2,618 projects whose own agent configuration covers testing. 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 agents8,369Claude Code6,848Data and AI3,594Git and workflow3,550Backend and APIs3,545Languages3,459Planning3,305Code review2,872DevOps and cloud2,444Writing and docs2,443Memory and context2,373Research2,311
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| potatoqualitee/kbupdate 🛡 KB Viewer, Saver, Installer and Uninstaller | 393 | Claude Code, Codex, GitHub Copilot, OpenCode | 10 | 1,046 tok |
| leeguooooo/claude-code-usage-bar pypi.org Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + cont | 387 | Codex, OpenCode | 1 | 961 tok |
| PowerBeef/Vocello vocello.vercel.app Vocello: a private voice studio for Apple Silicon. Write a script, pick or describe a voic | 387 | Claude Code, Codex | 17 | 4,189 tok |
| receptron/mulmoclaude npmjs.com Nurture your own AI assistant on your own computer. Local-first and MIT: memories, data an | 386 | Claude Code | 17 | 4,768 tok |
| CodSpeedHQ/codspeed codspeed.io CodSpeed is the all-in-one performance testing toolkit. Optimize code performance and catc | 384 | Claude Code, Codex, OpenCode | 2 | 700 tok |
| AlexGladkov/claude-in-mobile MCP server for mobile and desktop automation — Android (via ADB), iOS Simulator (via simct | 381 | Claude Code | 2 | 619 tok |
| tae0y/real-estate-mcp 🏠 Ask Claude about Korean apartment prices — powered by the Ministry of Land, Infrastruct | 379 | Claude Code | 1 | 1,480 tok |
| mrwogu/promptscript getpromptscript.dev Prompt-as-Code for Enterprise AI. Standardize, audit, and deploy instructions across any A | 378 | Claude Code, Codex, GitHub Copilot, OpenCode | 28 | 7,750 tok |
| AnnenkovLabs/girl-agent oss.girl-agent.com An AI girl with human-like behavior: sleep, mood, schedule, memory, relationship stages, a | 376 | Claude Code, Codex, OpenCode | 2 | 1,375 tok |
| nwiizo/tfmcp crates.io 🌍 Terraform Model Context Protocol (MCP) Tool - An experimental CLI tool that enables AI | 372 | Claude Code, Codex, OpenCode | 8 | 673 tok |
| mamertofabian/mcp-everything-search usemcp.com | 367 | Claude Code, Codex, OpenCode | 15 | 3,824 tok |
| yukuku/androidbible alkitab.app Open Source Bible for Android | 366 | Codex, OpenCode | 1 | 3,904 tok |
| hookdeck/hookdeck-cli hookdeck.com CLI for Hookdeck: forward webhooks to localhost (ngrok alternative), manage and query Even | 366 | Claude Code, Codex, OpenCode | 5 | 9,539 tok |
| remorses/tuistory TMUX for agents. let agents control & test terminal user interfaces. Like Playwright & age | 366 | Codex, OpenCode | 1 | 1,946 tok |
| fizzbee-io/fizzbee fizzbee.io Easiest-ever formal methods language! Designed for developers crafting distributed systems | 366 | Claude Code, GitHub Copilot | 7 | 5,657 tok |
| akitaonrails/llm-coding-benchmark Simple benchmark to test the most popular open source and commercial LLMs with automated O | 365 | Claude Code, Codex, OpenCode | 3 | 7,956 tok |
| getsentry/vitest-evals npmjs.com A vitest extension for running evals. | 359 | Claude Code, Codex, OpenCode | 2 | 635 tok |
| benchflow-ai/benchflow benchflow.ai Research infra for creating RL environments, post-training, and evals. | 358 | Claude Code, Codex, OpenCode | 10 | 1,674 tok |
| hi0001234d/nexpath Local-first AI coding workflow for vibe coders, indie hackers, technical founders and prod | 358 | Claude Code | 1 | 298 tok |
| responsibleai/ASSERT responsibleai.github.io Requirement-driven evaluation harness for AI agents and LLM applications. Generate behavio | 357 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode | 6 | 6,087 tok |
| 0xku/kon Kon is a minimal coding agent (and also a highly opinionated one) | 356 | Claude Code, Codex, OpenCode | 3 | 305 tok |
| clay-good/OpenLore Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the h | 355 | Claude Code, Codex, OpenCode | 3 | 9,913 tok |
| zksecurity/zkbugs bugs.zksecurity.xyz Reproduce ZKP vulnerabilities | 351 | Claude Code, Codex, OpenCode | 3 | 997 tok |
| scouzi1966/maclocal-api 'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and | 350 | Claude Code, Codex, OpenCode | 9 | 5,916 tok |
