GitHub Radar
Repositories gaining stars fastest. Every other source measures demand — someone searching, asking, watching. This one measures supply: it already exists and people are starring it, which makes it the earliest signal here and the one most likely to name something before the market has a word for it.
Tracked repos
468
First seen today
17
On territory
32
Sent to frontier
118
| # | Repository | Stars | +7d | Stars / day | Accel | Momentum | Territory | Admitted | Days seen |
|---|---|---|---|---|---|---|---|---|---|
| 1 |
NandhaKishorM/laya
Multilingual, non-autoregressive System 1 decision engine. Typed decisions over 100+ languages in a single forward pass — 33 ms — trained with reinforcement learning against strictly proper scoring…
readme
Python
|
10,978 | – | 3659.3 est | – | 84 | unknown | velocity | 1 |
| 2 |
HEJustinSun/my-girlfriend-jingtian-latex
这是一个 5 x 8 英寸的 XeLaTeX 排版工程。
readme
TeX
|
4,209 | – | 168.4 est | – | 81 | unknown | velocity | 5 |
| 3 |
multica-ai/multica
Make humans and AI agents work as one team — open-source and self-hostable.
Go
|
51,028 | 1,176 | 168.0 | – | 76 | on | territory | 12 |
| 4 |
Albert-Weasker/niubigeo
Open-source AI brand visibility and competitor reports. Official website: https://niubigeo.ai/ | Paid services: AI testing by real people and GEO optimization. Pricing: https://niubigeo.ai/pricing
TypeScript
|
4,717 | – | 262.1 est | – | 71 | 39% | velocity | 1 |
| 5 |
deeplethe/utopia
World's first open-source enterprise world model.
Rust
agent-memorybitemporalgraphragknowledge-baseknowledge-graphllm
|
9,719 | 2,251 | 321.6 | – | 71 | 38% | velocity | 12 |
| 6 |
robbietilton/Compositor
The Photoshop alternative for Mac
Swift
|
4,441 | – | 888.2 est | – | 69 | 33% | velocity | 1 |
| 7 |
openTrinity/mycontext
MyContext is a local-first desktop app for everyday communication and knowledge work
TypeScript
|
5,008 | 700 | 100.0 | – | 69 | on | territory | 12 |
| 8 |
vectorize-io/hindsight
Hindsight: Agent Memory That Learns
Python
agentic-aiagentsai-memorymemory
|
24,746 | 1,111 | 158.7 | – | 69 | 40% | velocity | 12 |
| 9 |
vercel-labs/skills
The open agent skills tool - npx skills
TypeScript
|
32,193 | 558 | 79.7 | – | 68 | on | territory | 12 |
| 10 |
hypit-ai/hypit
Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.
TypeScript
agentic-aiaiai-agentsai-videocompilerdsl
|
12,809 | – | 237.2 est | – | 68 | 28% | velocity | 6 |
| 11 |
kunchenguid/firstmate
Talk to one agent. Ship with a crew.
Shell
|
6,921 | 958 | 136.9 | – | 67 | 40% | velocity | 12 |
| 12 |
mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Python
apple-silicondecision-modelinferencelayalocal-aimachine-learning
|
4,032 | – | 2016.0 est | – | 67 | 27% | velocity | 1 |
| 13 |
google/artemis
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.
Python
ai-agentsandroidgoogletest-automationtesting
|
8,909 | 3,468 | 495.4 | – | 67 | 26% | velocity | 9 |
| 14 |
Human-Agent-Society/reef
Continual learning infra for self-improving agents
Python
agent-infrastructureai-agentscontinual-learninginferencellmllm-training
|
3,941 | – | 187.7 est | – | 67 | 27% | velocity | 3 |
| 15 |
browser-use/jev-ultrafast
Fastest and cheapest web agent
Python
|
16,060 | – | 3212.0 est | – | 67 | 25% | velocity | 3 |
| 16 |
tamaratran/fast-jev-compaction
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
TypeScript
|
6,011 | – | 1502.8 est | – | 67 | 25% | velocity | 2 |
| 17 |
XiaoDuoYa/codex-with-chatgpt
ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
TypeScript
ai-agentschatgptcodexmcpmodel-context-protocoloauth
|
5,814 | 1,510 | 215.7 | – | 67 | 25% | velocity | 12 |
| 18 |
totec448-spec/chat-on-steroids
Cross-platform local MCP capabilities for ChatGPT with Chrome integration, Goal, Compact & Resume, and durable multi-agent workflows.
