Data and AI

2,938 projects whose own agent configuration covers data and ai. These are not mods to install — they are how the maintainers of these repositories tell an agent what to do, and what to avoid.

All projects Building agents7,412Backend and APIs3,694Languages3,682Planning3,492Git and workflow3,285Code review2,942Memory and context2,581Research2,499Writing and docs2,458Testing2,454Frontend2,420DevOps and cloud2,410

Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorKiroWindsurf

ProjectStarsConfiguresFilesAlways loaded
multica-ai/andrej-karpathy-skills A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's ob 210,431 Claude Code 1 522 tok
microsoft/vscode code.visualstudio.com Visual Studio Code 190,932 Claude Code, Codex, GitHub Copilot, OpenCode 84 34,527 tok
ollama/ollama ollama.com Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and ot 180,260 Claude Code, Codex, OpenCode 2 112 tok
firecrawl/firecrawl firecrawl.dev The context API to search, scrape, and interact with the web at scale. 🔥 176,982 Claude Code, Codex, OpenCode 2 776 tok
langchain-ai/langchain docs.langchain.com The agent engineering platform. 145,734 Claude Code, Codex, OpenCode 2 8,938 tok
Shubhamsaboo/awesome-llm-apps theunwindai.com 100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source. 136,277 Claude Code 1
microsoft/generative-ai-for-beginners 21 Lessons, Get Started Building with Generative AI 119,230 Claude Code, Codex, OpenCode 2 2,850 tok
JuliusBrussee/caveman docs.caveman.so 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens 103,826 Claude Code, Codex, Gemini CLI, OpenCode 3 9,792 tok
infiniflow/ragflow ragflow.io RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cu 90,107 Claude Code, Codex, GitHub Copilot, OpenCode 4 2,186 tok
modelcontextprotocol/servers modelcontextprotocol.io Model Context Protocol Servers 90,105 Claude Code 1 953 tok
dair-ai/Prompt-Engineering-Guide promptingguide.ai 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engine 78,042 Claude Code 1 135 tok
apache/superset superset.apache.org Apache Superset is a Data Visualization and Data Exploration Platform 74,661 Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode 7 3,630 tok
microsoft/ai-agents-for-beginners aka.ms 18 Lessons to Get Started Building AI Agents 74,010 Claude Code, Codex, OpenCode 8 2,488 tok
BerriAI/litellm docs.litellm.ai The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (o 58,128 Claude Code, Codex, Gemini CLI, OpenCode 3 3,540 tok
anthropics/claude-cookbooks A collection of notebooks/recipes showcasing some fun and effective ways of using Claude. 52,456 Claude Code 2 926 tok
CherryHQ/cherry-studio cherryai.com AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified ac 51,494 Claude Code, Codex, OpenCode 2 4,719 tok
router-for-me/CLIProxyAPI Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex 50,608 Claude Code, Codex, OpenCode 2 1,132 tok
mudler/LocalAI localai.io LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - 48,887 Claude Code, Codex, OpenCode 2 1,951 tok
HKUDS/nanobot nanobot.wiki Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with Web 47,737 Claude Code, Codex, OpenCode 2 1,294 tok
blader/humanizer skills.sh Agent skill that removes signs of AI-generated writing from text 43,612 Claude Code, Codex, OpenCode 1 541 tok
gradio-app/gradio gradio.app Build and share delightful machine learning apps, all in Python. 🌟 Star to support our wo 43,480 Claude Code, Codex, OpenCode 5 821 tok
deepspeedai/DeepSpeed deepspeed.ai DeepSpeed is a deep learning optimization library that makes distributed training and infe 43,065 Claude Code, Codex, OpenCode 2 1,314 tok
Hmbown/CodeWhale codewhale.net Open-source coding agent for your terminal, built in Rust and on a journey of continuous c 40,914 Claude Code, Codex, OpenCode 2 2,871 tok
