// Release stream · daily archive
Sat, Oct 17
133 releases from tracked repos.
Sat, Oct 17· 81
-
TauricResearch/TradingAgents v0.7.0 Minor Desktop app
Runs on your ChatGPT plan, backtests scored from the first close after each decision, a note at start-up when a newer release is out, and a wheel attached to each GitHub release.
-
thedotmack/claude-mem v14.0.0 Major +1 more
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future se…
-
anthropics/claude-code v2.1.302 Patch Desktop appNew agent
Added `CLAUDE_CODE_AUTO_MODE_MODEL` to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode
-
lobehub/lobehub v2.2.20-canary.7 Major
LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
-
jackwener/OpenCLI v2.0.0 Major
A major release focused on agent experience: a smaller CLI surface, predictable JSON results, native Chrome APIs, and evidence-driven adapter development. Includes Chrome extension **1.0.25**.
-
coleam00/Archon v0.12.0 Minor New agent +1 more
Providers become separate installs for release binaries. The SDLC pack gains intake, build and merge queues, a discoveries drain and attention pauses. Runs wait out usage and rate limits. Workflows can run without a data
-
aaif-goose/goose v1.55.0 Minor
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
-
Anil-matcha/open-dots v0.1.0 First releasepre Desktop app
Open Dots v0.1.0 — First Pre-release (Windows + macOS)
-
windmill-labs/windmill v1.838.0 First release +1 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…
-
openai/openai-python v3.33.0 Minor +1 more
3.33.0 (2026-10-16)
-
code-yeongyu/oh-my-openagent v5.1.35 Patch New agent
The omo-senpi typecheck gives the same result wherever the checkout sits.** It used to pick up `@types/node` from folders above the checkout, so a stray older copy there failed the typecheck while CI passed on the same c
-
openai/codex rust-v0.164.0-alpha.2 First releasepre +1 more
Lightweight coding agent that runs in your terminal
-
dream-num/univer v1.1.0 Minor
New features
-
NVIDIA/SkillSpector v2.13.0 Minor
SkillSpector v2.13.0
-
osaurus-ai/osaurus 0.25.23 Patch Desktop app
Integrate native workflow media controls, video and memory admission (#3104) by @jjang-ai
-
can1357/oh-my-pi v18.11.3 Patch New agent
@oh-my-pi/pi-agent-core
-
kortix-ai/suna v0.14.0 Minor
One credits plan.** Every account is on Free or Credits, with top-ups on either. Balances and usage read in credits everywhere; prices you pay stay in your currency. Raising your plan applies at once; lowering it takes e
-
langchain-ai/deepagents deepagents==0.7.27 Patch New agent +2 more
Keep the main agent informed of asynchronous subagent status updates (#6853).
-
ollama/ollama v0.40.6 Patch +1 more
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
-
jarrodwatts/claude-hud v0.11.3 Patch New agent
Background agents whose completion notice is logged as a queued command (seen in forked or resumed sessions) no longer stay `◐` running after they finish (#810).
-
openai/openai-node v7.36.0 Minor +1 more
Official JavaScript / TypeScript library for the OpenAI API
-
DietrichGebert/ponytail v5.3.2 Patch
Ponytail 5.3.2 brings your old sessions to the board. `/ponytail band import` reads your past Claude Code sessions once and adds them with their cost, agent time and tokens, so you can compare them with today's. The boar
-
farion1231/cc-switch v4.0.15 Patch
CC Switch v4.0.15
-
langchain-ai/langchain langchain-core==1.6.12 Patch
Changes since langchain-core==1.6.11
-
github/spec-kit v1.2.1 Patch
Toolkit to help you get started with SDD or any other process!
-
Graphify-Labs/graphify v0.9.92 Patch
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deter…
-
stablyai/orca v1.4.229 Patch +1 more
Thank you so much for using Orca and for your continued support! ❤️
-
YishenTu/claudian 2.3.23 Patch New agent
fix: keep Claude subagent history out of session metadata (#1671)
-
tangency-labs/solidcraft v0.15.0 Minor
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.
