2,355 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 agents8,442Claude Code6,875Git and workflow3,574Backend and APIs3,550Languages3,468Planning3,315Code review2,876Testing2,653DevOps and cloud2,462Writing and docs2,461Memory and context2,373Research2,315
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| multica-ai/andrej-karpathy-skills A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's ob | 229,888 | Claude Code | 1 | 522 tok |
| firecrawl/firecrawl firecrawl.dev Supercharge your AI agents with data from the web and beyond. Building the library for sup | 198,981 | Claude Code, Codex, OpenCode | 2 | 786 tok |
| ollama/ollama ollama.com Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other model | 186,037 | Claude Code, Codex, OpenCode | 2 | 112 tok |
| Shubhamsaboo/awesome-llm-apps theunwindai.com 100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source. | 143,974 | Claude Code | 1 | — |
| microsoft/generative-ai-for-beginners 21 Lessons, Get Started Building with Generative AI | 123,035 | Claude Code, Codex, OpenCode | 2 | 2,850 tok |
| dair-ai/Prompt-Engineering-Guide promptingguide.ai 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engine | 79,853 | Claude Code | 1 | 135 tok |
| microsoft/ai-agents-for-beginners aka.ms 18 Lessons to Get Started Building AI Agents | 79,004 | Claude Code, Codex, GitHub Copilot, OpenCode | 9 | 2,487 tok |
| apache/superset superset.apache.org Apache Superset is a Data Visualization and Data Exploration Platform | 75,425 | Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode | 7 | 3,834 tok |
| code-yeongyu/oh-my-openagent omo.dev OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engine | 70,736 | Claude Code, Codex, OpenCode | 5 | 17,920 tok |
| anthropics/claude-cookbooks A collection of notebooks/recipes showcasing some fun and effective ways of using Claude. | 54,260 | Claude Code | 2 | 985 tok |
| mudler/LocalAI localai.io LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - | 50,218 | Claude Code, Codex, OpenCode | 2 | 2,245 tok |
| gradio-app/gradio gradio.app Build and share delightful machine learning apps, all in Python. 🌟 Star to support our wo | 44,010 | Claude Code, Codex, OpenCode | 5 | 893 tok |
| Hmbown/CodeWhale codewhale.net Open-source agent for the terminal written in Rust. Use any provider or model. Issues & PR | 41,163 | Claude Code, Codex, OpenCode | 2 | 3,295 tok |
| HKUDS/LightRAG arxiv.org [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation | 40,557 | Claude Code, Codex, OpenCode | 4 | 7,651 tok |
| huggingface/diffusers huggingface.co 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in | 34,871 | 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 | 33,094 | Claude Code, Codex, GitHub Copilot, OpenCode | 28 | 30,810 tok |
| tobi/qmd mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking c | 30,907 | Claude Code | 1 | 1,887 tok |
| labring/FastGPT fastgpt.io FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of o | 29,995 | Claude Code, Codex, OpenCode | 16 | 2,380 tok |
| QwenLM/qwen-code qwenlm.github.io An open-source AI coding agent that lives in your terminal. | 29,032 | Claude Code, Codex, OpenCode | 2 | 4,424 tok |
| modelcontextprotocol/python-sdk py.sdk.modelcontextprotocol.io The official Python SDK for Model Context Protocol servers and clients | 24,773 | Claude Code, Codex, OpenCode | 4 | 2,212 tok |
| facebook/lexical lexical.dev Lexical is an extensible text editor framework that provides excellent reliability, access | 23,990 | Claude Code, Codex, OpenCode | 3 | 6,390 tok |
| walkinglabs/learn-harness-engineering walkinglabs.github.io Harness engineering beginner tutorial, from 0 to 1 | 23,320 | Claude Code | 1 | 776 tok |
| 1Panel-dev/MaxKB maxkb.cn 🔥 MaxKB is an open-source platform for building enterprise-grade agents. A powerful and e | 23,115 | Claude Code, Codex, OpenCode | 2 | 2,037 tok |
| Nagi-ovo/voyager voyager.nagi.fun Enhancement suite for Gemini, AI Studio, Claude & ChatGPT — plus a prompt manager for any | 20,516 | Claude Code | 2 | — |
