeek adapter now uses Files API for image uploads with automatic preprocessing, reusing files to reduce API costs
AI release Aug 21, 2026

Hermes Agent 0.20.5

Hermes Agent 0.20.5 bundles 323 PRs with group threads, keyless web tier with free provider rotation, CLI improvements, execution guards, and desktop performance optimizations
AI release Aug 21, 2026

Cline Desktop 0.0.15

Cline Desktop adds durable todos and recurring schedules for agents, fixes checkpoint restore and hook handling, consolidates plugins into marketplace, and refreshes model catalog with eight new providers
AI release Aug 21, 2026

Cline SDK 0.0.76

Cline SDK adds model-driven image generation, workspace-scoped task scheduling, improved tool activity observability, and fixes hook execution, command routing, and session status tracking
AI release Aug 21, 2026

Qwen Code 0.21.15

Web Shell gains file attachment support with faster streaming, Qwen models expose reasoning toggles, review workflows support resumption, and Git credential persistence enables private repository access
AI release Aug 20, 2026

Maple 3.3.5

Maple 3.3.5 adds Word document support, expands Agent Mode with richer ACP sessions and reversible per-project trust controls, and blocks known compromised Rust crates
AI release Aug 20, 2026

Anthropic Sdk Python 1.0.0

Breaking change: httpx2 upgrade requires dependency refresh
AI release Aug 20, 2026

Mistral Vibe 2.24.3

Slash commands now work during agent execution, Python security updates applied, and connector bootstrap errors properly surfaced instead of silently failing
AI release Aug 20, 2026

LocalAI 4.9.0

Authentication now deny-by-default, chat adds context compression, MiniMax-H3 video generation, and improved operator visibility across 146 pull requests
AI release Aug 20, 2026

whisper.cpp 1.9.3

Whisper.cpp 1.9.3 syncs GGML backend with performance optimizations across CUDA, Metal, SYCL, and other accelerators including quantization support and memory improvements
AI release Aug 20, 2026

opencode 1.18.19

Native OpenAI and Anthropic passthroughs for Cloudflare AI Gateway, improved rate limiting, and fixed provider authentication display and cost calculation bugs
AI release Aug 20, 2026

llama.cpp b10505

Adds dedup-cache-models preset option to server
AI release Aug 20, 2026

Claude Code Action 1.0.197

Fixed credential handling incompatibility with GitHub Actions checkout v6+ to prevent unintended credential exposure
AI release Aug 19, 2026

langchain-openai== 1.6.0

Langchain-openai adds standard model exception types and improves error handling for unexpected OpenAI API response types
AI release Aug 19, 2026

langchain-anthropic== 1.6.0

LangChain's Anthropic integration adds standard model exception types and fixes directory search scope issues
AI release Aug 19, 2026

Maple 3.3.4

Maple 3.3.4 adds mid-run request queuing with editing, better Agent prompt history navigation, and improved resilience to inference failures
AI release Aug 19, 2026

LlamaIndex 0.14.24

Fixes file-handle leaks in HotpotQA evaluator and preserves oversized leaf nodes in CodeSplitter
AI release Aug 19, 2026

Cli 1.0.0-alpha.2

Alpha.2 Install prebuilt binaries via shell script curl --proto ' =https ' --tlsv1.2 -LsSf | sh Install prebuilt binaries via powershell script powershel
AI release Aug 19, 2026

Packages React 1.13.0

Adds onContextUsage callback for context usage server events
AI release Aug 19, 2026

Ollama 0.32.15

Model metadata caching halves time-to-first-token, parser error handling fixed, Qwen system messages normalized
AI release Aug 19, 2026

langchain-core== 1.6.0

Resolves tool schema serialization issues, adds standard exception types, and improves Windows compatibility in langchain-core
AI release Aug 19, 2026

Deepseek Harness 0.1.0-rc.8

DeepSeek Harness adds multimodal image support, installable subagents, Windows PowerShell sessions, and fixes image payload failures plus OpenAI gateway compatibility
AI release Aug 19, 2026

HelixML 2.12.4

HelixML adds DeepSeek code agent runtime, GPU-optional headless tasks, durable agent cancellation, and improved sandbox resilience across API and CLI
AI release Aug 19, 2026

Anthropic Sdk Java 2.55.0

Anthropic Java SDK adds files and memory store APIs, fixes message stream accumulation bugs, and upgrades build tooling to Gradle 9 and Kotlin 2.3
AI release Aug 19, 2026

Hugging Face Transformers Patch release 5.15.1

Fixes DFlash and MTP candidate generator issues, resolves image processing on accelerators with Lanczos filter
AI release Aug 18, 2026

Kimi Code 0.37.2

Kimi Code 0.37.2 expands subagent detail panels and adds optional multi-tab sidebar navigation in Settings Lab
AI release Aug 18, 2026

langchain-openai== 1.5.2

Fixes reasoning item boundaries, adds gateway metadata extraction, and extends token counting support to o-series models
AI release Aug 18, 2026

Mistral Vibe 2.24.2

Session picker, runtime log control, and worktree management ship alongside faster startup and session resume for improved AI agent workflows
AI release Aug 18, 2026

llama.cpp b10486

Fixes LFM2 image tiling threshold; Cross-platform refactor
AI release Aug 18, 2026

llama.cpp 0.1.2

Llama.cpp synced GGML 0.20.2, added integer tokenizer scores, improved CUDA performance on DGX, and fixed xcframework builds
AI release Aug 18, 2026

langcrew-agentx== 0.1.10

Sets repository.url for npm provenance; Package.json metadata fix
AI release Aug 18, 2026

qwen-mm-plugins-edu-agent 1.0.2

Normalizes local file URIs across capabilities; Cross-platform path fix
AI release Aug 18, 2026

qwen-mm-plugins-core 1.0.3

Isolates 3D worker from MCP stdio; Windows process-handle and pipe fixes
AI release Aug 18, 2026

Hermes Agent 0.20.4

Hermes Agent 0.20.4 stabilizes 74 merged PRs including desktop UI improvements, bot group-chat fixes, NVIDIA security scanning on skill installs, and SessionDB performance hardening
AI release Aug 18, 2026

Qwen Code dsw-eas-tb-smoke-20260818-r2

Qwen improved end-to-end credential refresh handling in code tasks, verified against SWE-bench and Terminal-Bench benchmarks
AI release Aug 18, 2026

langchain-openai== 1.5

Adds gateway metadata extraction from response headers. Fixes o-series token counting
AI release Aug 18, 2026

Cline Desktop 0.0.14-beta.1

Beta release adds cloud sessions for syncing work across devices, avatar overlay companion, SSH remote execution, and voice input with model-driven image generation
AI release Aug 18, 2026

Qwen Code 0.21.11-nightly.20260818.259951c53e

Added session registry with qwen sessions ps, improved web-shell SSE handling and session management, enhanced agent workflow persistence, and added /advisor CLI command for code review feedback
AI release Aug 17, 2026

Olmoearth Pretrain Minimal Publish 0.0.7

Removed max_sequence_length constraint to enable flexible sequence handling in pretraining pipeline
AI release Aug 17, 2026

Claude Agent Sdk Typescript 0.3.234

Claude Agent SDK TypeScript adds ANTHROPIC_API_KEY source reporting, permission-class message delivery, effort-level tracking, and fixes unused type exports
AI release Aug 17, 2026

Hermes Agent 0.20.3

Hermes Agent 0.20.3 bundles MCP 2.x SDK migration, stateless protocol support, Bot Mode plugin, subprocess hardening, and cron scheduler self-healing fixes
AI release Aug 17, 2026

llama.cpp b10470

CI; Explicitly pushes release tag before creating GitHub release
AI release Aug 17, 2026

Deepseek Harness 0.1.0-rc.7

Deepseek Harness adds durable image attachments in MCP/ACP modes, Job Panel for subagent task management, fixes latency and stack overflows, and introduces configurable reasoning effort levels
AI release Aug 17, 2026

Qwen Code 0.21.13

Web shell now accepts text files as named attachments, conversation forking preserves checkpoints, review skill uses platform subcommands, and stopped takeovers get autofix/needs-human labels
AI release Aug 16, 2026

InvokeAI 6.14.0

Adds video generation via Wan 2.2; Release candidate 2
AI release Aug 16, 2026

Hermes Agent 0.20.2

Hermes Agent v0.20.2 consolidates 397 PRs across desktop, CLI, gateway, and auth with prompt caching, model routing, and platform robustness improvements
AI release Aug 16, 2026

koboldcpp 1.119

Video generation and I2V support with Minimax H3
AI release Aug 16, 2026

llama.cpp b10452

Removes some ggml concat calls; Model-layer refactor
AI release Aug 16, 2026

OpenClaw PR #124528 Gateway profile evidence

CPU profiling data for Gateway PR 124528; Three-node, twelve-turn rig
AI release Aug 16, 2026

Qwen Code 0.21.12-preview.5

Upstream release notes did not include a readable summary.
AI release Aug 15, 2026

llama.cpp b10447

Adds Kimi-K3 text-model support with hybrid KDA and MLA attention
AI release Aug 15, 2026

OpenClaw 2026.8.1-beta.2

Binds shared secrets to exact HTTPS destination hosts; Unbound substitution now fails closed before plaintext egress
AI release Aug 15, 2026

Qwen Code 0.21.12

Qwen Code adds drag-and-drop file uploads to Web Shell, implements diff growth limits in autofix reviews, requires executed witnesses for critical findings, and adaptively expands daemon journal capacity to 256 MiB
AI release Aug 14, 2026

llama.cpp b10434

Llama.cpp now passes reasoning_effort parameter through chat templates, enabling fine-grained control over model reasoning depth in inference
AI release Aug 14, 2026

langchain-openrouter== 0.2.8

LangChain OpenRouter now preserves cost metadata and provider information in usage chunks and response metadata
AI release Aug 14, 2026

Elevenlabs Python 2.64.0

Adds extra setup config escape hatch for on-prem deployments
AI release Aug 14, 2026

Client Ts typescript 2.6.3

OpenAPI Doc; Speakeasy CLI 1.763.6 (2.884.13); Typescript v2.6.3
AI release Aug 14, 2026

Cline SDK 0.0.75

Provider-executed web search, dedicated Cline gateway provider, and Hub daemon stability fixes prevent session crashes during multi-build installations
AI release Aug 14, 2026

Qwen Code DSW EAS SWE + Terminal-Bench E2E r2

Qwen3.7-plus model achieves 100% on SWE-bench verified, resolving one software engineering task end-to-end with artifacts and verifier evidence
AI release Aug 14, 2026

Ollama 0.32.11

Ollama added DeepSeek Harness and Meta Muse Code agent support, plus web search in OpenAI-compatible Responses API
AI release Aug 14, 2026

Qwen Code 0.21.11-nightly.20260814.45c2e73080

Qwen Code adds workspace file uploads, fixes session handling and UI jitter, patched sharp dependency vulnerability, and improves review workflows with witness verification and budget controls
AI release Aug 13, 2026

Claude Code Action 1.0.192

Claude Code Action improves GitHub Actions pagination, preserves structured tool output, and detects binary files rather than extension
AI release Aug 13, 2026

ComfyUI 0.33.1

Fixes KSamplerAdvanced nested latent handling, adds Minimax Music 3 and Bria image tools, improves VRAM management across platforms
AI release Aug 13, 2026

llama.cpp b10419

OpenVINO backend gains Qwen3.5 support, memory optimizations for GPU inference, and fixes for stateful RoPE accuracy and recurrent state handling
AI release Aug 13, 2026

AnythingLLM 1.16.0

AnythingLLM adds image generation, mid-session tool toggling, folder drag-drop uploads, and proper generation abortion to stop ghost inference
AI release Aug 13, 2026

InvokeAI 6.13.8

Patches two critical security vulnerabilities: arbitrary code execution via crafted URL payloads and unauthorized network connection attempts
AI release Aug 13, 2026

NanoClaw 2.2.0

Plugin-stamped agents now update in place with dry-run plans, MCP servers support working directories and HTTP URLs, and templates conform to Agent Plugins 1.0.0 spec for portability
AI release Aug 13, 2026

Hermes Agent 0.20.1

Hermes Agent 0.20.1 consolidates 656 merged PRs with stabilization fixes across desktop, gateway, installers, and provider tools
AI release Aug 13, 2026

Anthropic Cli 1.23.0

Anthropic CLI adds output_behavior flag to dream creation for choosing between new memory store or in-place input update
AI release Aug 13, 2026

Anthropic Sdk Ruby 1.62.0

Output behavior control for memory stores: create new or update in place. Bedrock now uses default-credentials hook
AI release Aug 13, 2026

Anthropic Sdk Python 0.122.0

Adds output-behavior control for memory-store creation. Fixes async SigV4 signing in Bedrock clients
AI release Aug 13, 2026

HelixML 2.12.3

Fixed MCP proxy resolution, Claude thread recovery, and rate limiter deadlock while adding persistent task terminal, workspace inspection, and inline task editing
AI release Aug 13, 2026

Client Python 2.9.3

OpenAPI Doc; Speakeasy CLI 1.763.6 (2.884.13); Python v2.9.3
AI release Aug 13, 2026

The builder’s guide to GPT‑5.6

Learn how startups use GPT-5.6 to build faster, more cost-efficient AI agents with smarter model selection and new Responses API capabilities
AI release Aug 13, 2026

Qwen Code DSW EAS Harbor full E2E 2026-08-13 r3

Non-production full SWE-bench Verified E2E validation
AI release Aug 13, 2026

Cline CLI 3.0.54

Claude Code provider now runs native tools with workspace anchoring and permission rules, tool-call JSON validation rejects malformed payloads instead of silently repairing them, and Hub daemon upgrades directionally without interrupting sessions
AI release Aug 13, 2026

Cline SDK 0.0.74

Claude Code provider now declares native tools and respects workspace boundaries and user permissions, tool-call JSON corruption fixed, Hub daemon upgrades directionally, and telemetry now accurately reports token usage without redundant counting
AI release Aug 13, 2026

