// Release stream · daily archive
Thu, Oct 22
219 releases from tracked repos.
HEADLINES
Highlightanthropics/claude-codev2.1.307
Highlightobra/superpowersv7.0.1
Thu, Oct 22· 79
-
anthropics/claude-code v2.1.307 Patch Desktop appNew agent
Added `/claude-api api-version` to move Claude API code to API version `2026-10-21`
-
esengine/DeepSeek-Reasonix v2.48.0 Major +1 more
A reliable coding agent for complex software engineering tasks.
-
farion1231/cc-switch v4.0.18 Patch Desktop app
CC Switch v4.0.18
-
obra/superpowers v7.0.1 Patch New agent
This release retunes brainstorming after its rebuild in v7.0.0. Many of you told us, rightly, that the new default questions got annoying fast and felt formulaic. Brainstorming now digs for context before it asks anythin
-
OpenHands/OpenHands v1.30.0 Minor
(2026-10-22)
-
zed-industries/zed v1.25.2 Minor +1 more
This week's release includes smaller Zed binaries across macOS, Windows, and Linux, the ability to apply inlay hint text edits by double-clicking, context compaction and session notices for external agents, and new GPT-6
-
langchain-ai/langgraphjs @langchain/[email protected] Sub-package +11 more
Framework to build resilient language agents as graphs.
-
ComposioHQ/composio py%400.29.0 First release +9 more
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
-
strands-agents/harness-sdk typescript/v1.22.0 Sub-package New agent +2 more
typescript/v1.22.0
-
vectorize-io/hindsight v1.1.0 Minor
docs: v1.0.0 changelog, Memlake launch post, and version-1.0 docs snapshot by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5550
-
comet-ml/opik 2.2.114-9120-merge-4045 First release +9 more
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
-
yetone/magpie v0.1.1318 Patch Desktop app +5 more
Fixed tray allowances showing their history and redrawing unnecessarily.
-
k2-fsa/sherpa-onnx tauri Rolling Desktop app
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support em…
-
czlonkowski/n8n-mcp v2.95.0 Minor
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
-
trycua/cua cua-spacesd-v0.7.0 Minor
cua-spacesd 0.7.0 release assets.
-
Infisical/infisical v0.167.0 Minor
feat(code-signing): use an existing DigiCert certificate and its HSM key in a signer by @carlosmonastyrski in https://github.com/Infisical/infisical/pull/8743
-
QwenLM/qwen-code desktop-v0.26.0 Minor +3 more
feat(daemon): support session-targeted Skill and Extension refresh by @callmeYe in https://github.com/QwenLM/qwen-code/pull/14050
-
windmill-labs/windmill v1.846.0 Minor +4 more
Open-source developer platform to power your entire infra and turn scripts into webhooks, workflows and UIs. Fastest workflow engine (13x vs Airflow). Open-source alternative to…
-
tangency-labs/solidcraft v0.18.4 Patch Desktop app
SolidCraft is open-source parametric 3D CAD in Rust: sketch, constrain, extrude, and change a parameter to watch the timeline rebuild. Website · documentation · try it in the browser · Discord · issues.
-
NousResearch/hermes-agent v0.22.4 Patch +1 more
The agent that grows with you
-
Yeachan-Heo/oh-my-claudecode v5.7.7 Patch New agent
oh-my-claudecode v5.7.6: Build artifact fixes and hook improvements
-
can1357/oh-my-pi v18.12.6 Patch New agent
@oh-my-pi/pi-catalog
-
akitaonrails/ai-memory v3.2.0 Minor
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
-
langchain-ai/deepagents deepagents==0.7.30 Patch New agent
Async subagent follow-ups can now queue without interrupting active work (#7082).
-
microsoft/markitdown v0.1.9 Patch
increase chunk size from 512 bytes to 64 KB for HTTP response reading by @YasirAlibrahem in https://github.com/microsoft/markitdown/pull/1511
-
Arize-ai/phoenix arize-phoenix-v20.24.0 Minor +6 more
20.24.0 (2026-10-21)
-
ollama/ollama v0.40.8 Patch +2 more
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
-
modelcontextprotocol/inspector 2.12.0 Minor +1 more
Visual testing tool for MCP servers
-
mcp-use/mcp-use mcp-use%402.12.0-canary.1 Minor +7 more
The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.
-
ARahim3/DigUp v0.6.2 Patch Desktop app
Fixes for the ten days since 0.6.1, with a lot of them from people who sent pull requests, and spreadsheets and presentations as a new kind of file.
-
inkeep/open-knowledge v0.88.0-beta.3 Minorpre Desktop app +6 more
Delta since previous beta (v0.88.0-beta.2) — 1 new changeset.
-
langchain-ai/langchain langchain==1.4.7 Patch +2 more
Changes since langchain==1.4.6
-
ggml-org/llama.cpp b11804 Rolling +7 more
LLM inference in C/C++
-
openai/codex rust-v0.164.0-alpha.10 Minorpre +1 more
Lightweight coding agent that runs in your terminal
-
BuilderIO/agent-native %40agent-native%2Ftoolkit%400.214.0 Minor +3 more
A framework for building agentic apps
-
vercel/eve eve%400.82.0 Minor
The Open Framework for Building Agents
-
langwatch/langwatch langwatch-3.21.0 Minor +4 more
Open-Source Agent Observability & Evals for AI Platform teams. Trace, test, route and govern every agent & coding assistant in the company.