TypeScript
automationchatgptchrome-extensionelectronlinuxlocal-first
|
3,719 | – | 124.0 est | – | 67 | 41% | velocity | 1 |
| 19 |
dataelement/dsh-desktop
DSHDesktop:DeepSeek Harness Desktop / DeepSeek Harness 桌面版
TypeScript
agentappsdeepseekdeepseek-harnessdeepseek-harness-desktopdesktop
|
8,288 | 1,910 | 272.9 | – | 66 | 22% | velocity | 12 |
| 20 |
trailhq/Graft
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
TypeScript
ai-agentsanthropicclaude-codeclicode-graphcodex
|
8,947 | 1,128 | 161.1 | – | 66 | 29% | velocity | 12 |
| 21 |
Alishahryar1/free-claude-code
Use Claude Code, Codex, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)
Python
|
55,632 | – | 235.7 est | – | 65 | 21% | velocity | 1 |
| 22 |
lidge-jun/opencodex
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
TypeScript
ai-gatewayai-toolsanthropicchatgptclaudeclaude-code
|
15,796 | 1,148 | 164.0 | – | 65 | 28% | velocity | 12 |
| 23 |
bilawalsidhu/gods-eye-view
A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe.
JavaScript
3d-globecesiumflight-trackinggeospatialgeospatial-intelligencegis
|
40,680 | 7,010 | 1001.4 | – | 65 | 21% | velocity | 12 |
| 24 |
herdrdev/herdr
the runtime your coding agents live on
Rust
agentagent-orchestrationaiai-agentsclaude-codecli
|
40,079 | 1,538 | 219.7 | – | 65 | 20% | velocity | 12 |
| 25 |
MiniMax-AI/MiniMax-H3
It ships with two prompt guides under skills/h3-prompt-writing/references/: base-en.txt for text/keyframe modes and ref-en.txt for full-reference (Ref2VA) mode.
readme
Python
|
9,054 | 426 | 60.9 | – | 65 | unknown | velocity | 12 |
| 26 |
miuuyy/codex-chatgpt-web
Use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without using Codex quota.
TypeScript
chatgptchatgpt-procodexfree-aimcpopenai
|
10,345 | 3,256 | 465.1 | – | 65 | 19% | velocity | 12 |
| 27 |
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
JavaScript
agent-skillsai-agentsclaudeclaude-codeclaude-code-plugincursor-rules
|
143,787 | 5,257 | 751.0 | – | 64 | 18% | velocity | 12 |
| 28 |
andrewyng/openworker
AI that gets your everyday tasks done. OpenWorker is an open-source AI coworker that lives on your desktop and delivers finished work, not just chat: your code reviewed for vulnerabilities with fixes…
readme
Python
|
18,109 | 408 | 58.3 | – | 64 | unknown | velocity | 12 |
| 29 |
colbymchenry/codegraph
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
C
|
71,742 | 868 | 124.0 | – | 64 | 33% | velocity | 12 |
| 30 |
ApodexAI/FrontierAgent
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
Python
agent-orchestrationagentic-aiagentic-frameworkai-agentsharnessmulti-agent
|
4,341 | – | 144.7 est | – | 64 | 28% | velocity | 5 |
| 31 |
amagine-ai/Amagine3D
Amagine3D: From hardware requirements to editable 3D designs
Python
|
6,096 | 1,392 | 198.9 | – | 64 | 17% | velocity | 12 |
| 32 |
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Rust
agentic-codingai-codinganthropicclaude-codeclicommand-line-tool
|
81,332 | 929 | 132.7 | – | 64 | 30% | velocity | 12 |
| 33 |
vorssaint/vorssaint-utils
Free and open-source macOS menu bar toolkit.
Swift
alt-tabapp-uninstallerappkitfinderfreekeep-awake
|
20,424 | 1,394 | 199.1 | – | 64 | 16% | velocity | 12 |
| 34 |
asgeirtj/system_prompts_leaks
Extracted system prompts from Anthropic - Claude Fable 5.1, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.