Kimi Code 0.36.0

Experimental fullscreen TUI mode, configurable model pools for subagents, LaTeX rendering, improved interrupt handling, and workspace trust enhancements
AI release Aug 13, 2026

Qwen Code 0.21.11

Qwen Code adds Agent Plugins v1 support, multi-agent workflows via /coordinate, and OpenTelemetry observability for session lifecycle tracking
AI release Aug 13, 2026

langchain-anthropic== 1.5.6

LangChain Anthropic 1.5.6 fixes tool result block normalization and corrects model profile data for recent Claude versions
AI release Aug 12, 2026

Ollama 0.32.10

Ollama 0.32.10 changes default repeat penalty to 1.0 for faster speculative decoding, speeds NVFP4 prefill%, and fixes blob verification on shared digests
AI release Aug 12, 2026

Claude Agent Sdk Typescript 0.3.229

SDK now exposes terminal slash commands to clients and properly surfaces request-body-size limits as API errors instead of image errors
AI release Aug 12, 2026

opencode 1.18.17

Session compaction now preserves complete recent turns and produces clearer summaries, plus fixes for PDF attachments, MERGE Gateway reasoning, and model routing
AI release Aug 12, 2026

Asta Bench Leaderboard Design review attachments

Rendered review evidence hosted outside the source tree and referenced from pull-request metadata
AI release Aug 12, 2026

Maple Proxy 0.3.1

Maple Proxy v0.3.1; All binaries include
AI release Aug 12, 2026

Kimi Code 0.35.0

Tasks panel now displays live subagent progress, image/video results open in fullscreen with zoom, token counting fixed, and startup freezes from search index loading eliminated
AI release Aug 12, 2026

llama.cpp b10369

Build b10375 tightens bare function parsing for Qwen models
AI release Aug 12, 2026

Qwen Code 0.21.10-nightly.20260812.a64d1291d2

Qwen Code fixes web-shell session navigation, bounds daemon buffers, improves keyboard interactions, and adds Agent Plugins v1 support
AI release Aug 11, 2026

Maple Proxy 0.3.0

Maple Proxy v0.3.0; All binaries include
AI release Aug 11, 2026

ComfyUI 0.32.0

ComfyUI 0.32.0 adds LTX 2.5 support, optimizes memory handling for H3 models, and improves nested tensor debugging for complex workflows
AI release Aug 11, 2026

langchain== 1.3.15

LangChain 1.3.15 adds state_schema to wrap_tool_call, exposes trace_policy on AgentMiddleware, and fixes middleware control flow, tool call handling, and structured output parsing
AI release Aug 11, 2026

Cline CLI 3.0.53

CLI now detects stale daemon upgrades, fixes reasoning model compaction, adds Fable 5 to Vertex catalog, and routes custom model IDs correctly
AI release Aug 11, 2026

langchain-core== 1.5.4

Langchain-core 1.5.4 fixes Pydantic 2.14 compatibility, stops StructuredPrompt from mutating caller kwargs, and preserves tool argument schemas
AI release Aug 11, 2026

Anthropic Sdk Go 1.63.0

Go SDK adds output_behavior control for dream memory creation, fixes agent toolset path handling and Vertex auth wrapping
AI release Aug 11, 2026

Mistral Vibe 2.24.1

Mistral Vibe 2.24.1 adds inline completions, improves agent resume performance, fixes MCP server error handling and voice transcription visibility, and patches security scoping for sensitive file access
AI release Aug 11, 2026

Ollama 0.32.9

Ollama adds NVIDIA's Nemotron 3.5 Lightning, a 30B mixture-of-experts model optimized for always-on agent deployment
AI release Aug 11, 2026

llama.cpp b10359

Switches ROCm target to 7.14, the first production release using TheRock build system
AI release Aug 11, 2026

vLLM 0.27.1

VLLM adds support for quantized DSpark Markov heads, enabling efficient inference with compressed attention mechanisms
AI release Aug 11, 2026

Client Ts typescript 2.6.2

OpenAPI Doc; Speakeasy CLI 1.763.6 (2.884.13); Typescript v2.6.2
AI release Aug 10, 2026

Ollama 0.32.8

Muse Glimmer model now available across all platforms, optimized for coding agents and personal assistants with MLX performance on Apple Silicon
AI release Aug 10, 2026

vLLM 0.27.0

561 commits from 242; Review the changelog before upgrading production inference workloads
AI release Aug 10, 2026

llama.cpp b10344

Added MTP (Multi-Token Prediction) support for Nemotron models, enabling faster inference for this architecture
AI release Aug 10, 2026

Qwen Code 0.21.9

Qwen Code adds plugin installation from multiple sources, Local Control pairing via QR code, drag-and-drop image support, and improves code review performance for large diffs
AI release Aug 10, 2026

Ollama 0.32.7

Muse Glimmer, Meta's 30B multimodal agent model, now runs locally on Ollama with Apple Silicon optimization and image input support
AI release Aug 10, 2026

Hugging Face Transformers Release 5.15.0

Adds Meta Muse Glimmer model support for agentic multimodal workflows
AI release Aug 10, 2026

opencode 1.18.16

Config parsing now tolerates unknown fields, project registration works correctly from Home, and right-click project menu opens in Desktop mode
AI release Aug 10, 2026

Qwen Code 0.21.8

Qwen Code 0.21.8 restores fork PR autofixes, enables compression cache sharing across OpenAI/Gemini/Vertex AI, and improves /review performance to 93.3% cache hit rates
AI release Aug 9, 2026

Maple 3.3.2

Agent Mode gains Goose and RMCP 3 support with improved reliability, sidebar UX, model memory, and Gemma 4 thinking integration
AI release Aug 9, 2026

Cline 4.1.7

Adds task change review via SDK checkpoints, pre-registered OAuth for remote MCP servers, and fixes session durability across aborts, LiteLLM routing, and MCP server initialization timeouts
AI release Aug 8, 2026

Qwen Code 0.21.8

Qwen Code 0.21.8 restores fork PR autofix, enables compression cache sharing across OpenAI/Gemini/Vertex, and improves /review performance to 93.3% cache hit rates
AI release Aug 8, 2026

llama.cpp b10329

Corrects server info endpoint to report the isolate working directory when a tools runtime is configured
AI release Aug 8, 2026

openclaw 2026.6.34

Hardens browser and network boundaries: sandboxed routes, trusted DNS, custom origins, and loopback endpoints now reject unsafe paths
AI release Aug 8, 2026

ComfyUI 0.31.0

Reduces pinned memory on Linux systems without swap partitions
AI release Aug 8, 2026

Claude Agent Sdk Typescript 0.3.225

Fixed background subagents failing to resume after shell commands or monitors complete in headless SDK sessions
AI release Aug 8, 2026

Claude Code 2.1.225

Claude Code 2.1.225 fixes OAuth token handling in headless sessions, MCP keychain timeouts, safety-filter retry loops, and Remote Control session resume breakage on large conversations
AI release Aug 8, 2026

Qwen Code 0.21.7-nightly.20260808.4ec0371e6

Qwen Code fixes core stability issues including file cache bounds, session transcript handling, memory reporting, and adds compression cache sharing with OpenAI and Gemini providers
AI release Aug 7, 2026

llama.cpp b10326

TTS timing now accounts for full vocoder pass instead of single trailing window
AI release Aug 7, 2026

Anthropic Sdk Csharp 12.40.0

C# SDK adds mid-conversation tool changes, session budgets, advisor tools, and GitHub skill auto-loading for Claude API integration
AI release Aug 7, 2026

Anthropic Sdk Typescript 0.116.0

Adds session budgets, mid-conversation tool changes beta, advisor tool, and pinned inference location
AI release Aug 7, 2026

LocalAI 4.8.2

LocalAI 4.8.2 adds NVIDIA NeMo-Speech.cpp backend for speech processing and improves model gallery resilience with mirror fallbacks
AI release Aug 7, 2026

langchain-openai== 1.4.2

Filters langchain-generated content-block IDs; Handles ContextWindowExceededError
AI release Aug 7, 2026

Cline Desktop 0.0.10

Cline Desktop adds OAuth authentication for remote MCP servers, fixes silent failures in chat turns, improves model onboarding visibility, and stabilizes reasoning controls across AI SDK providers
AI release Aug 7, 2026

opencode 1.18.15

Message chronology fixes prevent ordering corruption during imports, forks, and compaction; Blob attachments now work in web UI; Broader locale support added to desktop
AI release Aug 7, 2026

Anthropic Sdk Go 1.62.0

Adds session budgets, advisor tool, mid-conversation tool changes beta, and pinned inference location
AI release Aug 7, 2026

Claude Code 2.1.224

Claude Code adds self-hosted environments, cross-session messaging, archive plugin installation, and sandbox credential-masking for Team/Enterprise users
AI release Aug 7, 2026

Qwen Code 0.21.7

Removed 50-turn limit for Goals, added inline terminal image rendering, introduced repository-specific review manifests, and fixed streaming response hangs
AI release Aug 6, 2026

LocalAI 4.8.1

LocalAI 4.8.1 fixes VRAM handling for malformed GGUF metadata, restores vllm-cpp backend ABI compatibility, and adds Qwen3.5 variants to model gallery
AI release Aug 6, 2026

Kimi Code 0.34.0

Kimi Code adds Windows Computer Use support, persistent failure cards with one-click resume, and cache-expiry reminders for idle sessions
AI release Aug 6, 2026

Cline 4.1.6

Cline adds Muse Spark 1.2 model option and fixes telemetry attribution to report failures against actual models used
AI release Aug 6, 2026

Cline CLI 3.0.51

Reasoning effort now applies consistently across all providers including Ollama, new Muse Spark model added to Cline provider, error telemetry tracks actual model used
AI release Aug 6, 2026

Qwen Code Live Host 0.1.0

Qwen Code Live Host 0.1.0 adds local GitHub authentication, mid-turn read-only command execution, and dependency closure testing for code reviews
AI release Aug 6, 2026

llama.cpp b10290

AMD ROCm CI support for gfx1151; No inference changes
AI release Aug 6, 2026

Qwen Code 0.21.6-nightly.20260806.cb3dc107f

Upstream release notes did not include a readable summary.
AI release Aug 5, 2026

Cline 4.1.5

Cline 4.1.5 unifies reasoning settings across AI providers and adds clarity when free model promotions expire, replacing generic errors with model-selection prompts
AI release Aug 5, 2026

llama.cpp b10289

Fixed directory traversal vulnerabilities in file search, improved path handling on Windows with UTF-8 conversion, and added cache expiration for UI picker searches
AI release Aug 5, 2026

langchain-anthropic== 1.5.4

Langchain-anthropic 1.5.4 fixes tool schema composition handling, preserves tool_choice settings, and adds user_profile_id attribute support
AI release Aug 5, 2026

Mistral Vibe 2.24.0

Adds admin config layer and server-side default model routing; Unpinned default model option tracks recommended model
AI release Aug 5, 2026

HelixML 2.12.2

Autonomous bot runs on internal repos, recurring tasks work with external agents, org-level agent provider isolation, and UI refinements for task status and browser navigation
AI release Aug 5, 2026

Elevenlabs Android 0.12.0

Adds media audio stream option to ConversationConfig; Fixes WebSocket disconnect attribution
AI release Aug 5, 2026

LocalAI 4.8.0

LocalAI 4.8.0 ships vllm.cpp (C++20 inference engine), 3D generation, audio.cpp multi-family backend, VRAM budgets, and distributed mode hardening across 386 merged PRs
AI release Aug 5, 2026

Cline Desktop 0.0.9

Universal macOS binary, session filtering, context-window cost ring, skill/workflow disambiguation, plugin naming, plan-mode file-blocking, auto-context recovery, and multi-provider empty-response retry
AI release Aug 5, 2026

Kimi Code 0.33.0

CLI now runs on agent-core-v2 engine, adds Computer Use and WebBridge to marketplace, and improves session forking and trust prompts
AI release Aug 5, 2026

Qwen Code 0.21.6-preview.0

Browser extension diagnostics, headless Goal workflows, PR/issue URL artifact tracking, web-shell agent stability fixes, and prompt cache reuse improvements
AI release Aug 4, 2026

Claude Code Action 1.0.185

Claude Code Action now derives trigger timestamps for events, pins bun config for MCP servers, matches downloaded images ID, and validates collaborator permissions for workflow runs
AI release Aug 4, 2026

Claude Agent Sdk Typescript 0.3.222

Fixed resumed agent sessions not inheriting user settings like API keys, environment variables, hooks, and permissions
AI release Aug 4, 2026

Room Connect Ecr 0.5.0

Point-cloud generation for 3DGS initialization with curvature-weighted PLY, k-NN density stats, and Fast/Standard/Dense presets; Adds equirectangular backdrop image
AI release Aug 4, 2026

llama.cpp b10271

Adds a per-conversation working directory with file picker; Agents can now treat path-like queries as directory navigation
AI release Aug 4, 2026

Ollama 0.32.6

Ollama 0.32.6 speeds up Qwen3.5 on Apple GPUs via speculative decoding, fixes OpenAI API streaming format compliance, and improves TUI usability
AI release Aug 4, 2026

HelixML 2.12.1

Chat UX improvements and rich attachments
AI release Aug 4, 2026

llm CLI 0.32

Major overhaul of how prompts, responses, tools, and logs are represented; Backwards-compatible
AI release Aug 4, 2026

whisper.cpp 1.9.2

Syncs with ggml; Includes Parakeet in build-xcframework.sh and fixes pkgconfig configuration
AI release Aug 4, 2026

Elevenlabs Mcp 0.12.2

@cwood-11 made their first contribution in 128
AI release Aug 4, 2026

Kimi Code 0.32.0

Kimi Code 0.32.0 adds hook events for session lifecycle tracking, offline model catalog fallback, renames loop control config keys, and fixes tool call ID parsing with colon-containing provider responses
AI release Aug 4, 2026