| neohaskell/NeoHaskell neohaskell.org ⏩ NeoHaskell is a dialect of Haskell that is focused on newcomer-friendliness and producti | 348 | Claude Code, Codex, OpenCode | 72 | 5,063 tok |
| mediar-ai/fazm fazm.ai Fazm Desktop for macOS | 347 | Claude Code, Codex, OpenCode | 4 | 12,081 tok |
| my-take-dev/inspired-mino-design-skills Development skills created from materials published on Minodrive's website. | 346 | Codex, OpenCode | 8 | 3,661 tok |
| shenjingnan/xiaozhi-client xiaozhi-client.shenjingnan.com Xiaozhi AI client, currently mainly used for MCP integration | 346 | Claude Code, Codex, GitHub Copilot, OpenCode | 32 | 7,158 tok |
| aminueza/terraform-provider-minio registry.terraform.io Terraform provider for MinIO and S3-compatible storage (R2, B2, Hetzner, Spaces) — buckets | 345 | Codex, OpenCode | 1 | 1,729 tok |
| boringcomputers/nehemiah boringcomputers.com On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser | 345 | Claude Code, Codex | 1 | — |
| guoqingbao/xinfer guoqingbao.github.io Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime. | 344 | Cursor | 3 | — |
| auth0/auth0-cli auth0.github.io Build, manage and test your Auth0 integrations from the command line | 343 | Claude Code, Codex, OpenCode | 2 | 2,182 tok |
| bia-technologies/yaxunit bia-technologies.github.io YAxUnit. An extension for running tests | 342 | Claude Code, Codex, OpenCode | 4 | 2,037 tok |
| morluto/jacobian Composable mathematics tools for agents | 340 | Claude Code, Codex, OpenCode | 11 | 1,518 tok |
| scrypster/muninndb The cognitive database. A new class of data storage. Not a vector store, not a graph DB, n | 335 | Claude Code | 15 | 3,881 tok |
| PageAI-Pro/ralph-loop ralphloop.sh A long-running AI agent loop. Ralph automates software development tasks by iteratively wo | 334 | Claude Code, Codex, OpenCode | 13 | 374 tok |
| tuva-health/tuva-core thetuvaproject.com Main repo including core data model, data marts, data quality tests, and terminology sets. | 333 | Codex, OpenCode | 1 | 4,808 tok |
| buildswithpaul/Frappe_Assistant_Core docs.assistantcore.cloud Infrastructure that connects LLMs to ERPNext. Frappe Assistant Core works with the Model C | 333 | Claude Code, Codex, OpenCode | 2 | 2,570 tok |
| hughjonesd/huxtable hughjonesd.github.io An R package to create styled tables in multiple output formats, with a friendly, modern i | 333 | Codex, OpenCode | 1 | 834 tok |
| cognesy/instructor-php instructorphp.com Unified LLM API, structured data outputs with LLMs, and agent SDK - in PHP | 328 | Codex, OpenCode | 3 | 3,583 tok |
| vercel/next-evals-oss nextjs.org Evals for Next.js up to 15.5.6 to test AI model competency at Next.js | 327 | Claude Code, Codex, OpenCode | 3 | 419 tok |
| DitriXNew/EDT-MCP MCP for 1C:EDT | 323 | Claude Code, GitHub Copilot | 15 | 3,654 tok |
| enuno/unifi-mcp-server An MCP server that leverages official UniFi API | 322 | Claude Code, Codex, Cursor, Gemini CLI, OpenCode | 49 | 15,461 tok |
| simion/termic termic.dev Open-source Conductor.build alternative. Runs the real claude/gemini/codex CLIs in real te | 322 | Claude Code, Codex, OpenCode | 4 | 6,363 tok |
| dedene/zentty zentty.org A native macOS terminal for agent-driven development, built on Ghostty. | 321 | Codex, OpenCode | 1 | 2,156 tok |
| aviatesk/JETLS.jl aviatesk.github.io A new language server for Julia, enabling modern, compiler-powered tooling. | 318 | Claude Code, Codex, OpenCode | 7 | 1,607 tok |
| sleuth-io/sx sleuth-io.github.io Skill sharing made easy | 315 | Claude Code, Codex, OpenCode | 2 | 864 tok |
| phase-rs/phase preview.phase-rs.dev A rules engine and game client — Rust + WASM + React | 313 | Claude Code, Codex, Gemini CLI, OpenCode | 38 | 8,048 tok |
| sgl-project/rbg rolebasedgroup.github.io A workload for deploying LLM inference services on Kubernetes | 312 | Claude Code | 1 | — |
| Trendyol/stove trendyol.github.io Stove: The easiest way of writing e2e/component tests for your back-end app (jvm, go, rust | 311 | Claude Code | 1 | — |