// Release stream · daily archive

Tue, Oct 13

190 releases from tracked repos.

Next day: 10-14 → ← Previous: 10-12

Show pre-releases & patches

Tue, Oct 13· 105

vectorize-io/hindsight v1.0.0 Major

fix(docs): overview hero reaches the window edges on wide screens by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5440

22:08
milvus-io/milvus pkg%2Fv3.0.3 Major

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

20:19
langfuse/langfuse v4.58.0 Major +2 more

feat(web): require Turnstile on password-reset emails by @maxdeichmann in https://github.com/langfuse/langfuse/pull/18584

15:05
oraios/serena v2.0.0 Major

See change log

20:25
kestra-io/kestra v2.0.6 Major +1 more

Event Driven Orchestration & Scheduling Platform for Mission Critical Applications

22:25
tangency-labs/solidcraft v0.7.0 First release Desktop app +2 more

SolidCraft is open-source parametric 3D CAD in Rust: sketch, constrain, extrude, and change a

11:38
google/adk-go v2.6.0 Major

fix(artifact): keep session filenames out of shared listings by @ktsoator in https://github.com/google/adk-go/pull/1673

22:09
DietrichGebert/ponytail v5.2.0 Minor +1 more

Mostly fixes for the level you pick. It now survives context compaction instead of falling back to the default, and on macOS the hooks can no longer lose their output, so the ruleset always arrives.

09:48
github/spec-kit v1.2.0 Minor

uv tool install specify-cli --from git+https://github.com/github/[email protected]

23:49
thedotmack/claude-mem v13.37.0 Minor +2 more

This release fixes the broken 13.36.1 marketplace update. After that update, the worker, the MCP search server and the server runtime failed to start, so memory capture stopped. Upgrading is strongly recommended.

11:07
esengine/DeepSeek-Reasonix studio-v2.38.0 First release +1 more

本版加入从任意回复分支会话、会话批量操作、模型显示别名和 MCP 工具定义变更审批，并修复长对话里拖选文字卡死、重载后丢失撤销入口等问题。

09:43
upstash/context7 mcpb-v4.4.0 Minor +7 more

MCP Bundle for @upstash/[email protected]

21:35
strands-agents/harness-sdk python/v1.60.0 Sub-package New agent

python/v1.60.0

03:37
alibaba/open-code-review v1.13.0 Minor

feat(auth): enable ChatGPT plan reviews through public Responses (#1622)

18:09
langchain-ai/langgraph checkpoint==4.3.0 Minor +4 more

Changes since checkpoint==4.2.0

06:26
google/agents-cli v1.10.0 Minor New agent

Release v1.10.0

03:47
CopilotKit/CopilotKit v1.79.0 Minor

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

01:28
browseros-ai/BrowserOS claw-server%2Fv0.0.71 First release +3 more

The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.

09:35
genspark-ai/genoffice v0.11.727 Patch Desktop app

GenOffice v0.11.727 stable desktop installers.

23:10
wheresryan22/anatomy v1.1.0 Minor

An agent skill for creating detailed, interactive isometric illustrations of real-world machines and complex systems. Generates polished SVGs with optional WebGL shaders and 3D…

02:43
windmill-labs/windmill v1.831.0 Minor

1.831.0 (2026-10-13)

22:02
weaviate/weaviate v1.40.1 Minor +2 more

Breaking Changes

14:35
modelscope/ms-swift v4.6.0 Minor

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5…

21:30
millionco/react-doctor v2.4.0 Minor +4 more

Your agent writes bad React. This catches it

07:16
vastsa/PI-Desktop v0.19.0 First release +3 more

Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins

11:56
run-llama/liteparse docker-v2.16.0 Minor +3 more

Docker images published to GHCR:

06:09
ollama/ollama v0.40.4 Patch

Decision models in the CLI

03:00
ARahim3/DigUp v0.6.1 Patch Desktop app

Fixes for what people ran into in the first week, and a few additions.

00:20
aipoch/open-science v0.37.2 Patch Desktop app

AIPOCH Open-Science v0.37.2

13:10
farion1231/cc-switch v4.0.11 Patch +1 more

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

23:39
Graphify-Labs/graphify v0.9.89 Patch +1 more

(2026-10-13)

18:43
apify/apify-mcp-server v0.18.0 Minor

The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scraper…

15:55
paperclipai/paperclip v2026.1012.0 Rolling New model

Paperclip v2026.1012.0

05:06
ruvnet/RuView v3263 Rolling +11 more

Source snapshot validated by the CI pipeline. This entry does not contain firmware bundles.

12:27
vllm-project/vllm v0.32.0rc0 Minorpre

A high-throughput and memory-efficient inference and serving engine for LLMs

04:49
dograh-hq/dograh dograh-v1.49.0 Minor

(2026-10-12)

06:03
OpenHands/OpenHands v1.27.1 Patch

(2026-10-12)

03:33
rtk-ai/rtk v0.52.0 Release +1 more

0.52.0 (2026-10-13)

18:53
ruvnet/ruflo v3.56.9 Patch +1 more

Patch release: `@claude-flow/cli`, `claude-flow`, `ruflo` 3.56.9 (latest, alpha, v3alpha). The bundled leaves `@claude-flow/security` 3.0.5 and `@claude-flow/codex` 3.0.5 were published standalone first, and the CLI pins

05:14
googleapis/python-genai v2.30.0 Minor +1 more

Google Gen AI Python SDK provides an interface for developers to integrate Google's generative models into their Python applications.