JavaScript
aiai-agentsai-promptsanthropicchatbotchatgpt
|
68,012 | 1,178 | 168.3 | – | 64 | 22% | velocity | 12 |
| 35 |
danny-avila/LibreChat
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
TypeScript
aianthropicartifactsawsazurechatgpt
|
44,585 | 1,036 | 148.0 | – | 63 | 25% | velocity | 8 |
| 36 |
spinabot/brigade
Brigade — Your personal intelligence, built enterprise-grade
TypeScript
agent-runtimeaiai-crewautonomous-agentsbrigadebrigade-agent
|
4,915 | 1,178 | 168.3 | – | 63 | 21% | velocity | 12 |
| 37 |
apify/apify-mcp-server
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 scrapers, crawlers, and automation tools available on the Apify Store.
TypeScript
agentsaimcpmcp-server
|
7,978 | 827 | 118.1 | – | 63 | 32% | velocity | 12 |
| 38 |
deepseek-ai/deepseek-harness
DeepSeek Harness: Everything is a Plugin.
TypeScript
ai-agentscordisdshdsh-plugin
|
232,440 | 8,286 | 1183.7 | – | 63 | 14% | velocity | 12 |
| 39 |
zai-org/ZCode
Z.ai's coding agent harness. Powerful, intelligent, extensible.
TypeScript
|
5,768 | – | 5768.0 est | – | 63 | 14% | velocity | 1 |
| 40 |
Dpro-at/Tel-Agent
AI phone assistant | open-source
Python
agentagent-skillsagentic-aiaigood-first-issuehacktoberfest
|
995 | 531 | 75.9 | – | 63 | 47% | velocity | 12 |
| 41 |
JuliusBrussee/caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Go
aianthropiccavemanclaudeclaude-codellm
|
107,187 | 1,586 | 226.6 | – | 63 | 14% | velocity | 12 |
| 42 |
TencentCloud/Octop
A smarter, self-hosted AI assistant — multi-user, multi-agent.
Python
agentagentic-aiaiai-agentai-agentslocal-first
|
4,520 | – | 60.3 est | – | 63 | on | territory | 4 |
| 43 |
vercel-labs/agent-browser
Browser automation CLI for AI agents
Rust
|
43,006 | 434 | 62.0 | – | 62 | on | territory | 12 |
| 44 |
rakanki911/DLSS5-Swapper
Install, tune and restore DLSS 5 in your games with one click. Native RenoDX, DLSS5-Feeder for games without DLSS, OptiScaler and multipass routes; DirectX 8/9/11/12, Vulkan, OpenGL, DirectDraw and emulators. In-game F8 overlay, automatic backups, and a community page showing what works on your games and your graphics card.
JavaScript
|
6,224 | 1,610 | 230.0 | – | 62 | 10% | velocity | 12 |
| 45 |
stablyai/orca
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
TypeScript
adeagent-ideai-agentsclaude-codeclicodex
|
74,785 | 5,968 | 852.6 | – | 62 | 9% | velocity | 12 |
| 46 |
trycompai/crm
Comp AI CRM is an open source, CRM designed for AI agents. Agentic-first CRM.
TypeScript
|
10,711 | 282 | 40.3 | – | 61 | on | territory | 12 |
| 47 |
ifixai-ai/iFixAi
Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.
Python
agent-evaluationaiai-alignmentai-evaluationai-governanceai-safety
|
15,667 | 1,173 | 167.6 | – | 60 | 11% | velocity | 12 |
| 48 |
lnkiai/m3e-canvas
Sketch Material 3 Expressive screens in the browser and turn them into vibe-coding prompts.
TypeScript
design-toolmaterial-3-expressivematerial-designmaterial3nextjsprompt
|
7,939 | 1,137 | 162.4 | – | 60 | 12% | velocity | 12 |
| 49 |
aipoch/open-science
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
TypeScript
agent-skillsai-agentai-for-scienceai-researchai-research-workbenchai-workbench
|
4,891 | 709 | 101.3 | – | 60 | 28% | velocity | 12 |
| 50 |
agentscope-ai/agentscope
Build and run agents you can see, understand and trust.
