Testing

1,595 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 agents8,356Claude Code6,837Data and AI3,595Backend and APIs3,545Git and workflow3,545Languages3,458Planning3,300Code review2,870DevOps and cloud2,441Writing and docs2,440Memory and context2,373Research2,311

Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro

ProjectStarsConfiguresFilesAlways loaded
vanillagreencom/kendex kendex.ai Package manager for agents, skills, hooks, and extensions. Author once, install on every h 88 Claude Code, Codex, GitHub Copilot, OpenCode 78 3,231 tok
UncertaintyArchitectureGroup/The-Subprime-Code-Crisis Independent research synthesis on AI-assisted software delivery risk: how local code-gener 88 Codex, OpenCode 1 8,418 tok
autohandai/commander autohand.ai Commander, your AI coding commander centre for all you ai coding cli agents 87 Codex, OpenCode 1 2,227 tok
mmacpherson/tenforty Python library to compute US federal taxes, and state taxes for some states. 87 Claude Code, Codex, OpenCode 5 3,205 tok
vantage-sh/vantage-mcp-server vantage.sh MCP Server to fetch costs and usage data from your Vantage account. 86 Claude Code, Codex, OpenCode 4 1,849 tok
swt-labs/vibe-better-with-claude-code-vbw Vibe Better With Claude Code - You're not an engineer anymore. You're a prompt jockey with 86 Claude Code, Codex, GitHub Copilot, OpenCode 14 4,356 tok
ZenlixAI/hitl-mcp A production-ready, state-persistent MCP server for Human-in-the-Loop (HITL) interaction. 85 Claude Code, Codex 13 —
mortis-cube/mo-code mo-code is an experimental project by mortis implementing Claude Code's core functionality 85 Claude Code, Codex, OpenCode 12 95 tok
Blushyes/reef blushyes.github.io The minimal dev terminal for the AI coding era — AI writes the code, Reef is where you r 84 Claude Code, Codex 6 —
WillEhrendreich/SageFs sagetech.dev Sage Mode for F# development — REPL with solution or project loading, Live Testing for FRE 84 Codex, OpenCode 1 10,112 tok
moorestech/moorestech Animated open world automated factory game 84 Claude Code, Codex, OpenCode 43 4,455 tok
fastxyz/skill-optimizer Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs 82 Claude Code, Codex, Gemini CLI, OpenCode 3 1,762 tok
snyk/snyk-ls snyk.io Language Server used by IDEs as Snyk Backend for Frontends 82 Claude Code, Codex, Cursor, OpenCode 9 1,485 tok
www-zaq-ai/zaq zaq.ai Connect your people, tools and data with your custom AI agents. ZAQ is an open source coll 82 Claude Code, Codex, OpenCode 54 1,729 tok
wingedsheep/argentum-engine magic.wingedsheep.com Magic: The Gathering rules engine + online play platform, in Kotlin 81 Claude Code, Codex, OpenCode 19 4,822 tok
JasonBoy/msw-mcp msw-mcp-docs.vercel.app Cli & MCP server for msw (Mock Service Worker) for AI Agents with dynamic mocking 81 Claude Code, Codex, OpenCode 2 940 tok
G12789/mcp-quickstart Forge a working, testable, publishable MCP server in 30s. TypeScript or Python, with examp 80 Codex, OpenCode 1 714 tok
woocommerce/woocommerce-paypal-payments wordpress.org 80 Claude Code, Codex, OpenCode 15 2,170 tok
cartridge-gg/controller x.cartridge.gg A self custodial embedded account to seamlessly play onchain games 80 Claude Code, Codex, OpenCode 20 2,222 tok
supabase/pg-toolbelt Postgres migrations made easy 80 Claude Code, Codex, OpenCode 3 11 tok
strands-rl/strands-sglang SGLang model provider for Strands Agents. 79 Claude Code, Codex, OpenCode 7 3,637 tok
Aerozb/Postman-cn The latest fully Chinese-translated version of Postman 79 Claude Code, Codex, OpenCode 3 3,002 tok