-
ruvnet/ruflo v3.59.13 Patch +4 more
fix(claims): anchor MCP claims store to project cwd** (#3210) — claims persistence now resolves via `getProjectCwd()` instead of a raw `resolve(CLAUDE_DIR)`, matching every other file-backed MCP tool. A claims-aware MCP
-
heygen-com/hyperframes v0.8.185 Patch +1 more
HyperFrames v0.8.185
-
anthropics/anthropic-sdk-python v2.1.0 Minor
api:** add enforcement status, actions and filter to user profiles
-
QuantumNous/new-api v1.0.0-rc.46 Patch New model
[!IMPORTANT]
-
onyx-dot-app/onyx helm/onyx-0.9.21 Sub-package +2 more
Onyx application and Craft sandbox deployment chart
-
feder-cr/invisible_dots golden-1cf048d96945 Rolling
The golden image of the inputs 1cf048d96945, built by the golden image workflow from ef69f5e19c1b46e41e743234fa5019e39442adcb. invisible-dots image build downloads it when a checkout's inputs have this digest. It holds U
-
simstudioai/sim v0.9.31 Patch +1 more
feat(chat): recall sent messages from composer (#9289)
-
archestra-ai/archestra platform-v1.4.0 Patch New agent +4 more
1.4.0 "Arpa" (2026-10-21)
-
deepset-ai/haystack v3.4.1 Patch +2 more
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control ove…
-
genkit-ai/genkit middleware-v0.11.0-rc.3 First releasepre +9 more
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
-
lexmount/moli v1.1.19 Patch
CDP, Inspector & Browser Lifecycle
-
NVIDIA/open-gpu-kernel-modules 580.196.07 Patch +1 more
NVIDIA Linux open GPU kernel module source
-
dagger/dagger sdk%2Frust%2Fv0.21.11 Release +7 more
Automation engine to build, test and ship any codebase. Runs locally, in CI, or directly in the cloud
-
web-infra-dev/midscene v1.16.3 Patch
See interfaces like a human. E2E testing in natural language.
-
superset-sh/superset desktop-canary Rolling
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
-
Unstructured-IO/unstructured 0.27.33 Patch
fix(chunking): don't repeat a very large split element in every chunk by @kholdrex in https://github.com/Unstructured-IO/unstructured/pull/4565
-
xerj-org/xerj pack-xerj-storage-e449d171 Rolling +9 more
Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search wi…
-
elie222/inbox-zero desktop-v0.1.21 Patch
The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
-
omnigent-ai/omnigent v0.19.1 Patch
We have updated our dependencies to mitigate the impact from the recent eMudhra Intermediate CA Compromise.
-
github/copilot-sdk v1.0.25-unstable.39668197943.gc332e3b Patch +7 more
Multi-platform SDK for integrating GitHub Copilot Agent into apps and services
-
anthropics/claude-agent-sdk-python v0.2.171 Patch
Internal/Other Changes
-
leejet/stable-diffusion.cpp master-987-a77d362 Rolling +4 more
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
-
Gentleman-Programming/engram v3.5.2 Patch
d85c45701129d19c2a165266d279c5c195283726 fix(release): ignore generated distribution output (#1959)
-
bethington/ghidra-mcp v7.0.0 Patch
Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server i…
-
Blaizzy/mlx-vlm v0.7.10 Patch
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
-
vitali87/code-graph-rag v0.2.14 Patch
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
-
-
Agenta-AI/agenta v0.122.10 Patch
Clearer run failures.** When an agent run fails in the playground, the failure now reads like an agent answer. The full server message is shown, and the ways to recover (add a key, buy credits, change the plan) stay next
-
omnirush-ai/omnirush-gui v3.7.2 Patch +1 more
A desktop coding agent with free access to frontier models.
-
UKGovernmentBEIS/inspect_ai 0.3.283 Patch
Inspect: A framework for large language model evaluations
-
charmbracelet/crush nightly Rollingpre
Verifying the artifacts
-
NVIDIA-NeMo/DataDesigner v0.9.7 Patch
NeMo Data Designer 0.9.7 updates CA trust following the eMudhra compromise and improves process and dependency compatibility.
-
anthropics/claude-agent-sdk-typescript v0.3.307 Patch
Added `wakeup_source` to the `command_lifecycle` `started` frame of a scheduled wakeup or task, and `scheduled_for` for a wakeup (capability `lifecycle_wakeup_source_v1`), so a host can tell which one fired
-
NVIDIA/TensorRT-LLM v1.4.0rc1 Patchpre
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on…
-
Comfy-Org/workflow_templates v0.11.94 Patch
ComfyUI template workflows
-
altic-dev/FluidVoice windows-v0.0.12 Patchpre
File Transcription**: drop an audio or video file (MP3, M4A, WAV, FLAC, OGG, Opus, MP4, MOV, MKV, WebM and more) on the new File Transcription page to get a transcript with your active voice model. Recordings up to 3 hou
-
langchain-ai/openevals openevals==0.2.2 Patch +1 more
chore: add Dependabot configuration by @jkennedyvz in https://github.com/langchain-ai/openevals/pull/228
-
langchain-ai/open-swe desktop-v0.3.8-nightly.20261022021836 Patchpre +1 more
build(mda): carry upstream browser localhost sharing by @byhow in https://github.com/langchain-ai/open-swe/pull/4328
-
ibm-granite/granite-tsfm v0.3.11 Patch
Add model-compatible output aliases to ForecastResult by @fearghalodonncha in https://github.com/ibm-granite/granite-tsfm/pull/550
-
truefoundry/trueforge @truefoundry/[email protected] Sub-packagepre
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
-
awslabs/aidlc-workflows v2.11.2-preview.20261021.1 Patchpre
AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents
-
vllm-project/vllm-metal v0.32.0.dev20261022015004 Patchpre +1 more
Community maintained hardware plugin for vLLM on Apple Silicon
Nothing matches this filter.