Python
agentchatbotlarge-language-modelsllmllm-agentmcp
|
32,133 | 472 | 67.4 | – | 59 | 39% | velocity | 12 |
| 51 |
K-Dense-AI/scientific-agent-skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Python
agent-skillsai-scientistbioinformaticschemoinformaticsclaudeclaude-skills
|
45,962 | 1,022 | 146.0 | – | 59 | 12% | velocity | 12 |
| 52 |
JustVugg/colibri
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
C
|
36,880 | 4,658 | 665.4 | – | 58 | 0% | velocity | 12 |
| 53 |
anywhere-labs/dsh-desktop
为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」,桌面本身也是「插件」。
TypeScript
cordiscordis-plugindeepseekdeepseek-harnessdesktopdsh
|
28,308 | 1,754 | 250.6 | – | 58 | 0% | velocity | 12 |
| 54 |
eternity4719/HowToLiveBetter
按性价比排序的循证生活指南:长寿防病、急救、省钱理财、法律红线、失业与工伤、医保社保、恋爱婚育、怀孕育儿、创业与做平台合规、出国与技能。每条写明成本、收益、证据等级和原始出处,只引期刊论文与官方文件。
HTML
|
11,366 | – | 811.9 est | – | 58 | 0% | velocity | 4 |
| 55 |
abue-ammar/tinycast
Tinycast — a tiny, fully native macOS launcher, hotkeys, and clipboard history.
Swift
|
7,112 | 3,643 | 520.4 | – | 58 | 0% | velocity | 7 |
| 56 |
sdli1995/dlssg_for_sm86
Here is a dlssg for RTX30 Series GPU
|
3,739 | – | 267.1 est | – | 58 | 0% | velocity | 2 |
| 57 |
github/spec-kit
💫 Toolkit to help you get started with Spec-Driven Development
Python
aicopilotdevelopmentengineeringprdspec
|
138,242 | – | 349.1 est | – | 58 | 0% | velocity | 6 |
| 58 |
petergyang/no-ai-slop
Removes 20+ patterns of AI slop from any piece of writing.
Python
|
10,966 | 1,390 | 198.6 | – | 58 | 0% | velocity | 12 |
| 59 |
tw93/Mole
🐹 Clean, uninstall, analyze, optimize, and monitor your Mac. Free open-source CLI, plus a native Mac app.
Shell
analyzerappcleanercleancleanercleanmymaccommand-line
|
68,033 | 858 | 122.6 | – | 58 | 15% | velocity | 12 |
| 60 |
chaitanyagiri/munder-difflin
A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents
TypeScript
agent-orchestrationagentsai-agentsautonomous-agentsclaude-codecodex
|
7,791 | 662 | 94.6 | – | 58 | 24% | velocity | 12 |
| 61 |
pipecat-ai/pipecat
Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
Python
aichatbot-frameworkchatbotsreal-timevoicevoice-assistant
|
15,756 | 214 | 30.6 | – | 58 | on | territory | 12 |
| 62 |
guillaumemeyer/watermarks-remover
A privacy-first app that strips AI watermarks from content you own.
Python
agent-skillaianthropicc2pachatgptclaude
|
22,529 | 499 | 71.3 | – | 57 | 30% | velocity | 12 |
| 63 |
Vincentwei1021/video-shotcraft
AI video skill for Claude Code & Codex — cinematic product videos with Remotion: 152 shot recipe cards, 209 motion previews, a production-ready template
TypeScript
agent-skillsai-agentsai-videoclaude-codeclaude-code-skillsclaude-skills
|
9,189 | 613 | 87.6 | – | 57 | 22% | velocity | 12 |
| 64 |
opendatalab/MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python
ai4sciencedocument-analysisdocxextract-datalayout-analysisocr
|
80,427 | – | 86.0 est | – | 56 | 21% | velocity | 3 |
| 65 |
genspark-ai/genoffice
Free, open-source AI Office suite: Docs, Sheets, Slides, PDF, Markdown and HTML editors with a built-in AI agent, plus a `genoffice` CLI and agent skill so Claude Code, Codex and Cursor can create and edit real .docx/.xlsx/.pptx files locally. Bring your own key. macOS, Windows & Linux.
TypeScript
aiai-agentclaude-codeclicodexcursor
|
7,439 | 662 | 94.6 | – | 56 | 17% | velocity | 12 |
| 66 |
patchy631/ai-engineering-hub
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
Jupyter Notebook
agentsaillmsmachine-learningmcprag
|
37,927 | 384 | 54.9 | – | 55 | 33% | velocity | 12 |
| 67 |
infiniflow/ragflow
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
Go
agent-harnessagentic-aiagentic-nagiveagentic-retrievalagentic-searchai
|
91,119 | 422 | 60.3 | – | 55 | 30% | velocity | 12 |
| 68 |
truefoundry/trueforge
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
TypeScript
agentagentic-aiagentsharnessharness-engineering
|
5,885 | 284 | 40.6 | – | 55 | 42% | velocity | 12 |
| 69 |
experientiallabs/experiential
Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.