Qwen Code 0.21.5

Adds tool-call outcome tracking, prevents unsafe MCP replays on connection loss, stops infinite Goal retries, and improves review result visibility
AI release Aug 4, 2026

openclaw 2026.7.1-1

Openclaw fixes GPT/Codex response completion, memory startup recovery, WSL permissions handling, legacy migration tolerance, and plugin update staling
AI release Aug 4, 2026

Claude Code 2.1.221

Claude Code 2.1.221 adds Focus view for cleaner chat UI, sandbox credential masking on Linux/WSL, permission-check security fixes for Bash and PowerShell, and MCP server connection reliability improvements
AI release Aug 4, 2026

Claude Agent Sdk Typescript 0.3.221

Improved skills validation to reject malformed names, fixed external MCP servers not connecting before first turn preventing tool calls
AI release Aug 3, 2026

Room Connect Ecr 0.4.0

Adds OPENCV camera model, HDR EXR output, and persistent camera/light settings for Gaussian Splat workflows
AI release Aug 3, 2026

Hermes Agent 0.20.0

V0.20.0 Herald release; 3,650 commits, 559k insertions since v0.19.0
AI release Aug 3, 2026

Mistral Vibe 2.23.3

/retry command and improved /rewind control surface let users recover from interrupted LLM responses, with better cost visibility and cache token accounting
AI release Aug 3, 2026

llamafile 0.10.5

Focused on simplifying the upstream llama.cpp sync task
AI release Aug 3, 2026

llama.cpp b10236

Implements DSv4 Lightning Indexer and f16 Lightning Indexer for Metal; Affects 128-dimensional 64-head inputs on Apple silicon
AI release Aug 3, 2026

Qwen Code 0.21.4

Web Shell is now a native desktop app with lifecycle management and auto-updates, subagents are isolated per fork, and prompt cache reuse reduces latency
AI release Aug 2, 2026

llama.cpp b10232

WebGPU backend adds f16 repeat support; MacOS KleidiAI build disabled
AI release Aug 2, 2026

openclaw 2026.7.2-beta.7

OpenClaw adds durable message recovery across gateway restarts, conversation branching and rewinding, MCP app hosting on dashboards, agent approvals with push notifications, Teams/Zoom meeting integration, Wear OS companion app, and local LLM inference
AI release Aug 2, 2026

Cline CLI 3.0.49

Cline CLI 3.0.49 fixes undo/checkpoint functionality, improves Ollama cold-load handling, adds UTF-8 PowerShell stdin support, and resolves provider error reporting
AI release Aug 2, 2026

Cline SDK 0.0.69

Ollama timeout increased to 5 minutes for large model cold-loads, empty responses retried automatically, checkpoints now captured and restored with file state tracking
AI release Aug 2, 2026

Qwen Code 0.21.3-nightly.20260802.184365390

Fixed history pagination failure on oversized transcripts and completed TUI keyboard shortcut documentation
AI release Aug 1, 2026

NanoClaw 2.1.54

Rollup of 36 commits since v2.1.17; No individual fix highlighted
AI release Aug 1, 2026

llama.cpp b10219

Llama.cpp now preserves reasoning content in chat history, enabling multi-turn conversations to leverage previous model reasoning with --reasoning-preserve flag
AI release Aug 1, 2026

opencode 1.18.11

Fixed MCP SSE reconnect loops, reasoning field parsing, and desktop UI issues including external link handling and file tree clipping
AI release Aug 1, 2026

koboldcpp 1.118.1

Row Split option removed; Selecting it now defaults to tensor split
AI release Aug 1, 2026

Cli 1.0.19

Adds Hailuo H3 video generation; Fixes quota reporting and truncated downloads
AI release Aug 1, 2026

openclaw 2026.7.2-beta.6

OpenClaw ships crash-recovery for persisted data, durable message delivery across channels, conversation branching, interactive MCP dashboards, and local inference support with Claude Opus 5
AI release Jul 31, 2026

llama.cpp b10212

Adds driver-version check for Intel GPUs on Windows to avoid crashes; No action unless running that config
AI release Jul 31, 2026

InvokeAI 6.14.0

Adds video generation via Wan 2.2
AI release Jul 31, 2026

Kimi Code 0.31.1

Fixes model catalog initialization race, preserves interrupted outputs, enables Monaco code highlighting, improves TUI performance, and corrects permission ordering and chat rendering bugs
AI release Jul 31, 2026

ComfyUI 0.29.2

Frontend improvements and new API/partner nodes for extending ComfyUI's extensibility and integration capabilities
AI release Jul 31, 2026

Qwen Code 0.21.2

Autofix now defers lower-severity suggestions after five rounds, Auto Recall searches external context with security limits, and Web Shell gains contextual task panels
AI release Jul 31, 2026

Maple 3.3.1

Maple 3.3.1 adds private Voxtral text-to-speech, improves Agent Mode continuity, hardens Local Proxy authentication, and restores Android 16 KB page-size support
AI release Jul 31, 2026

Cline CLI 3.0.48

History command now opens in existing TUI; Connector threads recover from missing sessions
AI release Jul 31, 2026

Cline SDK 0.0.67

Reasoning controls now driven catalog with normalized budgets per provider, MCP timeouts configurable per server, session forking for editing prior prompts, and checkpoint compaction fixed to prevent repeated summarizer calls
AI release Jul 31, 2026

Qwen Code 0.21.1-nightly.20260731.702932cc7

Qwen Code adds session-scoped MCP runtime, persists Goal v3 state, fixes shell output flushing, and improves CI reliability with zombie process cleanup and retry logic
AI release Jul 30, 2026

Hermes Agent 0.19.1

Hermes Agent 0.19.1 stabilizes 1,000+ PRs with bug fixes across gateway, voice, desktop, and installer subsystems
AI release Jul 30, 2026

llama.cpp b10195

Tests alternative convolution layout; Extends layout checks for conv2d kernel
AI release Jul 30, 2026

llm CLI 0.32rc1

Default model now GPT-5.6 Luna for users without a configured default
AI release Jul 30, 2026

Elevenlabs Mcp 0.11.0

Adds simulate conversation tool, defaults STT to scribe v2
AI release Jul 30, 2026

Elevenlabs Python 2.60.0

Fixes blocking in AsyncConversation startup, corrects multipart field handling
AI release Jul 30, 2026

Mistral Vibe 2.23.2

Adds skill-creator built-in flow, session cache-hit token tracking, custom login domain support
AI release Jul 30, 2026

Kimi Code 0.31.0

Kimi Code adds plugin-contributed custom agents with Markdown definitions, configurable system prompts, and sub-agent delegation, plus fixes for request headers and task blocking
AI release Jul 30, 2026

Qwen Code 0.21.1-nightly.20260730.1643a6c9a

Qwen Code adds session-scoped MCP runtime, Goal v3 state persistence, image zoom tooling, and fixes shell stream flushing, quota handling, and composer text preservation
AI release Jul 29, 2026

llama.cpp b10182

Adds NextN and MTP speculative decoding for GLM-5.2; GLM DSA support
AI release Jul 29, 2026

Kimi Code 0.30.0

Customizable footer status line, halted retries on invalid tool calls, quota warnings for plugins, fast-fail on account exhaustion, and removed file upload size limits
AI release Jul 29, 2026

Cline Desktop 0.0.7

Cline Desktop adds system tray status, paginated history, session favorites, subagent tracking, free-tier model support, fixes regional endpoint routing and tool-call parsing bugs
AI release Jul 29, 2026

ComfyUI 0.29.0

Streams video transcode instead of buffering all frames in memory
AI release Jul 29, 2026

Qwen Code 0.21.1

Qwen Code adds Goal v3 runtime orchestration, GitHub channel notifications, workspace trust hot-reloading, and read-only external corpora search for code review automation
AI release Jul 28, 2026

Cline 4.0.12

Cline adds free model tier support with usage limit indicators and fixes response loss during max-turns errors
AI release Jul 28, 2026

llama.cpp b10173

Added Laguna-S-2.1 model support to llama.cpp for local inference
AI release Jul 28, 2026

opencode 1.18.8

MCP server reconnection after SDK expiration, OAuth callback port handling, and deprecated sampling parameter removal improve compatibility and stability across newer AI model integrations
AI release Jul 28, 2026

Dify 1.16.1

Dify 1.16.1 adds workflow tool multi-select inputs, node locators in logs, agent DSL export, and fixes collaboration draft saves, RAG document processing, and agent preview chat persistence
AI release Jul 28, 2026

openclaw 2026.7.2-beta.5

OpenClaw 2026.7.2 adds crash-durable message recovery, conversation branching, interactive MCP dashboards, structured agent approvals across platforms, and local model inference with Wear OS support
AI release Jul 28, 2026

Cline Desktop 0.0.6

Cline Desktop adds queued message management, persistent update notifications with one-click restart, and improved UI layout for narrow windows and dark mode
AI release Jul 27, 2026

Packages React 1.11.0

Streaming reasoning response events now available via onAgentReasoningResponsePart callback
AI release Jul 27, 2026

Qwen Code DSW manual benchmark POC 20260727-2

Nightly achieved 376/500 resolved on SWE-bench Verified, results quarantined pending production validation
AI release Jul 27, 2026

Room Connect Ecr 0.3.0

Depth map rendering 32x faster. Hot-swap GLB workflow with confirmation dialog
AI release Jul 27, 2026

llama.cpp b10153

MiMo-V2.5 RVQ-based audio input support added
AI release Jul 27, 2026

Kimi Code 0.29.2

Kimi Code 0.29.2 fixes goal interruption, message handling during active goals, chat copying over HTTP, and /undo consistency; Defers tool schema registration and improves runtime state management
AI release Jul 27, 2026

vLLM 0.26.0

VLLM 0.26.0 adds Inkling model support, DeepSeek-V4 performance optimizations, fp32 generation heads, flexible attention backends, and mature KV offloading with tiered storage
AI release Jul 27, 2026

Qwen Code 0.21.0-nightly.20260727.c003e1718

Measure insight days and hours in local time everywhere; Extract review verification runner; Don't fail triage cleanup when there is nothing to clean; Align GenAI content telemetry fields
AI release Jul 26, 2026

Maple 3.3.0

Adds local PDF OCR with PDFOxide, expands Agent Mode with authenticated web tools, stabilizes chat-history pagination
AI release Jul 26, 2026

Qwen Code 0.21.0

Qwen Code 0.21.0 adds workspace management, file previews, background agent persistence, MCP reconnects, and autofix improvements for stale bases and infrastructure failures
AI release Jul 25, 2026

vLLM 0.26.0

411 commits from 212; Check release notes for model and hardware support changes
AI release Jul 25, 2026

Ollama 0.32.4

Ollama 0.32.4 adds Laguna support for Apple GPUs, fixes Qwen3 MoE expert quantization, and improves speculative decoding performance
AI release Jul 25, 2026

Qwen Code 0.21.0

Qwen Code 0.21.0 adds workspace management, file previews, background agent persistence, MCP reconnects, and auto-recovery for stale pull request bases
AI release Jul 24, 2026

opencode 1.18.5

Opencode 1.18.5 stabilizes multi-model AI handling (Claude, OpenAI, Mistral, MiniMax) and adds current-server support to the desktop app with backwards compatibility
AI release Jul 24, 2026

langchain-anthropic== 1.5.2

LangChain Anthropic added Claude Opus 5 model support for AI tooling integrations
AI release Jul 24, 2026

Cline 4.0.11

Adds Claude Opus 5 support across providers, including 1M context variants
AI release Jul 24, 2026

Claude Code 2.1.219

Claude Opus 5 now default with 1M context, sandbox network allowlist controls added, nested subagent forwarding in stream-json, and various fixes for permission handling and UI state
AI release Jul 24, 2026

Claude Agent Sdk Typescript 0.3.219

Adds interrupt cancellation, fast-mode diagnostics, directory lifecycle hooks, network allowlist controls, and workflow sizing guidance for agent orchestration
AI release Jul 24, 2026

Anthropic Sdk Csharp 12.39.0

C# SDK adds Claude Opus 5 model, tool addition/removal blocks, tool_change events, and fixes streaming parallel tool-use logic
AI release Jul 24, 2026

HelixML 2.11.58

HelixML adds Slack topic delivery, fixes clipboard paste in embedded streaming, and defaults to Claude Opus 1M context
AI release Jul 24, 2026

llama.cpp b10105

Refactors mlock, mmap, and direct I/O into unified load-mode argument
AI release Jul 24, 2026

Qwen Code DSW SWE-bench Full POC 20260724 Run 3

Isolated test pre-release for SWE-bench PR 7656; Not a production artifact
AI release Jul 24, 2026

Kimi Code 0.29.1

Kimi Code 0.29.1 adds MCP server timeouts, fixes reasoning field detection for OpenAI-compatible endpoints, and enables web search/fetch configuration via environment variables
AI release Jul 24, 2026

Qwen Code 0.20.1-nightly.20260724.7d17c44a3

Qwen Code nightly adds workspace switching, lazy-loads dependencies for faster startup, optimizes session rendering, and includes security fixes for daemon secret isolation
AI release Jul 23, 2026

llama.cpp b10099

CUDA NVFP4 W4A4 activation quantization improvements, fused per-channel amax and quantization kernels
AI release Jul 23, 2026

langchain-openai== 1.4.1

LangChain OpenAI adds LangSmith gateway support via environment variable and fixes GPT-5.3 profile configuration
AI release Jul 23, 2026

langchain-anthropic== 1.5.1

LangChain's Anthropic integration now supports LangSmith gateway via environment variable and enables structured output for Claude Opus 4.8
AI release Jul 23, 2026

Mistral Common 1.11.7

Mistral Common adds auto-detecting chat template generation, validates special token policies during decoding, and rejects thinking chunks in tool messages
AI release Jul 23, 2026

HelixML 2.11.57

API thread hang fixes, GitLab topic webhooks, Claude subscription clarification, and 100MB attachment support for spec tasks
AI release Jul 23, 2026

Jan 0.8.4

Settings and credentials now live in backend-managed store. Migration required
AI release Jul 23, 2026