-
siteboon/claudecodeui v1.37.5 Patch New agent
1.37.5 (2026-10-17)
-
cline/cline desktop-v0.0.48 Patch +2 more
GPT-6 models (such as `gpt-6-sol` and `gpt-6.1-sol`) work on OpenAI and Azure OpenAI-compatible endpoints. Before, every request was rejected because Cline sent `max_tokens` instead of `max_completion_tokens`
-
heygen-com/hyperframes v0.8.168 Patch +3 more
HyperFrames v0.8.168
-
hugohe3/ppt-master v6.7.2 Patch
Patch release: fixes from an audit of the issue history. Most of them stop a tool from losing, overwriting or rewriting content while it reports success.
-
ultralytics/ultralytics v8.4.180 Patch +1 more
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
-
router-for-me/CLIProxyAPI v8.0.32 Patch
Linux release assets
-
QuantumNous/new-api v1.0.0-rc.45 Patch
[!IMPORTANT]
-
alibaba/open-code-review v1.13.1 Patch
fix(config): fix bad config for providers or keys that cotains dots (self-defined) (#1661)
-
DeusData/codebase-memory-mcp v0.12.1 Patch +1 more
Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware…
-
langchain-ai/langgraph 1.2.16 Patch +2 more
Changes since 1.2.15
-
Yeachan-Heo/oh-my-claudecode v5.7.4 Patch
oh-my-claudecode v5.7.4: More reliable hooks, team workflows, HUD, and Jev planning
-
NandhaKishorM/laya v0.4.10 Patch +1 more
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the rig…
-
onyx-dot-app/onyx helm/onyx-0.9.17 Sub-package
Onyx application and Craft sandbox deployment chart
-
feder-cr/invisible_dots golden-798090c64bb0 Rolling +2 more
The golden image of the inputs 798090c64bb0, 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
-
topoteretes/cognee v1.6.5 Patch
v1.6.5 — Faster trace processing & richer code-graph docs
-
Niko1221/Strata v0.1.45 Patch
: Qwen3.6-35B-A3B reads pictures, serves several requests at once and runs up to 40% faster; switches for multi-user servers; Mac and setup fixes.** Answers of the Qwen3.8-Flash-Next models are the same as in 0.1.44.1 (b
-
simstudioai/sim v0.9.25 Patch
feat(library): How Do You Embed an AI Agent Inside Your SaaS Product? (#9130)
-
h4ckf0r0day/obscura v0.2.5 Patch
The headless browser for AI agents and web scraping
-
PrefectHQ/fastmcp v3.4.9 Patch
This release backports security fixes from 4.1: OpenAPI path parameters reject `.` and `..` segments, a skill's `SKILL.md` must stay inside its skill folder, regex tool search is bounded in time and pattern length, and J
-
Kilo-Org/kilocode jetbrains/v7.1.11 Sub-package Mobile +2 more
List remote agents for the mobile app.
-
deepseek-ai/deepseek-harness dsh-v0.2.1-rc.2 Patchpre +1 more
DeepSeek Harness: Everything is a Plugin.
-
langchain-ai/langgraphjs @langchain/[email protected] Sub-package New agent +8 more
Framework to build resilient language agents as graphs.
-
lexmount/moli v1.1.18 Patch
CDP, Navigation & Window
-
confident-ai/deepeval typescript-v0.9.23 Patch +3 more
The LLM Evaluation Framework
-
MODSetter/SurfSense v2.2.2 Patch
makes sources usable seconds after you add them, and adds speech recognition that runs on this computer: recordings become sources, and a mic in the composer turns your voice into text. PDFs with a text layer and Word fi
-
Unstructured-IO/unstructured 0.27.28 Patch
feat: opt-in langdetect-rs backend for partition language detection by @kholdrex in https://github.com/Unstructured-IO/unstructured/pull/4547
-
browseros-ai/BrowserOS claw-server%2Fv0.0.75 Patch +1 more
The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.