| langbot-app/LangBot space.langbot.app Production-grade platform for building agentic IM bots - Production-grade multi-platform i | 18,745 | Claude Code, Codex, OpenCode | 2 | 2,963 tok |
| RightNow-AI/openfang openfang.sh Open-source Agent Operating System | 18,243 | Claude Code, Codex, OpenCode | 2 | 1,448 tok |
| itwanger/toBeBetterJavaer javabetter.cn An easy-to-understand, witty, and humorous Java learning guide covering core topics includ | 17,826 | Claude Code, Codex, OpenCode | 14 | 1,397 tok |
| weaviate/weaviate weaviate.io Weaviate is an open-source vector database that stores both objects and vectors, allowing | 16,940 | Claude Code | 2 | 1,507 tok |
| Arindam200/awesome-ai-apps studio1hq.com A collection of projects showcasing RAG, agents, workflows, and other AI use cases | 16,722 | Claude Code, Codex, GitHub Copilot, OpenCode | 4 | 3,496 tok |
| NVIDIA/TensorRT-LLM nvidia.github.io TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models | 15,021 | Claude Code, Codex, OpenCode | 46 | 3,656 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 avatar r | 14,603 | Claude Code, GitHub Copilot | 2 | 2,908 tok |
| semantica-agi/semantica getsemantica.ai Graph-Native Infrastructure for Context and Accountable AI Systems | 14,446 | Claude Code | 1 | — |
| 567-labs/instructor python.useinstructor.com structured outputs for llms | 14,098 | Claude Code | 1 | 3,148 tok |
| StarTrail-org/LEANN arxiv.org [MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. En | 13,775 | Claude Code | 1 | 2,437 tok |
| mrexodia/ida-pro-mcp plugins.hex-rays.com AI-powered reverse engineering assistant that bridges IDA Pro with language models through | 13,379 | Claude Code | 1 | 1,135 tok |
| axolotl-ai-cloud/axolotl docs.axolotl.ai Go ahead and axolotl questions | 12,668 | Claude Code, Codex, OpenCode | 2 | 3,197 tok |
| jina-ai/reader jina.ai Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/ | 12,238 | Claude Code | 1 | 2,542 tok |
| cocoindex-io/cocoindex cocoindex.io Incremental engine for long horizon agents 🌟 Star if you like it! | 11,827 | Claude Code, Codex, OpenCode | 5 | 6,373 tok |
| StarTrail-org/PixelRAG arxiv.org https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel- | 10,855 | Claude Code | 1 | 371 tok |
| skypilot-org/skypilot skypilot.ai The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one | 10,799 | Claude Code, Codex, OpenCode | 2 | 3,959 tok |
| microsoft/vscode-copilot-chat code.visualstudio.com Copilot Chat extension for VS Code | 9,940 | Claude Code, Codex, GitHub Copilot | 6 | 7,048 tok |
| pycaret/pycaret pycaret.org Open-source, low-code AutoML platform for Python. PyCaret 4.0: sklearn-native engine + Rea | 9,857 | Claude Code, Codex, OpenCode | 9 | 4,649 tok |
| modelcontextprotocol/modelcontextprotocol modelcontextprotocol.io Specification and documentation for the Model Context Protocol | 9,624 | Claude Code, Codex, OpenCode | 2 | 1,064 tok |
| oumi-ai/oumi oumi.ai Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM! | 9,425 | Claude Code, Codex, OpenCode | 2 | 508 tok |
| rikkahub/rikkahub rikka-ai.com RikkaHub is an Android APP that supports for multiple LLM providers. | 8,666 | Claude Code, Codex, OpenCode | 7 | 1,646 tok |
| xerrors/Yuxi xerrors.github.io A self-hosted multi-tenant knowledge agent platform: unified RAG, knowledge graphs, multi- | 7,613 | Claude Code, Codex, OpenCode | 2 | 2,299 tok |
| traceloop/openllmetry traceloop.com Open-source observability for your GenAI or LLM application, based on OpenTelemetry | 7,523 | Claude Code | 1 | 636 tok |
| NVIDIA-NeMo/Guardrails docs.nvidia.com NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM | 7,439 | Claude Code, Codex, OpenCode | 2 | 2,438 tok |
| Zipstack/unstract unstract.com LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Work | 7,421 | Claude Code | 4 | — |
| gepa-ai/gepa gepa-ai.github.io Optimize prompts, code, and more with AI-powered Reflective Optimization | 7,295 | Claude Code, Codex, OpenCode | 3 | 452 tok |