08:17
stablyai/orca mobile-android-v0.0.55 Patchpre New agent

Thank you for using Orca mobile! ❤️

08:07
ultralytics/ultralytics v8.4.177 Patch New model +1 more

Ultralytics 8.4.177 makes SAM prompts work consistently across image directories and video frames, alongside fixes that improve export reliability, training resumes, and prediction inputs.**

23:36
modelscope/evalscope v1.13.0 Minor

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

18:27
router-for-me/CLIProxyAPI v8.0.27 Patch

Linux release assets

00:37
multica-ai/multica v0.6.2 Patch

bacc41f848870b165ddf2cdc83ca8ad76377615 MUL-7573 fix(lark): clear the Typing reaction without trusting in-process state (#8656)

18:48
PrimeIntellect-ai/verifiers v0.4.0 Minor

Our library for RL environments + evals

05:24
herdrdev/herdr v0.9.4 Patch

the runtime your coding agents live on

23:41
volcengine/OpenViking [email protected] Sub-package

Adds BatchWriteOptions.skip_conflicts (required by VikingBot Compile finalize) and grep(level_limit).

16:02
Yeachan-Heo/oh-my-claudecode v5.7.1 Patch

oh-my-claudecode v5.7.1: Bug Fixes

10:59
stanfordnlp/dspy 3.4.1 Patch

DSPy 3.4.1 makes GEPA's structured `InstructionProposer` the default instruction proposer and lets `dspy.RLM` build DSPy sub-agents from inside its REPL. It also adds Python 3.15 support, fixes a 3.4.0 import crash, and

07:12
can1357/oh-my-pi v18.10.3 Patch

@oh-my-pi/pi-agent-core

03:23
skypilot-org/skypilot v1.0.0.dev20261013 First releasepre

The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

20:44
onyx-dot-app/onyx helm/onyx-0.9.12 Sub-package +1 more

Onyx application and Craft sandbox deployment chart

01:40
topoteretes/cognee v1.6.4 Patch +1 more

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free

23:29
supermemoryai/supermemory server-v0.0.9 Patch

Added prebuilt Docker images for Linux amd64 and arm64.

02:59
Niko1221/Strata v0.1.43.1 Patch

A hotfix for 0.1.43: Linux NVIDIA decode is fast again on desktops (the adaptive overlap is opt-in again), long prompts no longer stall on Windows and SATA SSDs, two-card batch serving is about 35% faster again, RX 6000

01:30
opendataloader-project/opendataloader-pdf v2.5.13 Patch

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

11:48
langchain-ai/deepagents deepagents-acp==0.0.13 Release

Shell permissions now apply only to the exact commands authorized.

07:00
Infisical/infisical v0.166.5 Patch

Infisical is the open-source platform for securing secrets, certificates, access, and AI Agents.

04:28
docling-project/docling-serve v1.37.0 Minor

Running Docling as an API service

22:10
TencentCloud/TencentDB-Agent-Memory v2.0.3-beta.1 Patch

[2.0.3-beta.1] - 2026-10-13

18:43
jarrodwatts/claude-hud v0.11.2 Patch

A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress

12:58
manaflow-ai/cmux v0.65.1 Release +2 more

ci: run backend migrations gate on every PR again (revert #17415) by @teamleaderleo in https://github.com/manaflow-ai/cmux/pull/17432

07:11
mlflow/mlflow v3.17.1 Patch

MLflow 3.17.1 is a patch release that contains some minor feature enhancements, bug fixes, and documentation updates.

17:33
activepieces/activepieces 0.92.3 Patch

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

02:43
dyad-sh/dyad v1.19.0 Patch

Local, open-source AI app builder for power users v0 / Lovable / Replit / Bolt alternative Star if you like it!

01:57
lexmount/moli v1.1.17 Patch

Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust

04:20
vllm-project/vllm-metal v0.31.0 Minor

vLLM Metal v0.31.0

14:51
NVIDIA/Megatron-LM 26.09-lambda.rc1 Patch +1 more

Ongoing research training transformer models at scale

19:34
Kilo-Org/kilocode v7.8.9 Patchpre New agent +1 more

Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.

08:15
web-infra-dev/midscene v1.15.3 Patch

feat(test): generate Markdown results after each test run by @yuyutaotao in https://github.com/web-infra-dev/midscene/pull/3240

14:59
openai/codex rust-v0.163.0-alpha.9 Patchpre +1 more

Release 0.163.0-alpha.9

23:47
akitaonrails/ai-memory v2.6.6 Patch

Checksums (SHA256)

15:17
altic-dev/FluidVoice v1.6.11 Patch +1 more

FluidVoice v1.6.11

03:34
Arize-ai/phoenix arize-phoenix-sqlean-v0.2.0 Release +1 more

0.2.0 (2026-10-12)

11:17
LMCache/LMCache v0.5.6rc5-cu129 Patch +4 more

CUDA 12.9 wheels for LMCache v0.5.6rc5 on linux/amd64 and linux/arm64.