Qwen Code 0.20.0-nightly.20260722.b98306b7e

Qwen Code benchmark; Field; Result; Status
AI release Jul 23, 2026

Ollama 0.32.3

Ollama 0.32.3 fixes stalled downloads, expands GPU support to Windows ARM64 and B200, and adds chat/tool-calling for Laguna 2.1 models
AI release Jul 22, 2026

Claude Agent Sdk Python 0.2.126

SDK now surfaces query termination reasons and properly types model usage with provider identification for cross-provider model tracking
AI release Jul 22, 2026

Claude Code Action 1.0.181

Claude Code Action now shares WIF credentials across spawned processes instead of creating duplicates
AI release Jul 22, 2026

llama.cpp b10090

Adds depthwise conv2d kernel for WebGPU backend, ported from Vulkan
AI release Jul 22, 2026

Anthropic Cli 1.19.0

Adds support for Managed Agents model effort, initial session events, threads delta streaming
AI release Jul 22, 2026

Anthropic Sdk Csharp 12.37.0

C# SDK adds Managed Agents model effort controls, initial session events, and threads delta streaming support
AI release Jul 22, 2026

Anthropic Sdk Typescript 0.113.0

Adds support for Managed Agents model effort, initial session events, threads delta streaming
AI release Jul 22, 2026

Kimi Code 0.29.0

Kimi Code 0.29.0 adds granular thinking effort levels in ACP clients, custom Markdown-based agents with tool gating, video attachment support, and raw file serving via API
AI release Jul 22, 2026

Elevenlabs Python 2.59.0

Adds HMAC-signed post-call webhook config for on-prem conversations
AI release Jul 22, 2026

Maple 3.2.0

Adds manual Agent project ordering and prevents Markdown image loading
AI release Jul 22, 2026

Qwen Code 0.20.0-preview.0

Upstream release notes did not include a readable summary.
AI release Jul 22, 2026

Cline Desktop 0.0.2

First signed, notarized macOS build (Apple Silicon and Intel) for running and inspecting Cline sessions
AI release Jul 21, 2026

InvokeAI 6.13.7

Closes config-file exposure affecting all versions through 6.13.6. Upgrade immediately
AI release Jul 21, 2026

llama.cpp b10078

Vulkan queue refactoring enables driver-side synchronization on supported hardware, reducing host-side mutex contention for GPU inference
AI release Jul 21, 2026

langchain-anthropic== 1.5.0

Adds reasoning-effort as a standard parameter; Fixes builtin tool recognition
AI release Jul 21, 2026

langchain-openai== 1.4.0

Adds reasoning-effort parameter; Bumps Pillow to 12.3.0
AI release Jul 21, 2026

Mistral Vibe 2.22.0

Adds /new alias for /clear and ACP review support with live refresh
AI release Jul 21, 2026

HelixML 2.11.56

HelixML fixes task merge detection bugs, adds GitLab OAuth attribution, and requires branch specification for existing mode
AI release Jul 21, 2026

Introducing Gemini 3.6 Flash 3.5

Google released Gemini 3.6 Flash with faster inference and new specialized variants (Flash-Lite, Flash Cyber) for different compute constraints
AI release Jul 21, 2026

langchain-core== 1.5.0

Adds reasoning effort as a standard chat-model parameter
AI release Jul 21, 2026

Qwen Code 0.20.0-nightly.20260721.cda0e0348

Qwen Code improves autofix label-driven workflows, adds persisted conversation branches, routes shell commands level, and isolates parallel web-shell sessions
AI release Jul 20, 2026

Ollama 0.32.2

Ollama 0.32.2 adds agent skills system, fixes Anthropic thinking-block handling, updates llama.cpp and MLX backends, and enables unlimited tool rounds for cloud models
AI release Jul 20, 2026

Hermes Agent 0.19.0

Hermes Agent drops first-token latency 80% across platforms, streams reasoning live, adds terminal subscription management, integrates Bitwarden/1Password, and ensures durable delivery through crashes
AI release Jul 20, 2026

opencode 1.18.4

Adaptive thinking now works with Kimi models on Anthropic-compatible providers
AI release Jul 20, 2026

Kimi Code 0.28.1

ACP sessions now accept pre-configured model credentials, web servers run foreground-only, and subagents respect runtime permission changes
AI release Jul 20, 2026

Kimi Code 0.28.0

Replaced kimi server with kimi web for foreground operation and multi-instance support sharing one home directory, fixed permission mode descriptions, and enabled symlink handling in agent file loading
AI release Jul 19, 2026

HelixML 2.11.54

Fixes macOS VM pinning, recovers idle threads, returns admin status in login, rejects nested YAML configs, and exposes external agent sessions in API
AI release Jul 19, 2026

Qwen Code 0.20.0

Qwen Code 0.20.0 adds daemon log rotation, WebShell history replay, improved review findings tracking, and fixes Java SDK timeout handling plus tool calling schema support
AI release Jul 19, 2026

Cline SDK 0.0.65

Claude and Codex provider SDKs now load on demand instead of bundling, reducing install size, with OAuth retry, team-run isolation, and Windows shell fixes
AI release Jul 19, 2026

Qwen Code 0.19.12-nightly.20260719.86ad532de

Qwen Code adds daemon log rotation, fixes Java SDK timeout constants and exception handling, improves code review CI checks and findings tracking, and defers TUI startup for faster daemon initialization
AI release Jul 18, 2026

openclaw 2026.7.1

Control UI overhaul, app updates across iOS/Android/macOS, GPT-5.6 and Tencent Hy3 support, improved coding agents, and fixes to Gateway crashes, messaging channels, and scheduled workflows
AI release Jul 18, 2026

openclaw 2026.7.2-beta.3

Remote coding sessions on cloud workers, native mobile automations, safer channel operation, guided setup flows, and gateway recovery improvements
AI release Jul 18, 2026

Cli 0.5.6

Agent templates fixed to work correctly with CLI tooling
AI release Jul 18, 2026

llama.cpp b10067

K/V cache rotation fix for DFlash quantization workflows
AI release Jul 18, 2026

Open Interpreter 0.0.34

Open Interpreter 0.0.34 release
AI release Jul 18, 2026

Qwen Code 0.19.11-nightly.20260718.767a32484

Qwen Code adds multi-workspace hardening, session export, skill management UI, and improves daemon startup tracing and stream handling
AI release Jul 17, 2026

Open Interpreter 0.0.30

Open Interpreter 0.0.30 release
AI release Jul 17, 2026

Buffa 0.9.0

Changie fragment files adopted to end changelog merge conflicts. Codegen and struct evolution policy documented
AI release Jul 17, 2026

Mistral Vibe 2.21.0

Breaking change: hooks graduated from experimental, hooks.toml is now stable. Registry skills content store and ACP config schema added
AI release Jul 17, 2026

llama.cpp b10064

OpenCL kernel gemm_moe_q6_k_f32_ns now loaded from binary kernel library. Binaries for macOS, iOS, Linux, and Windows published
AI release Jul 17, 2026

Mistral Common 1.11.6

Fixes audio chunk validators, rejects invalid sampling rates, improves token decoding under strict policies
AI release Jul 17, 2026

Dify 1.16.0

Dify 1.16.0 ships Agent sandbox execution with skill system, workflow integration, and improved AI-generated workflow generation for faster agent building
AI release Jul 17, 2026

Open Interpreter 0.0.29

Open Interpreter 0.0.29 release
AI release Jul 17, 2026

openclaw 2026.7.1

OpenClaw 2026.7.1 overhauls UI and onboarding, adds GPT-5.6 and Tencent Hy3 support, improves Codex agents and messaging channels, and fixes Gateway crashes
AI release Jul 17, 2026

Open Interpreter 0.0.28

Open Interpreter 0.0.28 release
AI release Jul 17, 2026

Elevenlabs Android 0.11.1

Fixes R8/ProGuard obfuscation of outgoing event fields
AI release Jul 17, 2026

Open Interpreter 0.0.27

Open Interpreter 0.0.27 release
AI release Jul 17, 2026

Cline CLI 3.0.44

Cline CLI 3.0.44 fixes UTF-8 BOM parsing in config files and improves token limit handling across LLM providers
AI release Jul 17, 2026

Cline SDK 0.0.64

Cline SDK improves token limit handling across AI providers and fixes UTF-8 BOM parsing in config files
AI release Jul 17, 2026

Qwen Code 0.19.11

Qwen Code added extension management, workspace locking, shell heartbeats, structured memory, and PR preview automation for improved development workflows
AI release Jul 17, 2026

Claude Agent Sdk Typescript 0.3.212

Fixed CLI argument parsing for session flags and added resolved model visibility in multi-model agent tool outputs
AI release Jul 17, 2026

Claude Code 2.1.212

/fork separates conversation branches into background sessions, while /subtask replaces in-session subagents; Adds runaway-loop safeguards, long-running tool backgrounding, and session-resumption picker
AI release Jul 16, 2026

llama.cpp b10051

MacOS, iOS, and Linux build artifacts now included in release notes
AI release Jul 16, 2026

llamafile 0.10.4

Introduces first version of transcribefile
AI release Jul 16, 2026

Anthropic Sdk Java 2.49.0

Anthropic Java SDK adds dreaming and MCP Tunnels support, plus session delta accumulator for agent message previews
AI release Jul 16, 2026

Anthropic Sdk Php 0.37.0

Anthropic PHP SDK adds dreaming and MCP Tunnels support, plus session delta accumulator for agent message previews
AI release Jul 16, 2026

Cli 1.0.18

Add npm package metadata; .github/workflows: Migrate workflows to Blacksmith runners 203; Release: v1.0.18
AI release Jul 16, 2026

Kimi Cli 1.49.0

Kimi CLI 1.49.0 fixes context budget allocation, reasoning content handling, and aligns telemetry events with schema for better observability
AI release Jul 16, 2026

Hugging Face Transformers Patch release 5.14.1

Fixes assisted generation issue with EncoderDecoderCache models
AI release Jul 16, 2026

Ollama 0.32.1

Ollama 0.32.1 fixes MLX model cache leaks, improves Gemma 4 tool calling, and adds working directory context to agents
AI release Jul 16, 2026

Cline CLI 3.0.42

Ollama native API routing fixed to properly respect context window and timeout settings
AI release Jul 16, 2026

Kimi Code 0.25.0

Chat now accepts any file type, uploading unconsumed files to server for model access, plus fixes for authentication bypass, symlink traversal, Anthropic thinking controls, and CSP issues
AI release Jul 16, 2026

Qwen Code 0.19.10-nightly.20260716.506ce0a1a

Web-shell improvements including workspace locking, extension management, adaptive composer layout, plus core heartbeat liveness detection and structured channel memory management
AI release Jul 15, 2026

llama.cpp b10032

Fixes OpenCL buffer creation for CL 2.x; MacOS arm64 and Linux CPU builds included
AI release Jul 15, 2026

Maple 3.1.5

Adds MCP server support; Hardens Zapstore zsp install
AI release Jul 15, 2026

Hugging Face Transformers 5.14.0

Adds Inkling multimodal model: 975B total parameters, 41B active, accepts text, image, and audio inputs
AI release Jul 15, 2026

Cline SDK 0.0.61

Context compaction now reports progress; Workspace git state persisted across sessions
AI release Jul 15, 2026

ComfyUI 0.28.0

Fixes Qwen3-VL tokenizer crash with custom embeddings; Adds AGENTS.md documentation
AI release Jul 15, 2026

Mistral Vibe 2.20.0

Windows command prompt now shell-aware; Double-Esc triggers rewind when input is empty; Hardened bash tool permissions
AI release Jul 15, 2026

Qwen Code 0.19.10

Multi-workspace support extends across transports and sessions, Web Shell gains artifact panels and user-level model config, and session recovery becomes more resilient to failures
AI release Jul 14, 2026

Claude Code Action 1.0.174

Claude Code Action now redacts GitHub user-to-server tokens from logs to prevent credential exposure
AI release Jul 14, 2026

Claude Agent Sdk Typescript 0.3.210

Bash tool output now includes timedOutAfterMs field when commands are auto-backgrounded due to timeout
AI release Jul 14, 2026

llama.cpp b10012

Adds contiguity checks for inner tensor dimensions
AI release Jul 14, 2026

Room Connect Ecr 0.1.2

Add K8s testing POR and upload optimization POR ( )
AI release Jul 14, 2026

LocalAI 4.7.1

Scopes llama.cpp serving options to the llama.cpp code path only
AI release Jul 14, 2026

Room Connect Ecr 0.1.0

Switched to GitHub-hosted runners with OIDC support to unblock ECR image pushes that were queuing indefinitely on self-hosted infrastructure
AI release Jul 14, 2026

HelixML 2.11.51

HelixML adds reasoning effort controls, subscription usage tracking, cron message configuration, and improved org chart visibility for agent workflows
AI release Jul 14, 2026

Kimi Code 0.24.1

Kimi Code fixes session hangs from empty reasoning steps, corrects tool availability timing, improves thinking-level persistence and UI display across web and CLI
AI release Jul 14, 2026

vLLM 0.25.1

VLLM 0.25.1 fixes FFmpeg import blocking model startup and mixed-dtype allreduce corruption in quantized models
AI release Jul 14, 2026

Kimi Code 0.24.0

Kimi Code 0.24.0 defaults local server to agent-core-v2 engine, handles long-running commands via backgrounding instead of killing, and adds session diagnostic export
AI release Jul 14, 2026

Qwen Code 0.19.10

Multi-workspace support now spans transport and sessions, Web Shell gains artifact panels and editable model config, and session recovery is more resilient to stream failures and daemon restarts
AI release Jul 14, 2026

Claude Code 2.1.209

Fixed dialog blocking in Claude agents background sessions that prevented /model and other commands from executing
AI release Jul 13, 2026

openclaw 2026.7.1

OpenClaw 2026.7.1 overhauls Control UI and onboarding, expands model support including GPT-5.6 and Tencent Hy3, strengthens coding-agent workflows, and improves Telegram, Slack, Discord, and Apple Messages integrations
AI release Jul 13, 2026

llama.cpp b9992

Corrects server endpoint to honour per-request reasoning-budget tokens in chat completions
AI release Jul 13, 2026

