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
cocoindex-io/cocoindex cocoindex.io Incremental engine for long horizon agents 🌟 Star if you like it! 11,492 Claude Code, Codex, OpenCode 5 4,383 tok
Arize-ai/phoenix arize.com AI Observability & Evaluation 11,341 Claude Code, Codex, OpenCode 31 192 tok
skypilot-org/skypilot skypilot.ai The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one 10,564 Claude Code, Codex, OpenCode 2 3,959 tok
microsoft/vscode-copilot-chat code.visualstudio.com Copilot Chat extension for VS Code 9,970 Claude Code, Codex, GitHub Copilot 6 7,048 tok
StarTrail-org/PixelRAG arxiv.org https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel- 9,884 Claude Code 1 371 tok
pycaret/pycaret pycaret.org Open-source, low-code AutoML platform for Python. PyCaret 4.0: sklearn-native engine + Rea 9,834 Claude Code, Codex, OpenCode 9 4,649 tok
oumi-ai/oumi oumi.ai Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM! 9,382 Claude Code, Codex, OpenCode 2 508 tok
modelcontextprotocol/modelcontextprotocol modelcontextprotocol.io Specification and documentation for the Model Context Protocol 9,145 Claude Code, Codex, OpenCode 2 1,064 tok
rikkahub/rikkahub rikka-ai.com RikkaHub is an Android APP that supports for multiple LLM providers. 7,423 Claude Code, Codex, OpenCode 7 997 tok
traceloop/openllmetry traceloop.com Open-source observability for your GenAI or LLM application, based on OpenTelemetry 7,413 Claude Code 1 636 tok
modelcontextprotocol/registry A community driven registry service for Model Context Protocol (MCP) servers. 7,224 Claude Code, GitHub Copilot 2 286 tok
Zipstack/unstract unstract.com LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Work 7,216 Claude Code 3
kyegomez/swarms docs.swarms.world The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai 7,132 Claude Code 1 8,544 tok
NVIDIA-NeMo/Guardrails docs.nvidia.com NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM 7,072 Claude Code, Codex, OpenCode 2 2,415 tok
stagewise-io/stagewise stagewise.io The Open Source Agentic IDE. Create and orchestrate coding agents, show app previews and r 6,803 Claude Code, Codex, OpenCode 11 1,611 tok
xerrors/Yuxi xerrors.github.io A self-hosted multi-tenant knowledge agent platform: unified RAG, knowledge graphs, multi- 6,702 Claude Code, Codex, OpenCode 2 1,920 tok
airweave-ai/airweave airweave.ai Open-source context retrieval layer for AI agents 6,566 Claude Code 1 1,738 tok
kvcache-ai/Mooncake kvcache-ai.github.io Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. 6,500 Claude Code, Codex, OpenCode 5 320 tok
op7418/CodePilot codepilot.sh A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, 6,444 Claude Code, Codex, OpenCode 2 6,636 tok
gepa-ai/gepa gepa-ai.github.io Optimize prompts, code, and more with AI-powered Reflective Optimization 6,423 Claude Code, Codex, OpenCode 3 452 tok
PrefectHQ/marvin marvin.mintlify.app an ambient intelligence library 6,194 Claude Code 1 462 tok
Helicone/helicone helicone.ai 🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and expe 6,133 Claude Code, Codex, Cursor, OpenCode 3 5,269 tok
jacob-bd/gemini-notebook-mcp-cli Programmatic access to Gemini Notebook - via command-line interface (CLI), Model Context P 6,028 Claude Code, Codex, Gemini CLI, OpenCode 3 7,523 tok
ModelEngine-Group/nexent modelengine-group.github.io Nexent is a zero-code platform for auto-generating production-grade AI agents using Harnes 5,850 Claude Code, Codex, OpenCode 4 1,369 tok