Python
|
5,399 | 537 | 76.7 | – | 54 | 19% | velocity | 12 |
| 70 |
wang2122/sprix-sage-router
Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks.
Python
a2aagent-orchestrationagent-routingai-agentsmulti-agent-systemspython
|
4,007 | 318 | 45.4 | – | 54 | 36% | velocity | 12 |
| 71 |
latent-spaces/brag
You built it. Now brag. Turn the project you just created into a short, shareable launch video with one command.
Python
|
6,602 | – | 68.1 est | – | 54 | 21% | velocity | 3 |
| 72 |
xzf-thu/VoiceMem
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
Python
aiai-agentsai-toolsapplicationaudio-streaminggenai
|
2,109 | 460 | 65.7 | – | 54 | 22% | velocity | 12 |
| 73 |
jakubkrehel/skills
A collection of agent skills that help you build great interfaces.
Markdown
|
6,983 | 373 | 53.3 | – | 53 | 29% | velocity | 12 |
| 74 |
yc-software/qm
Multiplayer agent harness for work.
TypeScript
aiassistantharnessqm
|
15,195 | 193 | 27.6 | – | 53 | on | territory | 12 |
| 75 |
img2threejs/img2threejs
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
Python
3dai-agentsclaude-codecomputer-graphicsgenerativeimage-to-3d
|
16,539 | 508 | 72.6 | – | 53 | 17% | velocity | 12 |
| 76 |
repowise-dev/repowise
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Python
aicode-complexitycode-healthcode-intelligencecode-qualitydead-code
|
6,846 | 412 | 58.9 | – | 53 | 23% | velocity | 12 |
| 77 |
CopilotKit/OpenBot
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
TypeScript
ag-uiagent-governanceai-agentsbrowser-automationcopilotkitgenerative-ui
|
5,285 | 391 | 55.9 | – | 53 | 25% | velocity | 12 |
| 78 |
Waishnav/devspace
Minimal Coding Agent Harness on MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw
TypeScript
agent-orchestrationchatgptclaudeclaude-codecodexdyanmic-workflow
|
5,056 | 317 | 45.3 | – | 52 | 29% | velocity | 12 |
| 79 |
tech-leads-club/agent-skills
The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.
TypeScript
agentaiantigravityclaude-codecopilotcursor
|
6,605 | 516 | 73.7 | – | 52 | 12% | velocity | 12 |
| 80 |
earthtojake/text-to-cad
A library of agent skills for CAD, CAE and CAM
Python
agentsai-agentscadmechanical-engineeringroboticsstep
|
16,236 | 447 | 63.9 | – | 51 | 15% | velocity | 12 |
| 81 |
crmne/spotifast
Spotify, native and fast. One lightweight Rust app for your whole library, local playback, and Spotify Connect on Linux, macOS, and Windows.
Rust
audiocross-platformdesktop-appeguiguilibrespot
|
4,501 | 435 | 62.1 | – | 51 | 15% | velocity | 12 |
| 82 |
FlashML-org/FreeToken
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
Python
deepseek-v4edgeglminferenceminimaxmoe
|
13,481 | 671 | 95.9 | – | 50 | 0% | velocity | 12 |
| 83 |
TencentCloud/TencentDB-Agent-Memory
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
TypeScript
agentai-agentembeddingllmlocal-firstlong-term-memory
|
27,110 | 422 | 60.3 | – | 50 | 15% | velocity | 12 |
| 84 |
openai/openai-agents-python
A lightweight, powerful framework for multi-agent workflows
Python
agentsaiframeworkharnessllmopenai
|
29,623 | 189 | 27.0 | – | 50 | 40% | – | 12 |
| 85 |
modelscope/ms-cookbook
魔搭紫皮书|ModelScope Cookbook:面向开发者的开源模型应用实战指南,覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC,从跑通第一个模型到构建实际应用。
HTML
ai-agentscookbookdiffusion-modelsfine-tuninggenerative-aillm
|
381 | – | 38.1 est | – | 50 | 29% | – | 5 |
| 86 |
baidu/Unlimited-OCR
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
Python
|
25,997 | 345 | 49.3 | – | 50 | 20% | velocity | 12 |
| 87 |
kirodotdev/KiroCrew
A persistent workspace for development work that self-improves and continues beyond one session.