Elevenlabs Python 2.58.0

Upstream release notes did not include a readable summary.
AI release Jul 13, 2026

openclaw 2026.7.1-beta.6

Adds Claude Sonnet 5, Meta Muse Spark, and new providers; Improves mobile offline chat, session management, macOS app, and startup recovery
AI release Jul 12, 2026

llama.cpp b9977

OpenCL int8 dp4 dense and MoE GEMM optimization for Adreno GPUs
AI release Jul 12, 2026

Kimi Code 0.23.6

Dismissed prompts now treated as non-answers, print-mode sessions survive background tasks and active goals, subagent timeouts extended to 2 hours and made configurable, web UI connection and scrolling fixes
AI release Jul 11, 2026

Maple Proxy 0.1.11

Maple Proxy v0.1.11; All binaries include
AI release Jul 11, 2026

vLLM 0.25.0

558 commits, 232; Compatibility and performance sweep
AI release Jul 11, 2026

OpenClaw 2026.7.1-beta.5

Conversational AI onboarding, multi-provider routing with quotas, offline mobile chat with speech, session organization with auto-titles, and Telegram/Slack integration across platforms
AI release Jul 11, 2026

Hugging Face Transformers Patch 5.13.1

Compatibility patch for vLLM 0.25.0
AI release Jul 11, 2026

llama.cpp b9959

Llama.cpp synced ggml changes, updating core ML infrastructure for model inference
AI release Jul 11, 2026

Claude Agent Sdk Python 0.2.116

Bundles Claude CLI 2.1.207; Fixes CI workspace trust for project-scoped permission grants
AI release Jul 11, 2026

Ollama 0.32.0

Adds Qwen3.5 parser and renderer selection; Agent UI warns before loading old agent models
AI release Jul 11, 2026

Qwen Code 0.19.9

Fixes subagent tool-call loops, broken session history detection, vision bridge timeouts, and shell process management while adding configurable memory agent timeouts
AI release Jul 10, 2026

langchain== 1.3.13

LangChain adds Meta model support via new meta extra and implements explicit prompt caching for OpenAI models
AI release Jul 10, 2026

Qwen Code 0.19.9

Fixes subagent tool-call loops, broken session history detection, vision bridge timeouts, and shell process management; Adds configurable memory agent timeouts and session persistence
AI release Jul 10, 2026

llama.cpp b9952

Llama.cpp optimizes DeepSeek V4 inference with f16 KQ masks, removes unnecessary attention bias, and eliminates redundant cache repeats for faster execution
AI release Jul 10, 2026

Qwen Code PR #6633 Screenshots

Screenshots for PR 6633 verification
AI release Jul 10, 2026

Claude Code 2.1.206

Claude Code adds directory suggestions to /cd, auto-confirms git pushes to configured remotes, fixes MCP timeouts and OAuth re-authentication, and improves agents view usability
AI release Jul 10, 2026

Claude Agent Sdk Typescript 0.3.206

Added command_lifecycle frames tracking message state transitions, eliminating stale duration metrics when API returns no results
AI release Jul 10, 2026

Qwen Code 0.19.8-nightly.20260710.205430235

Fixes subagent tool-call loops, broken history chain detection, vision bridge timeouts, and CLI command matching for more reliable agent execution
AI release Jul 9, 2026

llama.cpp b9945

Hexagon: tiles wide rows in unary ops to avoid VTCM overflow, replaces divs with fastdiv, adds VTCM layout and host-computed offsets
AI release Jul 9, 2026

Kimi Code 0.23.4

Kimi Code adds fuel-pack balance display, fixes session resumption and prompt-goal execution, implements image compression with configurable size limits to prevent request failures, and improves web UI reliability and styling
AI release Jul 9, 2026

HelixML 2.11.47

HelixML fixes Anthropic model ID rewriting for Zed Agent, surfaces deployment logs, and prevents public 502 error leaks
AI release Jul 9, 2026

llm CLI 0.31.1

Fixes JSON error from OpenAI Chat Completion providers when tool calls have empty arguments
AI release Jul 9, 2026

koboldcpp 1.117.1

KoboldCpp 1.117.1 fixes thinking trace display, improves multimodal image placement, adds full Ollama compatibility with embeddings and tool calling, and reworks group chat with multi-character avatars
AI release Jul 9, 2026

koboldcpp 1.117

Fixes terminal output for thinking traces; Multimodal images now inserted inline instead of at context top
AI release Jul 9, 2026

Dify 1.16.0-rc1

Experimental Dify Agent support; Serve only to trusted users
AI release Jul 9, 2026

Mistral Vibe 2.19.1

Bash tool for shell sessions, per-tool description overrides, reactive compaction, and lazy history loading improve agentic workflows and startup performance
AI release Jul 9, 2026

Elevenlabs Js 2.57.0

Pins Node to lts/Krypton in CI; Publishes with bundled npm
AI release Jul 9, 2026

Cline CLI 3.0.39

Cline CLI 3.0.39 adds free model selection in ClinePass provider, fixes str_replace diffs and context compaction, and improves telemetry tracking with versioned client headers
AI release Jul 8, 2026

langchain-openai== 1.3.4

Suppresses Pydantic serializer warnings on structured output parsed fields and fixes async context loop handling
AI release Jul 8, 2026

langchain== 1.3.12

LangChain 1.3.12 fixes interrupt propagation in tool retry middleware, prevents process-group kills in shell operations, and sanitizes Anthropic cache markers on fallback retries
AI release Jul 8, 2026

Qwen Code 0.19.8

CLI now supports inline skill preview with editor handoff, serve environment isolation with admission control, and multi-workspace session routing
AI release Jul 8, 2026

llama.cpp b9910

Fuses MMVQ post-scale and batch-size-1 path for NVFP4
AI release Jul 8, 2026

Hermes Agent 0.18.2

Fixed WhatsApp bridge dependency resolution Baileys from git commit to published npm release, enabling reliable Docker builds
AI release Jul 8, 2026

Qwen Code 0.19.7

Qwen Code 0.19.7 strengthens PR triage, adds session management and export, fixes file restoration during autofix, and improves daemon status visibility
AI release Jul 7, 2026

MLX 0.32.0

Minor bump to 0.32.0; Qmm implementations now generated via cmake
AI release Jul 7, 2026

Claude Code 2.1.203

Claude Code 2.1.203 fixes session recovery, background agent stability, and context-usage performance regressions affecting multi-agent workflows and daemon reliability
AI release Jul 7, 2026

Claude Agent Sdk Typescript 0.3.203

SDK now emits background_tasks_changed messages for full task state tracking and fixes TypeScript type reference resolution in stable builds
AI release Jul 7, 2026

Vla Evaluation Harness 0.4.0

Recording on; LeRobot bridge ships with four reproduced LIBERO scores and reproducible Docker builds
AI release Jul 7, 2026

HelixML 2.11.46

HelixML adds LM Studio integration with autodetection, improves sandbox stability, and unifies agent messaging on session-scoped queues
AI release Jul 7, 2026

Kimi Code 0.23.1

Kimi Code 0.23.1 fixes goal token budgets, WebSocket reconnection, background subagent handling, and Claude thinking preservation on Anthropic providers
AI release Jul 7, 2026

Cline CLI 3.0.38

Cline CLI adds visual mode distinction (blue for act, amber for plan) across UI, improves input parsing tolerance for weaker models, and defaults unspecified models to 128K context
AI release Jul 7, 2026

Qwen Code 0.19.6-nightly.20260707.bcdb44c5d

Qwen Code tightens PR review gates with improved problem detection, adds daemon status monitoring and session management, fixes auth persistence and file restoration bugs, and optimizes glob traversal performance
AI release Jul 6, 2026

Claude Code Action 1.0.166

Fixes symlink handling in config snapshots, preserves repeated CLI flags, and improves error propagation in install pipeline
AI release Jul 6, 2026

Ollama 0.31.2

Flash attention now works on older NVIDIA GPUs, vision model offloading improved, and non-UTF-8 model paths fixed
AI release Jul 6, 2026

llama.cpp b9890

Adds Metal col2im 1d op support for f32, f16, bf16
AI release Jul 6, 2026

LocalAI 4.6.2

Use slices.Contains to simplify code; Shard single-arch backend ma
AI release Jul 6, 2026

Cli 0.5.5

Fixes agent create and update to send raw JSON, preserving config round-trip
AI release Jul 6, 2026

Kimi Code 0.23.0

Preserved thinking enabled, progressive tool disclosure for prompt caching, archived session management, and improved user question feedback in AskUserQuestion
AI release Jul 6, 2026

Client Python 2.6.0

Adds PII and secrets redaction when OpenTelemetry is active
AI release Jul 6, 2026

HelixML 2.11.45

HelixML fixed node discovery query performance and updated error message handling in wedge-breaker tests
AI release Jul 6, 2026

Qwen Code 0.19.6-nightly.20260706.47f62a466

Qwen Code improves PR review triage, adds daemon status monitoring and session management, fixes file-restore and auth bugs, and optimizes glob traversal performance
AI release Jul 5, 2026

langchain-mistralai== 1.1.6

Surfaces citation metadata from chat responses. Model profile data refreshed
AI release Jul 5, 2026

langchain-openrouter== 0.2.6

Adds support for custom HTTP header injection via default headers
AI release Jul 5, 2026

InvokeAI 6.13.6

Fixes dictionary key error crash in Qwen Image and Qwen Image Edit models with default single-file encoder
AI release Jul 5, 2026

llama.cpp b9878

Fixes stale tensor-split metadata for GQA attention on draft models
AI release Jul 5, 2026

openclaw 2026.7.1-beta.2

OpenClaw adds GPT-5.6 support, external harness attachment for resumable workflows, Telegram Codex integration, event-driven cron scheduling, and macOS local Gateway setup
AI release Jul 4, 2026

InvokeAI 6.13.5

InvokeAI 6.13.5 stabilizes image generation with bug fixes for prompt history, GPU crashes, and UI layout while updating React 19, ROCm 7.1, and Transformers 5.5.4
AI release Jul 4, 2026

llama.cpp b9873

Adds guard to prevent dereferencing unallocated K/V rotation buffers; Defensive fix for edge-case crashes
AI release Jul 4, 2026

Checkpoint Engine 0.4.2

ParameterServer metadata now exposed via HTTP, enabling cross-process parameter sharing in distributed AI training setups
AI release Jul 4, 2026

LocalAI 4.6.0

AMD ROCm backends now offload to GPU correctly, distributed worker failures no longer lock model loads, and realtime sessions warm pipelines eagerly to eliminate cold-start stalls
AI release Jul 4, 2026

Cline CLI 3.0.37

Cline CLI now handles malformed tool calls from weaker models, makes mode switches visible to the model, and fixes plan/act mode prompt handling
AI release Jul 4, 2026

Qwen Code 0.19.6

Qwen Code 0.19.6 adds nested sub-agents, dataviz skill, mobile improvements, tool execution timeouts, and fixes multimodal payload bloat
AI release Jul 3, 2026

Claude Agent Sdk Typescript 0.3.201

Claude Agent SDK TypeScript now matches Claude Code v2.1.201 capabilities for building AI agents
AI release Jul 3, 2026

Claude Agent Sdk Typescript 0.3.200

SDK now validates model inputs, fixes permission-mode callbacks, and accepts 'manual' as permission alias
AI release Jul 3, 2026

Hugging Face Transformers 5.13.0

Adds KimiK 2.5, 2.6, 2.7 architecture support
AI release Jul 3, 2026

Mistral Vibe 2.19.0

Adds --worktree option for git worktree creation, raises Leanstral context limit, disables Sentry auto integrations
AI release Jul 3, 2026

llama.cpp b9866

Trims messages sent to StepFun parser, fixes long reasoning loops
AI release Jul 3, 2026

Diffusers 0.39.0

Ships Cosmos 3 pipelines for NVIDIA's unified world foundation model
AI release Jul 3, 2026

Qwen Code 0.19.5

Qwen Code adds HTTPS/TLS support, unified reasoning effort control, and leader approval workflows while fixing CLI responsiveness and web UI session handling
AI release Jul 2, 2026

Cline 4.0.6

Generalized model capability warnings to apply more broadly across different AI models
AI release Jul 2, 2026

llama.cpp b9860

Adds llama_model_ftype_name function to expose quantization type as string
AI release Jul 2, 2026

openclaw 2026.7.1-beta.1

Adds GPT-5.6 model recognition across catalog and runtime paths
AI release Jul 1, 2026

Claude Code Action 1.0.162

Agent-approval-check composite action added to Claude Code Action for gating AI-driven code changes behind manual review
AI release Jul 1, 2026

Claude Code 2.1.198

Background agents now auto-commit, push, and open PRs on code completion; Extended thinking and model selection now propagate to subagents; Transient network errors retry instead of failing
AI release Jul 1, 2026

Hermes Agent 0.18.0

Major release: 1,720 commits, 998 PRs merged, 949 issues closed, 370
AI release Jul 1, 2026

HelixML 2.11.41

Fixed agent session restart to properly clear state and corrected DALL-E model filtering for non-OpenAI endpoints
AI release Jul 1, 2026

Mistral Vibe 2.18.4

Mistral Vibe fixes session resume behavior, tool rendering, and config validation while improving diff display and auto-approve in lean mode
AI release Jul 1, 2026

Elevenlabs Python 2.56.0

Adds disable-auth parameter to speech engine
AI release Jul 1, 2026

llama.cpp b9857

Uses Hugging Face primary split as model path; Fixes issue 25181
AI release Jul 1, 2026

Qwen Code 0.19.4

Qwen Code 0.19.4 adds voice dictation to desktop, resumable interrupted turns without synthetic messages, Chrome extension via daemon architecture, and multiplayer channel-resident agent foundation
AI release Jul 1, 2026