areal-project/AReaL areal-ai.io The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible. 5,729 Claude Code, Codex, OpenCode 27 4,509 tok
OpenBMB/UltraRAG ultrarag.github.io A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines 5,681 Claude Code, Codex, OpenCode 2 4,149 tok
lemonade-sdk/lemonade lemonade-server.ai Lemonade helps users discover and run local AI apps by serving optimized LLMs right from t 5,627 Claude Code, Codex, OpenCode 2 4,978 tok
jgraph/drawio-mcp 5,348 Claude Code 1 3,005 tok
Marker-Inc-Korea/AutoRAG marker-inc-korea.github.io AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are usi 5,059 Claude Code, Codex, GitHub Copilot, OpenCode 3 7,798 tok
Kiln-AI/Kiln kiln.tech Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthe 5,046 Claude Code, Codex, OpenCode 10 1,070 tok
pytorch/executorch executorch.ai On-device AI across mobile, embedded and edge for PyTorch 4,991 Claude Code 2
campfirein/byterover-cli docs.byterover.dev ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Ci 4,956 Claude Code, Codex, GitHub Copilot, OpenCode 4 12,162 tok
aipotheosis-labs/aci aci.dev ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic 4,890 Claude Code 1 1,270 tok
homeassistant-ai/ha-mcp homeassistant-ai.github.io The Unofficial and Awesome Home Assistant MCP Server 4,632 Claude Code, Codex, OpenCode 3 2,870 tok
VectifyAI/OpenKB pageindex.ai OpenKB: Open LLM Knowledge Base 4,435 Claude Code, Codex, OpenCode 2 686 tok
crmne/ruby_llm rubyllm.com One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG 4,340 Claude Code, Codex, GitHub Copilot, OpenCode 4 4,341 tok
hao-ai-lab/FastVideo hao-ai-lab.github.io A unified inference and post-training framework for accelerated video generation. 4,332 Claude Code, Codex, OpenCode 19 1,342 tok
algorithmicsuperintelligence/optillm Optimizing inference proxy for LLMs 4,260 Claude Code 1 1,227 tok
jihe520/MathModelAgent mathmodel.top 🤖📐 An Agent and skills designed for mathematical modeling, automatically completing math 4,214 Claude Code 3 1,377 tok
0xNyk/council-of-high-intelligence nyk.dev Structured multi-perspective deliberation for hard decisions. Run full councils, focused t 4,206 Claude Code, Codex 1 626 tok
langroid/langroid langroid.github.io Harness LLMs with Multi-Agent Programming 4,102 Claude Code 1 2,637 tok
thinking-machines-lab/tinker-cookbook Post-training with Tinker 4,097 Claude Code, Codex, OpenCode 2 1,838 tok
claraverse-space/ClaraVerse claraverse.space Claraverse is a opesource privacy focused ecosystem to replace ChatGPT, Claude, N8N, Image 3,895 Claude Code 1 1,106 tok
NVIDIA/Model-Optimizer nvidia.github.io A unified library of SOTA model optimization techniques like quantization, distillation, p 3,749 Claude Code, Codex, OpenCode 2 923 tok
bethington/ghidra-mcp Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headle 3,703 Claude Code, Codex, OpenCode 2 10,062 tok
nextlevelbuilder/goclaw goclaw.sh GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, 3,589 Claude Code, Codex, OpenCode 2 12,319 tok
smallcloudai/refact refact.ai AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, pla 3,540 Claude Code, Codex, OpenCode 2 2,346 tok
synthetic-sciences/openscience openscience.sh The open-source AI workbench for scientific research 3,493 Claude Code, Codex, OpenCode 2 2,698 tok
Mesh-LLM/mesh-llm meshllm.cloud Distributed AI/LLM for the people. Share compute privately or publicly to power your agent 3,358 Claude Code, Codex, GitHub Copilot, OpenCode 32 11,756 tok
Ataraxy-Labs/sem ataraxy-labs.github.io Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 3,334 Claude Code 2