45,030 repositories keep their own agent configuration in the open: a CLAUDE.md, a rules file, instructions for Copilot, a skill the project runs on itself. These are not mods to install. They are worth reading for what they reveal — what a maintainer thinks an agent gets wrong.
Building agents8,564Claude Code6,906Git and workflow3,633Data and AI3,578Backend and APIs3,558Languages3,494Planning3,322Code review2,906Testing2,695DevOps and cloud2,496Writing and docs2,489Memory and context2,375Research2,320Frontend2,312Security2,181Project management1,980
All Claude Code32,552 Codex24,920 OpenCode23,840 GitHub Copilot3,723 Gemini CLI2,039 Cursor1,771 Windsurf202 Kiro117
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| DataJourneyHQ/MCP datajourneyhq.github.io DJHQ smarty pants | 5 | Codex, OpenCode | 1 | 503 tok |
| selfradiance/agentgate Collateralized execution engine for AI agents: bond-and-slash accountability with Ed25519 | 5 | Codex, OpenCode | 1 | 1,113 tok |
| reza-ebrahimi/machinestate MachineState - A single-binary Linux system state reporter with real-time JSONL streaming | 5 | Claude Code | 1 | 3,693 tok |
| sandraschi/ai-producer-hub MCP server integrating AI-powered music generation with professional production tools | 5 | Codex, Cursor, OpenCode | 2 | 392 tok |
| suisya-systems/claude-org-ja A Japanese-first multi-agent operations framework for Claude Code. Secretaries, dispatcher | 5 | Claude Code | 29 | 7,758 tok |
| pgalilea/memx Lightweight and extensible memory layer for LLMs | 5 | Codex, OpenCode | 1 | 67 tok |
| btn0s/redline npmjs.com Review mode for LLM-generated plans — Google Docs-style commenting on any .md file | 5 | Claude Code | 1 | 1,754 tok |
| RobinOppenstam/sema-evals robinoppenstam.github.io Open, causal evaluations for content-addressed semantics and multi-agent coordination. | 5 | Codex, OpenCode | 1 | 286 tok |
| Kerim-Sabic/elite-engineer The operating system for AI-assisted software engineering in TypeScript, React & Next.js. | 5 | Cursor | 1 | 2,899 tok |
| Lordymine/codegraph Token-efficient code knowledge graph for AI coding agents — type-checker-accurate call gra | 5 | Claude Code | 1 | 2,284 tok |
| chiruu12/Hive Local-first agent OS. Spawn persistent AI agents that collaborate, write code, and use too | 5 | Claude Code | 1 | 2,312 tok |
| wlvh/coding-workflow Bilingual agent workflow contracts, PR review templates, and sync automation for AI-assist | 5 | Codex, OpenCode | 1 | 320 tok |
| hiddenway/kovalsky hiddenway.github.io Kovalsky 🚀 Run an AI team with a single prompt. Kovalsky is an open-source platform for | 5 | Codex, OpenCode | 1 | 1,839 tok |
| ddx-510/Morpho A morphogenetic multi-agent framework where AI agents self-organize like biological cells. | 5 | Claude Code | 1 | 1,044 tok |
| getdeeptracer/deeptracer-js deeptracer.dev AI agent for log monitoring | 5 | Claude Code | 1 | 1,128 tok |
| statico/quickrag 🔍🤖 A fast and flexible RAG tool for indexing and querying documents | 5 | Claude Code, Codex, OpenCode | 2 | 636 tok |
| joshuamartyn/next-payload-ai-fluent-starter virtualnative.com AI-fluent full-stack starter with Next.js, Payload CMS, and TypeScript. Built for develope | 5 | Claude Code, Codex, OpenCode | 2 | 2,729 tok |
| GetPullRequest/Sia getpullrequest.com :star2: Your AI dev assistant who works on your behalf while you are offline. It gets your | 5 | Codex, Kiro, OpenCode | 5 | 3,397 tok |
| sikkrasmus/company-index-framework An open framework for an LLM-maintained knowledge base for GTM and RevOps teams. Schema, r | 5 | Claude Code | 1 | 1,902 tok |
| djblack1209-coder/OpenClaw-Bot OpenEverything — Personal AI automation with Telegram, a Tauri console, and traceable mode | 5 | Codex, OpenCode | 1 | 978 tok |
| sattyamjjain/proofloop Universal quality evaluation plugin for Claude Code — 7-dimension scoring (correctness, co | 5 | Claude Code | 1 | 4,440 tok |
| inbharatai/agent-arcade-gateway Agent cockpit for observing, debugging, and controlling AI agent runs across frameworks, w | 5 | Claude Code | 1 | 409 tok |
| nitinmms/LitosAiCodingAgent Litos is a real AI coding agent written entirely in C#/.NET, no black box. | 5 | Claude Code | 1 | 884 tok |
| shaahink/conductor payesh.vercel.app An orchestrator that runs coding agents unattended — and never believes them. Event-source | 5 | Claude Code, Codex, OpenCode | 3 | 7,172 tok |