HKUDS/LightRAG arxiv.org [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation 39,427 Claude Code, Codex, OpenCode 4 5,707 tok
huggingface/diffusers huggingface.co 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in 34,450 Claude Code, Codex, OpenCode 6 10 tok
topoteretes/cognee cognee.ai Cognee is the open-source AI memory platform for agents. Give your AI agents persistent lo 30,501 Claude Code, Codex, OpenCode 9 14,146 tok
tobi/qmd mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking c 29,542 Claude Code 1 1,727 tok
QwenLM/qwen-code qwenlm.github.io An open-source AI coding agent that lives in your terminal. 27,673 Claude Code, Codex, OpenCode 2 3,697 tok
modelcontextprotocol/python-sdk py.sdk.modelcontextprotocol.io The official Python SDK for Model Context Protocol servers and clients 24,211 Claude Code, Codex, OpenCode 4 2,212 tok
facebook/lexical lexical.dev Lexical is an extensible text editor framework that provides excellent reliability, access 23,832 Claude Code, Codex, OpenCode 3 4,620 tok
1Panel-dev/MaxKB maxkb.cn 🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台 22,719 Claude Code 1 2,021 tok
Nagi-ovo/voyager voyager.nagi.fun Enhancement suite for Gemini, AI Studio, Claude & ChatGPT — plus a prompt manager for any 19,953 Claude Code 2
pydantic/pydantic-ai pydantic.dev How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, eve 19,741 Claude Code, Codex, OpenCode 12 3,621 tok
RightNow-AI/openfang openfang.sh Open-source Agent Operating System 18,163 Claude Code, Codex, OpenCode 2 1,448 tok
langbot-app/LangBot langbot.app Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 17,659 Claude Code, Codex, OpenCode 2 1,193 tok
itwanger/toBeBetterJavaer javabetter.cn 一份通俗易懂、风趣幽默的Java学习指南,内容涵盖Java基础、Java并发编程、Java虚拟机、Java企业级开发、Java面试等核心知识点。学Java,就认准二哥的Java进阶 17,579 Claude Code, Codex, OpenCode 15 747 tok
weaviate/weaviate weaviate.io Weaviate is an open-source vector database that stores both objects and vectors, allowing 16,785 Claude Code 2 2,591 tok
img2threejs/img2threejs img2threejs.io Rebuild the object in a reference image as a code-only, procedural, quality-gated, animati 15,318 Claude Code, Codex 1 712 tok
walkinglabs/learn-harness-engineering walkinglabs.github.io Harness engineering beginner tutorial, from 0 to 1 14,851 Claude Code 1 776 tok
NVIDIA/TensorRT-LLM nvidia.github.io TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models 14,556 Claude Code, Codex, OpenCode 42 2,974 tok
567-labs/instructor python.useinstructor.com structured outputs for llms 13,831 Claude Code 1 3,148 tok
Arindam200/awesome-ai-apps dub.sh A collection of projects showcasing RAG, agents, workflows, and other AI use cases 13,751 Claude Code, Codex, GitHub Copilot, OpenCode 4 3,496 tok
Open-LLM-VTuber/Open-LLM-VTuber open-llm-vtuber.github.io Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking f 13,642 Claude Code, GitHub Copilot 2 2,908 tok
XiaomiMiMo/MiMo-Code mimo.xiaomi.com MiMo Code: Where Models and Agents Co-Evolve 12,956 Claude Code, Codex, OpenCode 2 1,172 tok
StarTrail-org/LEANN arxiv.org [MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. En 12,890 Claude Code 1 2,437 tok
The-PR-Agent/pr-agent pr-agent.ai 🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier. 12,869 Claude Code, Codex, OpenCode 2 2,603 tok
axolotl-ai-cloud/axolotl docs.axolotl.ai Go ahead and axolotl questions 12,443 Claude Code, Codex, OpenCode 2 1,680 tok
semantica-agi/semantica getsemantica.ai Graph-Native Infrastructure for Context and Accountable AI Systems 12,115 Claude Code 1
jina-ai/reader jina.ai Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/ 11,955 Claude Code 1 2,542 tok
mrexodia/ida-pro-mcp plugins.hex-rays.com AI-powered reverse engineering assistant that bridges IDA Pro with language models through 11,852 Claude Code 1 1,135 tok