Python
agentagentic-aiagentsai-agentai-agentsautomation
|
4,075 | 162 | 23.1 | – | 49 | 44% | – | 12 |
| 88 |
anbeime/skill
收录最全、更新最快的技能Skills商店:精选原创技能包(涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流),全部打包好可直接安装使用!同时自动抓取GitHub上万个Skills项目,按分类、更新时间、Star数量整理。The most comprehensive and frequently updated AI Agent skill library, featuring curated skill packs across document processing, content creation, programming, machine learning, automated workflows, and many more domains.
Python
agent-skillsclaude-skillscodexdeepseekdeepseek-harnessdeveloper-tools
|
7,064 | 363 | 51.9 | – | 49 | 17% | velocity | 12 |
| 89 |
yetone/cumora
Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.
TypeScript
|
3,835 | 236 | 33.7 | – | 49 | 31% | – | 12 |
| 90 |
butterbase-ai/butterbase
Open-source backend-as-a-service. Postgres, auth, storage, functions, AI gateway, MCP.
TypeScript
baasbackend-as-a-servicemcpopen-sourcepostgressupabase-alternative
|
3,645 | – | 29.4 est | – | 49 | 36% | – | 1 |
| 91 |
livekit/agents
A framework for building realtime voice AI agents 🤖🎙️📹
Python
agentsaiopenaireal-timevideovoice
|
14,302 | 107 | 15.3 | – | 49 | on | territory | 12 |
| 92 |
vectorize-io/self-driving-agents
179 ready-to-use, self-learning AI agents organized into 13 departments. Powered by Hindsight.
readme
TypeScript
|
3,046 | – | 20.9 est | – | 49 | unknown | – | 1 |
| 93 |
hydra-db/hydradb
HydraDB - fast graph database on object storage
Rust
|
3,898 | – | 48.7 est | – | 49 | 17% | velocity | 1 |
| 94 |
Osmantic/ODS
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
Python
ai-agentsamdcomfyuidockerllama-cppllm
|
6,687 | 177 | 25.3 | – | 48 | 38% | – | 12 |
| 95 |
ashemag/human-atlas
Open-source 3D anatomy explorer: 2,234 selectable BodyParts3D meshes, system layers, search, and exploded views.
TypeScript
|
3,740 | 292 | 41.7 | – | 48 | 21% | velocity | 7 |
| 96 |
dsh-market/dsh-market
The plugin market inside DeepSeek Harness — browse, search, one-click install · DSH 可视化插件市场
TypeScript
deepseek-harnessdsh-pluginmarketplace
|
4,333 | 426 | 60.9 | – | 48 | 8% | velocity | 12 |
| 97 |
Tencent/AI-Infra-Guard
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
Python
agentagent-securityagentic-aiai-infraai-red-teamingai-safety
|
6,537 | 262 | 37.4 | – | 48 | 24% | – | 12 |
| 98 |
Zeejay0/gathered-scenes-zine-skill
欢迎访问 zine AI 充值卡网(已上线 Plus 代充、Pro 5x、20x 等等):
readme
Python
|
5,150 | 140 | 20.0 | – | 48 | unknown | – | 12 |
| 99 |
ZeroGold/call-coach-ai
Jev powered call coach
HTML
|
35 | – | 35.0 est | – | 48 | 25% | – | 1 |
| 100 |
magnitudedev/magnitude
Open source inference engine optimized for consumer hardware. Profiles your machine, recommends the best models for it, then downloads, tunes, and runs them. Works on Apple Silicon, NVIDIA, AMD, or nothing but a CPU.
TypeScript
|
4,773 | 266 | 38.0 | – | 47 | 21% | – | 12 |
Stars / day is measured over the last seven observed days; est marks a repo seen for less than a week, where the number is its lifetime average instead.
Accel is this week's rate divided by the previous week's — 2.0× means it doubled.
Admitted repos become discovery-frontier items: territory when the description matches the seed vocabulary, velocity when it is growing fast enough to matter regardless of what it calls itself.