3,584 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 |
|---|---|---|---|---|
| richardwhiteii/rlm Recursive Language Model patterns for Claude Code — handle massive contexts (10M+ tokens) | 50 | Claude Code | 3 | — |
| mcp360/mTarsier mcp360.ai mTarsier - The Open Source MCP & Skill Manager for Claude, Cursor, VS Code & any AI client | 50 | Claude Code, Codex, OpenCode | 2 | 1,591 tok |
| serithemage/korea-ai-foundation-model-verification A project verifying whether the publicly released models from the five Korean government A | 50 | Claude Code | 9 | 3,321 tok |
| ricardoherediaj/football-rag-intelligence Football RAG system that generates post match analysis text reports and dashboard visualiz | 50 | Claude Code | 1 | 1,673 tok |
| fluyeporlaweb/mcp-x-intelligence X/Twitter research MCP for Claude, Cursor, Windsurf and any MCP-compatible AI agent | 50 | Claude Code | 1 | 148 tok |
| zycaskevin/Vault-Agent-Memory zycaskevin.github.io Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLi | 50 | Codex, OpenCode | 1 | 1,618 tok |
| hoangsonww/AI-RAG-Assistant-Chatbot lumina-david.vercel.app 👨🏻💻 Meet Lumina – my personal AI assistant powered by hybrid RAG with Pinecone vector | 50 | Claude Code, Codex, OpenCode | 14 | 1,788 tok |
| NERVsystems/llm9p LLM exposed as a 9P filesystem | 50 | Claude Code | 1 | 2,810 tok |
| aliou/pi-synthetic Pi provider for Synthetic - open-source models via OpenAI-compatible API | 50 | Claude Code, Codex, OpenCode | 2 | 1,427 tok |
| eighteendreamer/Ai_Test_Agent Yuce Tianjian · AI testing platform: Web version (LLM + browser automation testing, discon | 50 | Claude Code | 1 | — |
| memi-design/memi memoire.cv The design layer for agentic AI — design context, interface checks, and verification for c | 50 | Claude Code, Codex, OpenCode | 2 | 4,485 tok |
| xiaobei930/cc-best xiaobei930.github.io 🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 44 | 49 | Claude Code | 2 | 1,281 tok |
| Square-Q/subconscious-skill subconscious-skill: Biomimetic memory skill for LLM companions. Different from vector RAG | 49 | Claude Code | 3 | — |
| steel-dev/leaderboard leaderboard.steel.dev Open leaderboard for browser agents | 49 | Claude Code, Codex, OpenCode | 3 | 630 tok |
| woai3c/x-code-cli Open-source, model-agnostic coding agent CLI with subagents, skills, MCP, and plugins. | 49 | Codex, OpenCode | 1 | 1,995 tok |
| lainXXX/omniAgent A lightweight large language model intelligent agent (LLM Agent) framework built with Java | 49 | Claude Code | 1 | 3,833 tok |
| Azure-Samples/mcp-container-ts This is a quick start guide that provides the basic building blocks to set up a remote Mod | 49 | GitHub Copilot | 1 | 718 tok |
| glazperle/kimai_mcp A comprehensive Model Context Protocol (MCP) server for Kimai time-tracking integration. P | 49 | Claude Code | 1 | 13,961 tok |
| intel/gpu-ai-skills Agent Skills for running, benchmarking, and profiling Hugging Face models on Intel GPUs — | 49 | Claude Code, Codex, OpenCode | 2 | 2,191 tok |
| petekp/claude-code-setup My forkable Claude Code setup with sync feature | 49 | Claude Code, Codex, OpenCode | 2 | 476 tok |
| voxel51/fiftyone-skills | 48 | Codex, OpenCode | 1 | 3,276 tok |
| Eamonnn101/Chinese-LLM-Wiki A knowledge-base scaffold for LLM Agents that progressively compiles raw materials into a | 48 | Codex, OpenCode | 1 | 1,611 tok |
| kubony/claude-knowledge-graph Convert Markdown notes into an RDF/TTL knowledge graph for semantic search with SPARQL que | 48 | Claude Code | 5 | 1,402 tok |
| kittimasak/thai-token-optimizer A Thai token optimization tool for AI coding agents that keeps commands, code, and technic | 48 | Codex, Gemini CLI, OpenCode | 2 | 812 tok |
| neul-labs/fast-litellm fast-litellm.neullabs.com High-performance Rust acceleration for LiteLLM - providing significant performance improve | 48 | Claude Code | 1 | 1,987 tok |