Open WebUI 0.10.2

Streamed reasoning display, folder uploads preserving structure, memory system refinements, environment-based API configs, and security fixes
AI release Jul 1, 2026

Qwen Code 0.19.3-nightly.20260701.a974594d7

Voice dictation in desktop app, configurable auto-compact thresholds, resumable interrupted turns, and Chrome extension via daemon-direct architecture ship in this nightly build
AI release Jun 30, 2026

ComfyUI 0.27.0

Adds int8 convrot model support
AI release Jun 30, 2026

Ollama 0.31.1

Gemma 4 nearly 90 percent faster on Apple Silicon via multi-token prediction
AI release Jun 30, 2026

Cline 4.0.5

Cline adds Claude Sonnet 5 support across eight providers with updated model picker and recommendations
AI release Jun 30, 2026

Anthropic Sdk Php 0.34.0

Adds managed-agent event delta streaming, agent overrides, reverse pagination, vault credential scoping, webhook events
AI release Jun 30, 2026

Anthropic Cli 1.14.0

Adds managed-agent event delta streaming, agent overrides, reverse pagination, vault credential scoping, webhook events
AI release Jun 30, 2026

Claude Code 2.1.197

Claude Sonnet 5 now default in Claude Code with 1M-token context window and reduced pricing through August
AI release Jun 30, 2026

LocalAI 4.5.6

LocalAI adds native voice and face detection backends, improves distributed state management across replicas, and fixes GGUF context sizing and gallery matching
AI release Jun 30, 2026

llama.cpp b9849

Registers attention normalization tensor for Qwen3; Fixes input assignment in layer loop
AI release Jun 30, 2026

Maple 3.1.3

Maple 3.1.3 rejects ARM64EC Windows runtime DLLs and simplifies Authenticode verification for improved binary integrity validation
AI release Jun 30, 2026

Checkpoint Engine 0.4.2-rc0

Exposes ParameterServer metadata via HTTP for cross-process join workflows
AI release Jun 30, 2026

Vla Evaluation Harness 0.3.0

Adds SQLite recording and experiment tracking for observability workflows
AI release Jun 30, 2026

InvokeAI 6.13.5

Maintenance release focused on bug fixes and stability
AI release Jun 30, 2026

Qwen Code 0.19.3

Qwen Code 0.19.3 fixes streaming timeouts, web fetch fallbacks, IDE port validation, and skill persistence workflows while adding daemon voice APIs and skill usage stats
AI release Jun 29, 2026

Claude Code 2.1.196

Organization admins can now set default models, sessions have readable names, file attachments are clickable, and numerous fixes improve security, reliability, and background job handling
AI release Jun 29, 2026

vLLM 0.24.0

571 commits from 256; No breaking changes called out in summary
AI release Jun 29, 2026

Open WebUI 0.10.0

Adds folder sharing with teams
AI release Jun 29, 2026

Ollama 0.30.12

Fixed tool call parsing to handle JSON strings with braces correctly, and updated llama.cpp and MLX dependencies
AI release Jun 29, 2026

Maple 3.1.2

Maple 3.1.2 fixes AppImage runtime helpers and establishes signed Windows release verification with hardened Authenticode validation
AI release Jun 29, 2026

llama.cpp b9839

Adds DeepSeek V4 conversion support including pro model, rope fixes, and chat template
AI release Jun 29, 2026

Kimi Code 0.20.2

Adds optional API parameter to exclude empty sessions from the session list
AI release Jun 29, 2026

Cline CLI 3.0.32

Cline CLI 3.0.32 improves ClinePass onboarding with intermediate steps, refined UI copy, better context compaction, and clearer error messages
AI release Jun 29, 2026

Cline 4.0.2

Cline 4.0.2 adds reasoning effort support for DeepSeek thinking models and fixes environment variable replacement in the webview
AI release Jun 28, 2026

openclaw 2026.6.11-beta.2

Slack/Mattermost relay modes, per-DM model overrides, file-driven agent workflows, and reliability fixes for channel delivery, WhatsApp context preservation, and agent fallback behavior
AI release Jun 28, 2026

llama.cpp b9835

Fixes UI stop and reasoning skip in single-model mode
AI release Jun 28, 2026

Qwen Code 0.19.3

Qwen Code 0.19.3 adds workspace voice and control APIs, skill usage stats, fixes streaming timeout handling and reasoning content preservation, and improves web shell transcript and table interactions
AI release Jun 28, 2026

Qwen Code 0.19.2-nightly.20260628.714513df2

Qwen Code 0.19.2 fixes web fetch JSON fallback, adds daemon voice/control APIs, implements skill confirmation before persistence, and improves streaming stability and CLI responsiveness
AI release Jun 27, 2026

koboldcpp 1.116.1

Koboldcpp 1.116.1 adds Krea 2 Turbo, Ideogram 4, and Boogu Edit image generation models, MCP server support in the web UI, and fixes MTP performance issues
AI release Jun 27, 2026

koboldcpp 1.116

Adds Krea 2 Turbo support
AI release Jun 27, 2026

LocalAI 4.5.5

Fixed CI build failures across multiple backends, whisper macOS library loading, and added new gallery models
AI release Jun 27, 2026

llama.cpp b9825

Vulkan backend fix for zero-input step operator handling in llama.cpp inference
AI release Jun 27, 2026

Qwen Code 0.19.2-nightly.20260627.d93bec905

Qwen Code adds daemon voice and control APIs, skill usage stats, streaming timeout handling, web_fetch JSON fallback, and fixes CLI/IDE stability issues including duplicate responses and port validation
AI release Jun 27, 2026

LocalAI 4.5.4

LocalAI 4.5.4 fixes Darwin backend binary derivation from exec lines, resolving macOS model execution issues
AI release Jun 26, 2026

llama.cpp b9821

Adds support for version, licenses, and help flags
AI release Jun 26, 2026

Claude Code Action GitHub 1.0

1.0 is generally available
AI release Jun 26, 2026

Claude Code Action 1.0.159

Claude Code Action fixes app token revocation cleanup to prevent resource leaks
AI release Jun 26, 2026

Cline 4.0.0

Switches to an SDK-backed VS Code extension runtime
AI release Jun 26, 2026

Olmoearth Pretrain Adds 1.1

Pretrain dataset release with tokenization config propagation and 2D position encoding refactor
AI release Jun 26, 2026

Mistral Common 1.11.5

Mistral Common fixes multi-image content ordering in tokenization and inference workflows
AI release Jun 26, 2026

LocalAI 4.5.2

LocalAI 4.5.2 fixes the Opus backend to build and package correctly on macOS/Darwin
AI release Jun 26, 2026

Mistral Vibe 2.18.0

Adds clickable URLs in web fetch and search output, context-window token usage display, clipboard image paste on macOS, max-tokens config
AI release Jun 26, 2026

Cline CLI 3.0.30

Cline CLI 3.0.30 adds token counting, SAP AI Core provider support, improves model catalog accuracy, and fixes runtime packaging issues
AI release Jun 25, 2026

AnythingLLM 1.15.0

AnythingLLM 1.15.0 adds OS-wide Magic Features, dictation, text actions, and autocomplete that work locally across any app without leaving the browser
AI release Jun 25, 2026

Claude Agent Sdk Typescript 0.3.193

Browser SDK now supports promptSuggestions option for follow-up suggestions, and Windows subprocess spawning no longer flashes console windows
AI release Jun 25, 2026

HelixML 2.11.31

Admins can now grant paid plans directly via wallet PlanOverride without requiring Stripe integration
AI release Jun 25, 2026

Olmoearth Pretrain Minimal Publish 0.0.6

Fix literal string to filepath; ---------
AI release Jun 25, 2026

Dify 1.15.0

Redesigned onboarding, faster navigation palette, safer deletes with confirmation dialogs
AI release Jun 25, 2026

llama.cpp b9788

Fixes quantizing MoE models with mtp
AI release Jun 25, 2026

Mistral Common 1.11.4

Adds chat-template integration, deprecates RawAudio in favor of str or bytes, generalizes normalizer aggregation
AI release Jun 25, 2026

HelixML 2.11.28

HelixML adds Docker Compose hosting, self-healing health monitoring with restart policies, and DNS proxy fixes for sandbox stability
AI release Jun 25, 2026

Ollama 0.30.11

Ollama 0.30.11 fixes GPU detection on hybrid Windows systems, improves speculative decoding, and corrects memory reporting for partially offloaded models
AI release Jun 24, 2026

openclaw 2026.6.11-beta.1

Slack/Mattermost relay modes, per-DM model overrides, file-driven agent workflows, safer plugin distribution, and improved reliability across channel delivery and provider integrations
AI release Jun 24, 2026

Claude Agent Sdk Typescript 0.3.191

SDK now supports inline diffs in notebook edits, per-model weekly usage limits, and fixes fast mode persistence across conversation turns
AI release Jun 24, 2026

LlamaIndex 0.14.23

Dependency bumps across multiple integration directories
AI release Jun 24, 2026

Elevenlabs Android 0.10.0

Exposes reconciled message transcript as StateFlow, deprecates text and agent callbacks in favor of event-id variants
AI release Jun 24, 2026

Qwen Code 0.19.2

Qwen Code adds image transcription for text-only models, deterministic guards for destructive auto commands, voice dictation over daemon, and MCP resource matching improvements
AI release Jun 24, 2026

Jan 0.8.3

Jan 0.8.3 fixes MCP browser port leaks, video upload rendering, SVG markdown handling, and sampler defaults
AI release Jun 24, 2026

llama.cpp b9776

Adds LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M support; No impact unless loading those weights
AI release Jun 24, 2026

openclaw 2026.6.10

OpenClaw adds automatic fast mode for short conversations, improves model routing reliability across Zai and GLM providers, and fixes session state leaks and policy loss in hook composition
AI release Jun 23, 2026

LocalAI 4.5.0

LocalAI 4.5.0 adds depth perception, sound-event tagging, on-device multilingual TTS, PII filtering via NER, speaker-aware realtime conversations, and prefix caching for concurrent multi-user serving without configuration
AI release Jun 23, 2026

ComfyUI 0.26.0

ComfyUI adds Qwen3-VL text generation, SCAIL-2 multireference, Boogu image editing, Kling V3-Turbo, Luma Rays 3.2, and job cancellation API endpoints
AI release Jun 23, 2026

Client Ts typescript 2.3.0

OpenAPI Doc; Speakeasy CLI 1.763.6 (2.884.13); Typescript v2.3.0
AI release Jun 23, 2026

Rslearn 0.1.10

Rslearn adds Sentinel2 cloud filtering, OlmoEarth normalization, and memory-efficient raster operations for remote-sensing machine learning
AI release Jun 23, 2026

HelixML 2.11.27

Fixes org visibility, WebSocket sync bugs, prompt-queue ordering, environment variable forwarding under sudo, and disk-pressure detection on non-ZFS hosts
AI release Jun 23, 2026

Elevenlabs Python 2.54.0

Python SDK now allows passing custom headers and follow_redirects configuration through client initialization for HTTP request control
AI release Jun 23, 2026

Elevenlabs Js 2.54.0

Remove temporary DynamicVariablesConfig fernignore entries
AI release Jun 23, 2026

llama.cpp b9767

Improves WebGPU mat-vec path for small-batch decoding
AI release Jun 23, 2026

Kimi Code 0.19.1

Fixes ACP editor thread initialization, clears orphaned session data on archive, syncs unread indicators across browser tabs, and refactors web client state management
AI release Jun 23, 2026

Qwen Code 0.19.0

Qwen Code 0.19.0 adds voice dictation with native streaming, revivable background agents, artifact publishing for interactive HTML, and fixes loop detection and tool-call guards
AI release Jun 22, 2026

langchain== 1.3.11

LangChain 1.3.11 fixes strict tool mode enforcement for non-OpenAI compatible models and updates dependencies
AI release Jun 22, 2026

langchain-openai== 1.3.3

Fixes tool schema strictness for OpenAI-compatible models and removes unnecessary response storage fields and stop parameters from API calls
AI release Jun 22, 2026

llama.cpp b9760

Relevant if running the server component and permitting file edits, appends at end of file no longer trigger heap overflow
AI release Jun 22, 2026

HelixML 2.11.22

AWS Neuron inference support, agent auto-restart, session clearing for backends, and video rendering fixes for Safari 4K and frame ordering
AI release Jun 22, 2026

Kimi Cli 1.48.0

Fixes empty reasoning content handling and adds detection to stop tool loops on dead-end streaks
AI release Jun 21, 2026

llama.cpp b9752

Server batch construction refactored for more careful slot handling and improved abort logic
AI release Jun 21, 2026

openclaw 2026.6.9

Telegram messaging gains rich HTML and markdown rendering, agent recovery improves through retry logic and session repair, and official provider plugins become standalone npm packages
AI release Jun 20, 2026

llama.cpp b9739

WebGPU adapter toggles for F16 on Vulkan and NVIDIA. Relevant only if running those backends
AI release Jun 20, 2026

Cline CLI 3.0.29

Cline CLI 3.0.29 hides costs for free models, fixes Z.ai metadata resolution, and reverts model display changes from the previous release
AI release Jun 19, 2026

llama.cpp b9732

Server context-shift fix for non-bound n_discard value. Upgrade if running server mode with ctx shifting
AI release Jun 19, 2026

Hermes Agent 0.17.0

Hermes Agent 0.17.0 adds iMessage and Raft agent network support, substantially upgrades the desktop app, enables background subagents, and adds image editing capabilities
AI release Jun 19, 2026

whisper.cpp 1.9.1

Release: v1.9.1
AI release Jun 19, 2026

openclaw 2026.6.8

Telegram and WhatsApp channel delivery now supports rich formatting, agent runs handle state recovery correctly, and model routing adds GLM-5.2 and Claude Haiku 4.5 with safer authentication
AI release Jun 18, 2026

langchain-core== 1.4.8

Langchain-core 1.4.8 memoizes tool schemas, caches JSON schemas, preserves token usage in streaming, and drops Python 3.9 support
AI release Jun 18, 2026

