Data and AI

3,706 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 agents7,374Claude Code6,573Backend and APIs3,486Languages3,398Planning3,181Git and workflow3,100Code review2,701Memory and context2,354Testing2,311Research2,292DevOps and cloud2,282Writing and docs2,269

Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro

ProjectStarsConfiguresFilesAlways loaded
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
Martian-Engineering/lossless-claw Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw 4,897 Codex, OpenCode 1 909 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
FlowElement-xinliuyuansu/m_flow flowelement.ai A bio-inspired cognitive memory engine — a new paradigm for Graph RAG. 4,497 Codex, OpenCode 1 1,075 tok
VectifyAI/OpenKB pageindex.ai OpenKB: Open LLM Knowledge Base 4,435 Claude Code, Codex, OpenCode 2 686 tok
gptme/gptme gptme.org Your agent in your terminal, equipped with local tools: writes code, uses the terminal, br 4,410 Codex, OpenCode 1 933 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
walkinglabs/hands-on-modern-rl walkinglabs.github.io 🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alig 4,279 Codex, OpenCode 1 1,305 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
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
inkeep/open-knowledge openknowledge.ai Beautiful, AI-native markdown IDE and LLM wiki 4,039 Codex, OpenCode 1 1,656 tok
evalstate/fast-agent fast-agent.ai Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support 3,911 Codex, OpenCode 1 1,057 tok
steipete/oracle askoracle.sh Ask the oracle when you're stuck. Invoke GPT-5 Pro with a custom context and files. 3,902 Codex, OpenCode 1 1,193 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
modelcontextprotocol/rust-sdk docs.rs The official Rust SDK for the Model Context Protocol 3,886 GitHub Copilot 1 613 tok
liustack/modlens liustack.dev The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only co 3,879 Codex, OpenCode 1 1,760 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
modelcontextprotocol/java-sdk java.sdk.modelcontextprotocol.io The official Java SDK for Model Context Protocol servers and clients. Maintained in collab 3,683 Codex, OpenCode 1 839 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
truera/trulens trulens.org Evaluation and Tracking for LLM Experiments and AI Agents 3,536 Codex, OpenCode 1 2,825 tok
synthetic-sciences/openscience openscience.sh The open-source AI workbench for scientific research 3,493 Claude Code, Codex, OpenCode 2 2,698 tok
spinabot/brigade brigade.spinabot.com Brigade — Your personal intelligence, built enterprise-grade 3,412 Codex, OpenCode 1 3,380 tok
modelscope/evalscope evalscope.readthedocs.io A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evalua 3,373 Codex, GitHub Copilot, OpenCode 2 2,884 tok
omdsh-dev/DSH-better-sidebar An open sidebar foundation supporting third-party extensions to register new sidebar pages 3,361 Codex, OpenCode 1 3,543 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
Dailin521/codex-provider-sync Synchronize Codex session provider metadata across rollout files and SQLite state. 3,319 Codex, OpenCode 1 1,480 tok
taishi-i/awesome-ChatGPT-repositories huggingface.co A curated list of open source GitHub repositories related to ChatGPT, the OpenAI API, and 3,233 Claude Code 1 995 tok
lmnr-ai/lmnr laminar.sh Laminar - open-source observability platform purpose-built for AI agents. YC S24. 3,228 Claude Code 1 2,360 tok
letta-ai/letta-code letta.com Stateful agents that are like people, with memory, identity, and the ability to learn and 3,215 Claude Code, Codex, OpenCode 4 10,973 tok
simonlin1212/TradingAgents-astock arxiv.org A-share multi-agent investment research framework — compatible with A-share data sources ( 3,194 Claude Code 1 3,359 tok
Snailclimb/interview-guide javaguide.cn An open-source AI interview platform built with Spring Boot 4.1, Java 25, Spring AI 2.0, R 3,182 Claude Code, Codex, OpenCode 2 1,653 tok
supermemoryai/apple-mcp x.com Collection of apple-native tools for the model context protocol. 3,131 Claude Code 1 271 tok
blazickjp/arxiv-mcp-server pulsemcp.com A local MCP server for agent literature work. Original-LaTeX section reads, BibTeX from ar 3,108 Claude Code 1 831 tok
Forward-Future/loopy signals.forwardfuture.ai A library of practical AI-agent loops and an installable skill for finding, adapting, and 3,106 Codex, OpenCode 1 2,320 tok
sonos/tract Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference 3,059 Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode 4 893 tok
mitsuhiko/agent-stuff These are commands I use with agents, mostly Claude 3,058 Codex, OpenCode 1 116 tok
off-grid-ai/OGAM getoffgridai.co The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or 3,051 Claude Code, Codex, OpenCode 3 264 tok
microsoft/Generative-AI-for-beginners-dotnet aka.ms Five lessons, learn how to really apply AI to your .NET Applications 3,048 Claude Code, Codex, GitHub Copilot, OpenCode 24 6,616 tok
zcaceres/markdownify-mcp A Model Context Protocol server for converting almost anything to Markdown 2,986 Claude Code 1 43 tok
vercel-labs/opensrc opensrc.sh Fetch source code for npm packages to give AI coding agents deeper context 2,977 Codex, OpenCode 1 822 tok