| godmakereth/vibe-coding-tw 🌏 The Ultimate Vibe Coding Guide - Traditional Chinese Version | Traditional Chinese vers | 48 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 3,661 tok |
| seamus-brady/springdrift springdrift.ai A persistent runtime for long-lived LLM agents | 48 | Claude Code | 1 | 25,304 tok |
| AtomGraph/Web-Algebra pypi.org Suite of generic Linked Data/SPARQL as well as LinkedDataHub-specific MCP tools | 48 | Claude Code, Codex, OpenCode | 3 | 2,073 tok |
| Rootly-AI-Labs/rootly-graphify-importer rootly.com Turn Rootly incidents, alerts, and teams into a queryable knowledge graph. Visualize servi | 48 | Codex, OpenCode | 1 | 4,539 tok |
| agentcommunity/agent-identity-discovery aid.agentcommunity.org Agent Interface Discovery | 48 | Claude Code, Codex, OpenCode | 2 | 3,102 tok |
| npstorey/civic-ai-tools civicaitools.org Open-source platform connecting AI assistants to government open data — MCP server, curate | 48 | Claude Code, Codex, OpenCode | 3 | 2,107 tok |
| Epochal-dev/open-notebook-mcp MCP server for an Open Source implementation of Notebook LM: Open Notebook | 48 | Codex, OpenCode | 1 | 3,133 tok |
| KBThree13/mcp_espn_ff ESPN Fantasy API with LLMs! | 48 | Claude Code | 1 | 812 tok |
| ophydami/MCP-Google-Doc MCP Google Doc | 48 | Claude Code | 1 | 857 tok |
| Arkya-AI/claude-additional-models-mcp arkya.ai Reduce Claude Desktop consumption by 10x - Integrate Google's Gemini or Z.ai's GLM-5 (744B | 47 | Claude Code | 1 | 4,378 tok |
| CarlosVallejoRuiz/slurp Token-budget-aware graph navigation for AI coding agents. Serve exactly the noodles your L | 47 | Claude Code, Codex | 3 | 12,808 tok |
| floomhq/floom floom.dev Build and supervise scheduled AI workers with an open-source runtime, human approvals, run | 47 | Codex, OpenCode | 1 | 808 tok |
| IlyaGulya/gradle-mcp-server A Model Context Protocol (MCP) server to enable AI tools to interact with Gradle projects | 47 | Claude Code | 1 | 183 tok |
| agiletortoise/drafts-mcp-server Model Context Protocol for Drafts | 47 | Claude Code | 1 | 445 tok |
| hyeonsangjeon/Repolis hyeonsangjeon.github.io 🏙️ Public GitHub repos become a walkable 3D town. Traffic shapes the buildings, residents | 47 | Codex, OpenCode | 1 | 9,193 tok |
| xmm/codex-bmad-skills BMAD skills and workflows for OpenAI Codex (App, CLI, Web): intent-based execution, YAML p | 46 | Codex, OpenCode | 1 | 681 tok |
| nickytonline/dev-to-mcp nickyt.co A remote Model Context Protocol (MCP) server for interacting with the dev.to public API wi | 46 | Claude Code, GitHub Copilot, Cursor | 3 | 2,352 tok |
| heavy3-ai/code-audit Heavy3 Code Audit: Agent skill that uses multi-model consensus to review plans, code, and | 46 | Claude Code | 1 | 848 tok |
| ifokeev/telegram-ai-agent Telegram AI Agent: A powerful Python library for creating AI-powered Telegram bots | 46 | Cursor | 1 | 423 tok |
| entropy-data/dataproduct-mcp dataproduct-mcp.com A Model Context Protocol (MCP) server for discovering data products and requesting access | 46 | Claude Code | 1 | 1,237 tok |
| WaseemGhanem98/AgentCheck Behavioral testing for AI agents. | 46 | Codex, OpenCode | 1 | 1,617 tok |
| cafferychen777/ChatSpatial docs.cafferyang.com MCP server for spatial transcriptomics analysis through natural language interfaces. | 45 | Claude Code | 9 | — |
| ailake-io/ai-lakehouse AI-Lake Format: self-contained Parquet + HNSW index — unifying tabular data, embeddings, a | 45 | Claude Code | 1 | 33,745 tok |
| oxbshw/Agent-Span The Web Access Gateway for AI Agents — 52 channels, 92 MCP tools, 9 SDKs, self-healing bac | 45 | Codex, OpenCode | 1 | 700 tok |
| ActiveInferenceInstitute/ActiveInferenceJournal activeinferenceinstitute.github.io Transcripts, metadata, captions, and translations from the Active Inference Institute's vi | 45 | Codex, OpenCode | 1 | 566 tok |