-
anthropics/claude-agent-sdk-typescript v0.3.302 Patch New agent
Fixed structured output results delivering a response's output as `structured_output` when the API refused that response; the result is now an error with no payload
-
google-gemini/gemini-cli v0.66.0-nightly.20261017.ged96faedf Patchpre
Add Banner about Gemini CLI not being optimized for Gemini 4 by @srithreepo in https://github.com/google-gemini/gemini-cli/pull/29774
-
TencentCloud/Octop v1.0.2b9 Patch
A smarter, self-hosted AI assistant — multi-user, multi-agent.
-
vllm-project/vllm v0.32.0rc3 Patchpre
A high-throughput and memory-efficient inference and serving engine for LLMs
-
NVIDIA/garak v0.17.1 Patch
the LLM vulnerability scanner
-
infiniflow/ragflow dev-20261019 Rollingpre
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
-
rtk-ai/rtk dev-1.0.2-rc.552 Patchpre +2 more
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
-
leejet/stable-diffusion.cpp master-973-f0aac52 Rolling +2 more
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
-
open-multi-agent/open-multi-agent v1.21.3 Patch
Symlink loops and chains longer than the kernel's link limit now fail the sandbox check with a `Too many levels of symbolic links` error. Earlier versions also failed these writes, with the filesystem error instead.
-
vitali87/code-graph-rag v0.2.7 Patch
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
-
OpenBMB/PilotDeck v2026.10.17 Rolling
Task-oriented AI Agent productivity platform
-
siyuan-note/siyuan v3.8.8-alpha.3 Patchpre
Improve menu height and positioning for dynamically added items
-
archestra-ai/archestra platform-v1.3.75 Patch +2 more
1.3.75 (2026-10-17)
-
langroid/langroid 0.69.10 Patch +1 more
Harness LLMs with Multi-Agent Programming
-
samuelgursky/davinci-resolve-mcp v4.13.7 Patch +4 more
v4.13.7 — Missing-media relink works for paths written on another OS
-
trycua/cua cua-spaces-v0.9.4-rc.3 Patchpre
Automated Cua Spaces release.
-
QwenLM/qwen-code v0.25.2-nightly.20261016.b4614845f0 Patchpre New model +1 more
fix(managed-agent): admit team_plan_approval into the journal-only interrupted-turn settle (#13847) by @wenshao in https://github.com/QwenLM/qwen-code/pull/14160
-
manaflow-ai/cmux cmux-app-ffi-cb72f89622aeaa2c41bd5deb88bf69bc0b237d81 Rollingpre
The cmux app FFI (remote desktop core + sidebar layout reducer) as CCmuxAppFFI.xcframework (one static library, universal macOS arm64/x86_64). Source cb72f89622aeaa2c41bd5deb88bf69bc0b237d81. SwiftPM binaryTarget checksu
-
turboderp-org/exllamav3 v1.6.3 Patch
Support BailingMoeV3ForCausalLM (Ling-3.0, 3.1)
-
Comfy-Org/workflow_templates v0.11.87 Patch
ComfyUI template workflows
-
Tencent-Hunyuan/Hy-Memory v1.0.2 Patch
fix(memhub): relaunch safely with existing runtimes by @txfei in https://github.com/Tencent-Hunyuan/Hy-Memory/pull/18
-
langchain-ai/open-swe desktop-v0.3.8-nightly.20261017082058 Patchpre +2 more
fix(reviews): isolate diff highlights by revision by @ramon-langchain in https://github.com/langchain-ai/open-swe/pull/4182
-
vastsa/PI-Desktop v0.21.0-beta.3 Patchpre +1 more
Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins
-
apache/maka v0.2.1-dev.89.20261016 Patchpre
Developer Snapshot 0.2.1-dev.89.20261016
-
awslabs/aidlc-workflows v2.11.1-preview.20261016.1 Patchpre
AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents
Nothing matches this filter.