08:17
google-gemini/gemini-cli v0.65.0-nightly.20261013.g51617c1bc Patchpre

fix(cli): keep loading other extensions when one fails the allowlist check by @jesussamuel-byte in https://github.com/google-gemini/gemini-cli/pull/29720

09:36
wonderwhy-er/DesktopCommanderMCP v0.3.0 Patch

This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities

23:29
cloudflare/computer %40cloudflare%2Fcomputer%400.5.1 Patch

Give your agent a computer

21:44
awslabs/mcp 2026.10.20261012173232 Rolling +1 more

Open source MCP Servers for AWS

19:05
OpenWhispr/openwhispr v1.10.3 Patch

OpenWhispr 1.10.3

00:56
xberg-io/xberg v1.3.9 Patch +2 more

Polyglot document intelligence with a Rust core: extract text, metadata, images, tables, and structured data from 106 formats across 140 file extensions, plus code intelligence…

21:18
MervinPraison/PraisonAI v4.7.14 Patch

PraisonAI — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 li…

18:14
bytedance/flowgram.ai v1.0.16 Patch

FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials that helps developers build AI workflow platforms faster and simpler.

18:03
lobehub/lobehub v0.0.0-nightly.pr20447.34834 Patchpre +2 more

PR Build Information

17:30
leejet/stable-diffusion.cpp master-961-60423ab Rolling +3 more

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

23:25
Zipstack/unstract v0.192.13 Patch

LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

00:20
cloudflare/agents agents%400.28.1 Patch +1 more

Build and deploy AI Agents on Cloudflare

21:28
vllm-project/aibrix v0.8.0 Patch +1 more

Cost-efficient and pluggable Infrastructure components for GenAI inference

13:58
OpenBMB/PilotDeck v2026.10.13-r2 Rolling +1 more

Task-oriented AI Agent productivity platform

19:25
Agenta-AI/agenta v0.122.5 Patch

[feat] Show orbiting activity dots in the run timeline header by @ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/7400

02:31
zhongerxin/iPhone-use v0.3.12 Patch +1 more

让 Codex 通过 USB 操作真实 iPhone：引导安装、App 自动化、实时屏幕与截图回退。

17:43
langroid/langroid 0.69.7 Patch +1 more

What's in 0.69.7

05:56
Tencent/teamai-cli v0.28.0-beta.2 Patchpre New agent

perf: 45% faster init, 31% faster pull, 32% shorter e2e suite by @SaulMoro in https://github.com/Tencent/teamai-cli/pull/1039

21:55
lmnr-ai/lmnr v0.3.1 Patch

feat: opencode format by @olzhik11 in https://github.com/lmnr-ai/lmnr/pull/2534

16:18
UKGovernmentBEIS/inspect_ai 0.3.279 Patch

0.3.279 (2026-10-12)

07:47
QwenLM/qwen-code v0.25.1-nightly.20261012.18f80f5666 Patchpre

fix(managed-agent): connector and broker robustness from the #12692 R2 review by @wenshao in https://github.com/QwenLM/qwen-code/pull/13330

06:25
Comfy-Org/ComfyUI_frontend v1.55.17 Release

Official front-end implementation of ComfyUI

17:28
ROCm/FastFlowLM v1.0.8 Patch New model

This release adds **`minicpm-v-4.7:1b`**, a 1B vision-language model with toggleable thinking and tool calling. It also **opens up the source of the Gemma 4 engine**, so you can build it yourself and swap individual oper

01:36
sgl-project/sglang-omni v0.1.8 Patch

High Performance Serving Runtime For Interactive Super Intelligence System

02:22
wandb/weave v0.53.12 Patch +4 more

fix(weave): preserve complete usage across trace batches by @gtarpenning in https://github.com/wandb/weave/pull/7965

08:39
github/copilot-sdk runtime-1.0.95-0.unstable.r38345923974.g3754b70 Releasepre +3 more

Public unstable runtime 1.0.95-0.unstable.r38345923974.g3754b70

22:26
flashinfer-ai/flashinfer v0.7.2rc3 Patchpre

[release-v0.7.2] fix(tests): count caching-allocator requests in the Cake DSv4 hardening no-allocation checks by @yyihuang in https://github.com/flashinfer-ai/flashinfer/pull/6245

15:53
awslabs/aidlc-workflows v2.11.1-preview.20261012.1 Patchpre

Warning:** Full Suite failed for this source. A Full Suite failure report ends these notes.

08:15
vllm-project/vllm-ascend v0.30.0rc2 Patchpre

There is no code change in this release. It just contains a quick fix for Dockerfile to make the official Docker image build as expected. If you're using v0.30.0rc1 official docker image, please upgrade to v0.30.0rc2 ins

23:24