ComfyUI 0.25.1

ComfyUI added Kling V3-Turbo model support through partner nodes for faster video generation workflows
AI release Jun 18, 2026

HelixML 2.11.21

HelixML 2.11.21 fixes streaming frame flicker, improves runner visibility, and refactors agent framework without forking
AI release Jun 18, 2026

llama.cpp b9694

Fixed Windows x64 OpenVINO release build link to resolve CI pipeline failures
AI release Jun 17, 2026

llama.cpp b9690

Optional USM system allocations for buffers over 1GB if the device supports it
AI release Jun 17, 2026

Ollama 0.30.10

Command and Northfamily models now run on Apple Silicon via MLX engine, llama.cpp updated to build 9672
AI release Jun 17, 2026

NanoClaw 2.1.17

NanoClaw 2.1.17 adds Codex provider support with per-group selection, fixes provider-error reporting and command-gate access control, auto-upgrades OneCLI gateway on pin changes, and interrupts in-flight turns with slash commands
AI release Jun 17, 2026

whisper.cpp 1.9.0

Adds NVIDIA Parakeet model support. Check changelog if running Ruby bindings
AI release Jun 17, 2026

HelixML 2.11.20

HelixML 2.11.20 adds disk-pressure admission control for dev containers, fixes orphaned storage cleanup and chat model routing, and corrects Floor node counting logic
AI release Jun 17, 2026

Cline CLI 3.0.26

Restored previous model-selection UI expandable picker sections and ClinePass model integration
AI release Jun 16, 2026

Maple 3.1.0

Windows desktop port, hardened release provenance verification, paste image support, and improved chat UI for local AI workflows
AI release Jun 16, 2026

ComfyUI 0.25.0

ComfyUI adds audio consolidation, 3D preview nodes, partner integrations (Bria, Krea, Gemini), and performance optimizations for inference workflows
AI release Jun 16, 2026

openclaw 2026.6.8

GLM-5.2 and Claude Haiku 4.5 support, improved Telegram/WhatsApp rendering, safer model routing, and more reliable agent recovery paths
AI release Jun 16, 2026

llama.cpp b9670

Adds Vulkan support for gated delta net with S v=16
AI release Jun 16, 2026

whisper.cpp 1.8.7

Drops hardcoded /usr/lib assumption; Relevant if installing to non-standard prefixes
AI release Jun 16, 2026

Z Ai Sdk Java 0.3.5

Z AI SDK Java adds async image generation, OCR API, Java 9+ module support, and GLM 5.2 model support
AI release Jun 16, 2026

Predicting model behavior before release by simulating deployment

OpenAI released Deployment Simulation to predict model behavior before production using real conversation data, improving safety testing and evaluation accuracy
AI release Jun 15, 2026

Ollama 0.30.9

Ollama 0.30.9 adds Cohere2Moe support, fixes token output limits in coding agents, and validates message sizes against context windows
AI release Jun 15, 2026

Hugging Face Transformers Patch 5.12.1

Raises PEFT lower bound; Fixes mistral tokenizer resolution when mistral-common is installed
AI release Jun 15, 2026

Hugging Face Transformers Patch 5.10.3

Fixes for vLLM integration, token ID handling, InternVL models, and processor offsets in Transformers 5.10.3
AI release Jun 15, 2026

Maple Proxy 0.1.10

Maple Proxy v0.1.10; All binaries include
AI release Jun 15, 2026

Continue 1.2.24-vscode

Final stable release drops Hub slugs from config templates; Migrate to explicit model definitions if using old syntax
AI release Jun 15, 2026

llama.cpp b9642

CUDA operators note F32/F16 restriction on GGML OP REPEAT; KleidiAI macOS build remains disabled
AI release Jun 15, 2026

vLLM 0.23.0

DeepSeek-V4 hardening, Model Runner V2 expansion to Llama/Mistral, Rust frontend maturation with streaming and LoRA endpoints, Gemma 4 support, Transformers v5 compatibility, multi-tier KV cache offloading
AI release Jun 14, 2026

llama.cpp b9628

Adds Cohere2MoE vocab for TINY AYA. No impact unless loading those weights
AI release Jun 13, 2026

langchain-openai== 1.3.1

Fixes streamed tool call normalization and structured output fallbacks, adds package version tracking to tracing metadata
AI release Jun 12, 2026

vLLM 0.23.0

Minimax M3 models remain unsupported in this version
AI release Jun 12, 2026

Ollama 0.30.8

Ollama 0.30.8 improves prompt caching efficiency, fixes provider selection bugs, and hardens MLX inference stability with snapshot creation
AI release Jun 12, 2026

Hugging Face Transformers 5.12.0

Adds MiniMax-M3-VL vision-language model support
AI release Jun 12, 2026

llama.cpp b9611

Llama.cpp refactored build dependencies to reduce coupling between fit and llama-ext headers
AI release Jun 12, 2026

koboldcpp 1.115.1

Koboldcpp 1.115.1 adds Anthropic API support with multimodal and tool calling, Gemma4 UV models, MTP speculative decoding, video generation improvements, and sampling speedups
AI release Jun 12, 2026

koboldcpp 1.115

Implements full Anthropic /v1/messages API support including multi-turn conversations
AI release Jun 12, 2026

openclaw 2026.6.6

OpenClaw tightens security across transcripts, sandboxing, and tool execution while improving Telegram delivery coherence, iMessage recovery, browser connectivity, and startup latency
AI release Jun 12, 2026

langchain== 1.3.8

Langchain 1.3.8 tightens structured output model fallbacks and fixes async middleware decorator typing
AI release Jun 11, 2026

LocalAI 4.4.1

LocalAI 4.4.1 restores vLLM 0.22+ compatibility and adds streaming pipeline stages for realtime LLM, TTS, and transcription workflows
AI release Jun 11, 2026

Cline 3.89.2

Cline upgrades Anthropic SDK for Node 24 compatibility, fixing provider issues on VS Code 1.123 and later
AI release Jun 11, 2026

Cline 3.89.1

Cline restored Anthropic provider support on VS Code 1.123+ and added DeepSeek V4 reasoning format handling
AI release Jun 11, 2026

llama.cpp b9594

Refactors normalizer flags into options struct and adds strip-accents support. No model or inference changes
AI release Jun 11, 2026

langchain-model-profiles== 0.0.6

Tool call chunk validation added to standard streaming tests, improving LLM integration reliability
AI release Jun 10, 2026

langchain-mistralai== 1.1.5

Adds content block token support in callbacks and stabilizes integration tests with rate limiting
AI release Jun 10, 2026

LocalAI 4.4.0

LocalAI 4.4.0 adds multimodal capabilities: parakeet.cpp and CrispASR audio backends, video understanding, object detection, LTX-2 video generation, distributed prefix-cache routing, and security hardening
AI release Jun 10, 2026

HelixML 2.11.16

HelixML improved agent crash recovery, fixed streaming interrupts, added multi-tenant org redesign with GitHub App bot identity and reporting-line topology, and scaffolded YellowDog compute integration
AI release Jun 10, 2026

llama.cpp b9589

CUDA: Fix ssm_scan_f32 data-races missing syncthreads calls to prevent shared memory corruption
AI release Jun 10, 2026

langchain-groq== 1.1.3

Langchain-groq 1.1.3 adds content-block-centric streaming v2, strict mode for Groq, standard model properties, and updates dependencies including langsmith 0.8.0 and langchain-core 1.3.3
AI release Jun 9, 2026

llm CLI 0.32a3

Tool calls now support pausable chains with unique IDs and human-in-the-loop resumption, enabling approval workflows before model invocation
AI release Jun 9, 2026

langchain-openai== 1.3.0

Langchain-openai 1.3.0 adds support for OpenAI's apply_patch built-in tool and updates model profile data
AI release Jun 9, 2026

Cline 3.89.0

Cline adds Claude Fable 5 model support, fixes MiniMax M3 thinking controls, and cleans up the Codex model list
AI release Jun 9, 2026

llama.cpp b9585

Operators running llama.cpp with plamo2 models should upgrade. Fixes an attention key-value length regression introduced in a prior build
AI release Jun 9, 2026

openclaw 2026.6.5

QQBot strips thinking scaffolding, MCP tool results coerce to safe formats, extended-thinking sessions recover after cache expiry, Parallel web-search bundled, Matrix voice-notes and threading improved
AI release Jun 9, 2026

AnythingLLM 1.14.0

AnythingLLM now enables tool calling across all providers, adds STT/TTS support, converts web scrapes to markdown, and improves agent summarization
AI release Jun 9, 2026

Cline CLI 3.0.21

Cline CLI adds global auto-update control, Vertex AI ADC support with tool use, and fixes session routing bugs plus empty message replay for Bedrock
AI release Jun 8, 2026

llama.cpp b9568

Fixes im2col 1D case for audio models. Relevant only if running audio inference
AI release Jun 8, 2026

langchain-core== 1.4.2

LangChain Core deprecated the problematic dict() method to encourage use of safer serialization patterns in LLM application chains
AI release Jun 7, 2026

Ollama 0.30.7

Ollama adds Hermes Desktop, a native UI for managing Hermes agent conversations and integrations via ollama launch
AI release Jun 7, 2026

llama.cpp b9553

Sampler name matching now case-insensitive and accepts alternative names like top-k alongside canonical top_k format
AI release Jun 6, 2026

llama.cpp b9538

Qwen3.5 video support added; No impact unless loading those weights
AI release Jun 5, 2026

Ollama 0.30.6

Ollama adds Gemma 4 QAT models for lower memory use, integrates Oh My Pi coding agent, improves Apple Silicon quantization
AI release Jun 5, 2026

llama.cpp b9533

Build system fix resolves compilation failures in llama.cpp, enabling reliable local LLM inference on consumer hardware
AI release Jun 5, 2026

langchain-core== 1.4.1

Removes Bedrock prevalidation from load path; Bumps uuid-utils to 0.16.0
AI release Jun 5, 2026

vLLM 0.22.1

VLLM 0.22.1 adds Mellum v2 support, enables zentorch-accelerated quantized inference on AMD Zen CPUs, and fixes multi-node Ray serving hangs and model initialization regressions
AI release Jun 5, 2026

Cline CLI 3.0.20

Plugin wrappers now use readable source names instead of hashes, making installed extensions easier to identify and manage
AI release Jun 4, 2026

Hugging Face Transformers Patch 5.10.2

Fixes model conversion bug for CLIP-related models including SAM3. Update if those weights are in use
AI release Jun 4, 2026

llama.cpp b9498

WebGPU FlashAttention refactored with standardized quantization support, relevant if running WebGPU backend
AI release Jun 4, 2026

Maple Proxy 0.1.9

Maple Proxy v0.1.9; All binaries include
AI release Jun 3, 2026

openclaw 2026.6.1

Agents now recover cleanly from interrupted tool calls and stale bindings, channels stabilize across messaging platforms, and Skill Workshop adds governed proposal review with CLI and UI tooling
AI release Jun 3, 2026

ComfyUI 0.24.0

Fixes dtype handling for birefnet and dino3 models, upgrade if using those
AI release Jun 3, 2026

Cline 3.87.0

Cline adds MiniMax M3 model support and patches security vulnerabilities in VS Code extension dependencies including xmldom, axios, and undici
AI release Jun 3, 2026

langchain-deepseek== 1.1.0

Content-block streaming v2 support, dependency updates including langchain-core 1.3.3, and Azure endpoint handling fixes
AI release Jun 3, 2026

Ollama 0.30.3

Ollama added Gemma 4 12B model support, expanding locally-runnable open-weight options for builders
AI release Jun 3, 2026

Hugging Face Transformers 5.10.1

5.10.0 was yanked; Upgrade directly to 5.10.1
AI release Jun 3, 2026

HelixML 2.11.15

HelixML fixes nested GPU passthrough for containerized desktops, requires explicit org_id for credit grants, and improves chat message pacing to model realistic user behavior
AI release Jun 3, 2026

llama.cpp b9486

Adds support for qwen3 SSM architectures
AI release Jun 3, 2026

Ollama 0.30.2

Auto-install Cline CLI; Qwen code integration added; Template logging improved for troubleshooting
AI release Jun 2, 2026

langchain== 1.3.4

LangChain 1.3.4 improves human-in-the-loop rejection guidance for better control flow in AI agent workflows
AI release Jun 2, 2026

llamafile 0.10.3

Fixes SIGSEGV regression in GPU initialization, restoring CPU fallback when GPU setup fails
AI release Jun 2, 2026

langchain== 1.3.3

LangChain 1.3.3 adds subagent run projection to typed channels and human-in-the-loop interrupt predicates for agentic workflows
AI release Jun 2, 2026

llama.cpp b9473

SWA checkpoint optimization reduces KV cache storage masked cells, improving memory efficiency for inference
AI release Jun 2, 2026

whisper.cpp 1.8.6

Whisper.cpp 1.8.6 refactors ffmpeg transcoding logic and fixes CI header path resolution
AI release Jun 1, 2026

Open WebUI 0.9.6

Open WebUI 0.9.6 adds incremental knowledge base sync from multiple sources, filesystem commands for AI models to search KB contents, and nested folder organization for managing large document collections
AI release Jun 1, 2026

ComfyUI 0.23.0

MediaPipe face detection, multi-threaded model loading for faster startup, OAuth 2.1 support, and logic nodes shipped to improve performance and API standardization
AI release Jun 1, 2026

Jan 0.8.2

Jan 0.8.2 adds pause/resume for model downloads, AMD ROCm support, persistent assistant parameters, and fixes context limits, model crashes, and UI responsiveness
AI release Jun 1, 2026

HelixML 2.11.14

Goose agent integration, bring-your-own Claude billing, admin runner logs, and sandbox GPU vendor fixes
AI release May 31, 2026

llama.cpp b9444

Adds tokenizer support for jina-embeddings-v2-base-zh. No impact unless loading those specific embedding weights
AI release May 30, 2026