| mark-weeks/hello-nested-worlds-adventure enfolded.world Enfolded: Nested World Adventure — a shared persistent multiverse where humans and AI agen | 5 | Claude Code, Codex, OpenCode | 7 | 4,715 tok |
| stroland02/Sync Self-maintaining API integrations — watches the third-party APIs your code calls and opens | 5 | Claude Code, Codex, OpenCode | 22 | 8,533 tok |
| snapsynapse/guidecheck guidecheck.org AI setup guides can hide instructions a model reads but a human never sees. GuideCheck is | 5 | Claude Code | 1 | 2,960 tok |
| aleksandr-voitenko/agentic-lore-coding Agentic Lore Coding is a Git-native structured agent workflow (and protocol) for AI-assist | 5 | Claude Code, Codex, OpenCode | 2 | 1,439 tok |
| anshulixyz/multi-agent-loop-kit An agent-native setup kit for turning a well-scoped repo into a supervised multi-agent cod | 5 | Codex, OpenCode | 1 | 1,558 tok |
| LamantinAI/mayak A FastAPI backend template for services that are built and maintained by coding agents | 5 | Claude Code, Codex, OpenCode | 4 | 2,286 tok |
| incidentfox/box Box — self-hosted Claude Code in your pocket. Run real Claude Code & Codex sessions on you | 5 | Claude Code, Codex, OpenCode | 2 | 2,102 tok |
| 2389-research/ceo-personal-os 2389-research.github.io Personal operating system for executives - reflection frameworks, goal systems, coaching-s | 5 | Claude Code | 1 | 1,642 tok |
| ivanviragine/wade Every Wade does the dirty work so the heroes don't have to. Branches, worktrees, context, | 5 | Codex, OpenCode | 1 | 4,008 tok |
| accd/verchestra accd.github.io Verified, portable AI software-delivery harness with policy gates, read-only data probes, | 5 | Claude Code, Codex, Gemini CLI, OpenCode | 3 | 1,151 tok |
| cliffano/tech-team-agents Famous Tech Teams as AI Agent Personas - Actually useful - Definitely opinionated | 5 | Claude Code | 1 | 8,226 tok |
| shashikirandevadiga/apply-pilot AI-powered job application automation system that transforms job descriptions into tailore | 5 | Claude Code | 11 | 1,771 tok |
| feldera/feldera-demos feldera.com Demos showing how to build with Feldera | 5 | Claude Code | 11 | 822 tok |
| Amal-David/mlx-porting-skill mlx-porter.pages.dev MLX Porting Toolkit — an agent-guided, evidence-gated pipeline (scaffold → convert → parit | 5 | Claude Code, Codex, OpenCode | 2 | 1,258 tok |
| peter-olom/manor Local agent harness and Docker environment. Butler keeps Codex work supervised. | 5 | Codex, OpenCode | 1 | 1,560 tok |
| djbelieny/nova mynova.space An AI team that asks before it acts — 24 specialist agents, task decomposition, and human | 5 | Claude Code | 70 | 4,199 tok |
| shyamsridhar123/sharkbait AI-powered coding assistant for the command line. Uses OpenAI Responses API (not Chat). A | 5 | Claude Code, Codex, GitHub Copilot, OpenCode | 4 | 3,228 tok |
| error505/Flockion_AI_Engineering flockion.com Build less. Delete more. Keep the code boring. | 5 | Claude Code, Codex, GitHub Copilot, Kiro, OpenCode | 4 | 2,176 tok |
| Chasen-Liao/FinTrack An AI-based stock news analysis system that correlates news with stock price trends to sup | 5 | Claude Code, Codex, OpenCode | 2 | 1,230 tok |
| felipefernandes/iara pypi.org 🧜♀️Iara is an automated, project-agnostic, and configurable code review tool designed to | 5 | Claude Code, Codex, OpenCode | 5 | 286 tok |
| gitpcl/openorchestrator open-orchestrator.com Git worktree + AI agent orchestration for parallel development workflows | 5 | Claude Code | 6 | — |
| brandonkindred/Khala-Agentic-AI-Teams Many Agents, one objective... yours | 5 | Claude Code | 1 | 3,338 tok |
| mbanderas/maestro marklaursen.com Achieve Frontier AI performance in your CLI — fuse the local model CLIs you already run. F | 5 | Claude Code, Codex, Cursor, Gemini CLI, OpenCode | 5 | 5,441 tok |
| 48Nauts-Operator/xNaut xnaut.dev Native AI terminal for working with a fleet of coding agents. Run any agent (Claude Code, | 5 | Claude Code | 1 | 6,970 tok |
| bharat3645/The-Ideal-Harness Agent harness / control-plane around a stateless LLM: deterministic policy floor on PreToo | 5 | Claude Code, Codex, OpenCode | 10 | 5,796 tok |
| orkiaHQ/orkia orkia.dev An agentic shell that runs AI coding agents (Claude Code, Codex, Gemini) as governed, audi | 5 | Claude Code, Codex | 2 | 1,865 tok |