LocalAI 4.3.6

LocalAI 4.3.6 adds NVIDIA NeMo Parakeet ASR backend, hardens HTTP clients against redirects, and updates core dependencies
AI release May 30, 2026

openclaw 2026.5.28

Agent runtime stability improved with better isolation, recovery, and lock handling; Channel delivery safety expanded across plugins and platforms; Mobile UX and input validation strengthened; Claude Opus 4.8, encrypted PDFs, and caching optimizations added
AI release May 30, 2026

llama.cpp b9434

Fixed tensor parallelism granularity for Qwen 3.5/3.6 models across multiple GPUs
AI release May 30, 2026

koboldcpp 1.114.1

Koboldcpp 1.114.1 adds experimental parallel text generation, multi-GPU RPC support, LTX2.3 video generation, and support for Microsoft Lens, HiDream o1, LongCat, and Ernie image models
AI release May 30, 2026

koboldcpp 1.114

Experimental parallel text generation, RPC backend for distributed GPU sharing across networks, LTX2.3 video generation support, and multiple new image generation models added
AI release May 29, 2026

LocalAI 4.3.5

LocalAI 4.3.5 fixes tool-calling bugs with streaming and tokenizer templates, adds per-request reasoning effort control, and updates dependencies
AI release May 29, 2026

llama.cpp b9414

Adds DeepSeekOCR 2 support with multi-tile dynamic resolution
AI release May 29, 2026

Cline CLI 3.0.15

Cline CLI 3.0.15 adds Cline Hub for remote session monitoring, global agent rules, Discord participant muting, and updates model catalog with Claude Opus 4.8 and others
AI release May 29, 2026

llamafile 0.10.2

Llamafile 0.10.2 improves GPU acceleration detection, fixes CPU flash-attention and MoE matmul operations, and reduces CUDA library size
AI release May 29, 2026

whisper.cpp 1.8.5

Whisper.cpp 1.8.5 fixes server parameter handling, VAD streaming, Ruby binding memory leaks, and timestamp accuracy
AI release May 29, 2026

vLLM 0.22.0

VLLM 0.22.0 hardens DeepSeek V4 with fused kernels and CUDA graphs, advances Model Runner V2 toward default, adds experimental Rust frontend, and enables multi-tier KV cache offloading for extended memory management
AI release May 29, 2026

Jan 0.8.1

Jan 0.8.1 fixes model re-download tombstones, disables llamacpp auto-fit, uses OS-native TLS on desktop, and restores Settings attachments menu
AI release May 28, 2026

langchain-anthropic== 1.4.4

Normalizes cross-provider tool-call IDs in Anthropic integration to ensure consistent behavior across different LLM providers
AI release May 28, 2026

Cline 3.86.0

Adds Opus 4.8 including 1M-context variants where available
AI release May 28, 2026

LocalAI 4.3.3

LocalAI 4.3.3 updates core inference backends, fixes OpenAI API response compatibility, and optimizes UI bundle performance
AI release May 28, 2026

openclaw 2026.5.27

Security hardening isolates group prompts from system context, Codex app-server runtime stabilizes through memory routing and helper-failure recovery, and provider coverage expands with OpenAI-compatible embeddings and Pixverse video generation
AI release May 27, 2026

llama.cpp b9368

Mesa users on Intel BMG should see a 4.8 percent tg128 improvement for Qwen3.5-9B BF16 workloads
AI release May 27, 2026

langchain-fireworks== 1.4.2

Fireworks integration strips non-wire keys from content parts before serialization to prevent serialization errors
AI release May 27, 2026

InvokeAI 6.13.0

InvokeAI now supports Qwen Image 2.5, Qwen Image Edit 2.5, and Anima locally, plus externally-hosted models from OpenAI, Google, BytePlus, and Alibaba Cloud via API keys
AI release May 27, 2026

HelixML 2.11.13

HelixML 2.11.13 fixes npx binary detection, desktop shutdown crashes, and API pull request error handling
AI release May 27, 2026

langchain-perplexity== 1.3.0

ChatPerplexity now respects responses API flag; No impact unless that parameter is in use
Security May 27, 2026

Warp's big bet on building open source with GPT 5.5

Warp uses GPT-5.5 and OpenAI models to coordinate coding agents across local, cloud, and open-source development workflows
AI release May 26, 2026

AnythingLLM 1.13.0

Agent system rewrite changes interaction model toward passive and hybrid workflows; Existing agent configurations may need review
AI release May 26, 2026

llama.cpp b9334

CUDA users should upgrade for the PDL sync fix; MacOS KleidiAI artifacts now shipping
AI release May 25, 2026

Cline 3.85.0

GPT-5.5 now available in SAP AI Core provider configurations
AI release May 25, 2026

LocalAI 4.3.1

Fixes build break in kokoros backend. Upgrade if that backend is in use
AI release May 24, 2026

openclaw 2026.5.22

Gateway startup performance improved through lazy-loading, metadata caching, and channel-read reuse; Meeting-notes plugin and extensive documentation clarifications added
AI release May 24, 2026

llama.cpp b9305

Fixes UI build and adds macOS KleidiAI artifacts. No impact unless building the UI or deploying on Apple Silicon with KleidiAI
AI release May 23, 2026

llama.cpp b9297

Adds NVFP4 MTP scale tensors and links Qwen3.5 MTP tensors. No action unless running Qwen3.5 or NVFP4 hardware
AI release May 22, 2026

llama.cpp b9289

SYCL backend now supports gated_delta_net operations with K 1 for improved inference performance on Intel GPUs
AI release May 22, 2026

Cline CLI 3.0.11

Cline CLI 3.0.11 fixes ChatGPT OAuth token limits, adds Vertex Gemini authentication, and includes tool names in result logs for clearer session tracking
AI release May 22, 2026

Cline CLI 3.0.10

Cline CLI adds local plugin installs, Poolside/Gemini 3.5 Flash support, Telegram auto-detection, and performance optimizations for settings caching
AI release May 22, 2026

Jan 0.8.0

Adds MiniMax cloud provider and replaces Swift HTTP server with Rust FFI via fm-rs. Check integrations if using Foundation Models
AI release May 21, 2026

HelixML 2.11.12

Improved UI persistence, mobile layout fixes, system theme support, and stream reconnection stability across desktop and web clients
AI release May 21, 2026

langchain-tests== 1.1.9

Standard test suite relaxes streaming assertion validation to allow extra content blocks in LLM responses
AI release May 21, 2026

HelixML 2.11.10

HelixML fixes sandbox image pulling, external agent validation, and project deletion responsiveness
AI release May 21, 2026

llama.cpp b9258

Merges HunyuanOCR into HunyuanVL vision path and restores bilinear sampler precision for OCR tasks
AI release May 20, 2026

langchain-fireworks== 1.4.0

Migrates to fireworks-ai 1.x SDK. Breaking change for anyone pinning older SDK versions
AI release May 20, 2026

openclaw 2026.5.19

Agents now default to clean bounded refactors with explicit deprecation paths; Gateway startup latency reduced; Skills expanded with meme-maker, autoreview, Python debugging, node inspector; Browser modal dialogs surfaced
AI release May 20, 2026

ComfyUI 0.22.0

Audio processing nodes now handle None inputs gracefully
AI release May 20, 2026

text-generation-webui 4.9

Adds MTP speculative decoding via draft-mtp spec type
AI release May 20, 2026

Hugging Face Transformers 5.9.0

Adds Cohere2Moe Command A+ MoE model with hybrid attention
AI release May 20, 2026

llama.cpp b9245

RDNA3 GPU kernels for Q6_K quantized inference now use tuned warp configurations for better performance
AI release May 20, 2026

Cline CLI 3.0.9

CLI startup and plugin config toggles faster via concurrent sandboxed loading and optimistic updates, fuzzy file picker restored, session persistence on task cancel
AI release May 19, 2026

Dify 1.14.2

Dify 1.14.2 patches security isolation, workflow reliability, knowledge-base stability, and RAG document handling for production AI app deployments
AI release May 19, 2026

llama.cpp b9222

Adds Hexagon TRI op support; Matters only if targeting Qualcomm HTP acceleration
AI release May 18, 2026

openclaw 2026.5.18

Agents, browser automation, skills, plugins, proxy, and QA testing improvements including admin RPC login flows, modal dialog handling, tool plugin framework, and runtime parity scenarios
AI release May 18, 2026

langchain-tests== 1.1.8

Langchain-tests 1.1.8 constrains langchain-core version bounds and fixes per-call model override behavior in standard tests
AI release May 18, 2026

llama.cpp b9216

Llama.cpp UI refactored models store, MCP service, and debug logging behind environment flags to reduce noise and improve performance
AI release May 18, 2026

NanoClaw 2.0.64

Destination add/remove via approval flow now takes effect immediately instead of requiring container restart or silently failing on send
AI release May 18, 2026

HelixML 2.11.10

HelixML 2.11.10 fixes sandbox image pulls, skips validation for subscription agents, and improves project deletion UX
AI release May 18, 2026

Cline CLI 3.0.7

Cline CLI 3.0.7 eliminates startup network round-trip for ChatGPT OAuth and aligns available models to subscription tier
AI release May 17, 2026

llama.cpp b9198

Vulkan build now checks for SPIRV-Headers availability upfront to catch configuration issues before compilation starts
AI release May 16, 2026

Venice MCP Server 0.2.0

The project reached GA. No detail on what changed from prior beta
AI release May 16, 2026

LocalAI 4.2.5

LocalAI 4.2.5 fixes Ollama model listing, TTS output handling, parameter parsing, and improves OpenAI API compliance with upstream dependency updates
AI release May 16, 2026

koboldcpp 1.113.1

Breaking change: split mode now set independently to accommodate experimental tensor split. Existing launch scripts may need adjustment
AI release May 16, 2026

koboldcpp 1.113.2

KoboldCpp 1.113.2 fixes router mode regressions, splits tensor configuration independently, adds LoRA directory selection, and improves VAE decoding speed
AI release May 16, 2026

llama.cpp b9174

Moves web UI output directory and renames CMake variables. Existing build scripts may need path adjustments
AI release May 15, 2026

NanoClaw 2.0.63

NanoClaw 2.0.63 establishes proper release tagging, makes service names per-install, and fixes message wrapping, MCP credential routing, and CLI scope leaks
AI release May 15, 2026

vLLM 0.21.0

VLLM 0.21.0 adds KV offload + hybrid memory allocator integration, speculative decoding with thinking budgets, TOKENSPEED_MLA for Blackwell, and requires C++20 and Transformers v5
Security May 15, 2026

Databricks brings GPT 5.5

Databricks uses GPT-5.5 for enterprise agent workflows after the model set a new state of the art on the OfficeQA Pro benchmark
AI release May 14, 2026

Cline CLI 3.0.3

Adds a worktree flag for isolated task execution. Useful for parallel task runs without branch pollution
AI release May 14, 2026

llama.cpp b9156

Adds Qwen3.5 tokenizer support. No impact unless loading Qwen3.5 weights
AI release May 14, 2026

LlamaIndex 0.14.22

LlamaIndex core adds multimodal synthesis, fixes embedding event inheritance and cache persistence in multiprocessing pipelines, and updates dependencies across callback integrations
AI release May 14, 2026

HelixML 2.11.7

ARM64 builds restored, settings-sync daemon fixes context_server overrides, API provider model cache stale fallback improved, org lookup 404 resolved
AI release May 13, 2026

LocalAI 4.2.4

LocalAI 4.2.4 fixes distributed node cleanup, proxy prefix handling, agent job persistence races, and OpenAI tool_choice parsing, plus adds Vulkan VRAM detection and Liquid Audio speech models
AI release May 13, 2026

ComfyUI 0.21.1

Added Flux2, HiDream-O1, and Claude nodes, fixed fp8 safetensors saving and LTXV video alignment, improved memory usage
AI release May 13, 2026

Ollama 0.23.4

Ollama launch now handles vision models with image inputs. Local image paths work in Claude tool results
AI release May 13, 2026

Ollama 0.30.0

Ollama now builds directly on llama.cpp with GGUF format support and MLX acceleration for Apple Silicon inference
AI release May 13, 2026

llama.cpp b9129

Llama.cpp ZenDNN backend now adaptively falls back to CPU for small batch sizes, improving efficiency via runtime control
AI release May 13, 2026

Hugging Face Transformers Patch 5.8.1

Fixes Deepseek V4 integration. Update if using that model
AI release May 12, 2026

llm CLI 0.32a2

Llm CLI now supports OpenAI's Responses API for reasoning-capable models, streaming visible reasoning summaries and enabling interleaved reasoning across tool calls
AI release May 12, 2026

langchain== 1.3.0

LangChain agents now support v3 event streaming for improved visibility into agentic execution flows
AI release May 12, 2026

Dify 1.14.1

Dify 1.14.1 hardens self-hosted deployments with runtime SECRET_KEY generation, fixes workflow stability and IDOR issues, patches dependency CVEs, and improves knowledge-base filtering
AI release May 11, 2026

LocalAI 4.2.0

LocalAI 4.2.0 adds voice and face recognition, diarization, Ollama-compatible API, video generation, and eleven new backends for multimodal local AI workloads
AI release May 10, 2026

vLLM 0.20.2

VLLM 0.20.2 fixes DeepSeek V4 sparse attention hangs, KV cache allocation failures, gpt-oss torch.compile compatibility, and Qwen3-VL load issues
AI release May 9, 2026

Open WebUI 0.9.4

Chat conversations now scroll to the bottom reliably on load, fixing a regression caused optimization
AI release May 8, 2026

langchain== 1.2.18

LangChain 1.2.18 reverts agent-type tagging, deprecates hub operations, and retargets create_agent deprecations
AI release May 5, 2026

Hugging Face Transformers 5.8.0

Transformers 5.8.0 adds DeepSeek-V4, Gemma4 Assistant for speculative decoding, GraniteSpeechPlus speech-to-text, Granite4Vision for document extraction, and EXAONE-4.5 vision-language model