wham/github-brain An experimental GitHub MCP server with local database. 78 Claude Code, Codex, OpenCode 2 103 tok
nylas/cli cli.nylas.com Nylas CLI is a unified command-line tool for Nylas API authentication, email management (G 78 Claude Code, Codex, OpenCode 21 2,393 tok
maximem-ai/maximem_synap_sdk maximem.ai The memory and context-management layer for production AI agents. 95.6% on LongMemEval, 93 77 Codex, OpenCode 1 337 tok
iammm0/secbot secbot.site AI-powered authorized security testing workspace. Maintained on the release branch (NestJS 76 Claude Code, Codex, OpenCode 2 4,183 tok
smolcars/hunk A GPUI based diff viewer and Codex orchestrator for vibe engineering 76 Claude Code, Codex, OpenCode 8 1,393 tok
objectstack-ai/objectstack objectstack.ai The ontology is the software. One executable business ontology: AI writes it, the runtime 76 Claude Code, Codex, GitHub Copilot, OpenCode 14 19,407 tok
mochow13/keen-code mochow13.github.io A context-aware terminal-based coding agent written in Go. Supports multiple-providers, MC 75 Claude Code, Codex, OpenCode 4 292 tok
agigante80/actual-mcp-server Talk to your self-hosted Actual Budget from any MCP client: a remote HTTP server for Libre 74 Codex, GitHub Copilot, OpenCode 5 4,331 tok
kkollsga/kglite Embedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema 74 Codex, OpenCode 1 13,531 tok
actava-ai/chi-bench actava.ai Χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows 73 Claude Code, Codex, OpenCode 2 5,110 tok
rasinmuhammed/misata misata.studio Declarative synthetic data for Python. State the facts a dataset must hold (monthly revenu 72 Codex, OpenCode 1 1,824 tok
andrianllmm/renux pypi.org A terminal-based bulk file renamer with a TUI 72 Claude Code, Codex, OpenCode 4 247 tok
rerun-io/examples-monorepo Holds all the more complex examples in a single monorepo 72 Claude Code, Codex, OpenCode 2 7,741 tok
WaseemGhanem98/AgentCheck Behavioral testing for AI agents. 72 Codex, OpenCode 1 1,617 tok
scylladb/scylla-cluster-tests Tests for Scylla Clusters 72 Claude Code, Codex, GitHub Copilot, OpenCode 7 9,599 tok
yantrikos/yantrikdb yantrikdb.com Cognitive memory engine for AI agents — temporal decay, contradiction detection, autonomou 71 Claude Code, Codex, OpenCode 2 512 tok
mavka-ai/unit-tests-skills mavka.ai AI agent skills for generating high-quality unit tests — Given-When-Then test cases, JUnit 70 Claude Code, Codex, OpenCode 3 3,127 tok
AlexanderMattTurner/agent-glovebox A minimal-friction secure experience that lets agents do their work. (beta) 68 Claude Code, Codex, GitHub Copilot, OpenCode 43 16,964 tok
tan-yong-sheng/triliumnext-mcp MCP server for TriliumNext Notes 68 Claude Code, Codex, OpenCode 20 11,344 tok
yfge/ai-video-studio AI video production workflow platform for professional short drama teams. Timeline-first, 68 Claude Code, Codex, Gemini CLI, OpenCode 6 1,434 tok
ronikobrosly/RigorLoop A statistically-sound agentic build framework that employs agentic loops to create code ar 67 Claude Code, Codex, OpenCode 2 1,515 tok
vichhka-git/opencode-shannon-plugin AI Penetration Testing Plugin for OpenCode — Autonomous pentesting with 600+ Kali Linux t 67 Codex, OpenCode 1 1,881 tok
GoogleCloudPlatform/evalbench EvalBench is a flexible framework designed to measure the quality of generative AI (GenAI) 67 Codex, OpenCode 1 2,556 tok
seldonframe/seldonframe seldonframe.com Open-source AI front-office factory for agencies serving local businesses: website, bookin 67 Claude Code, Codex, Cursor, OpenCode, Windsurf 22 5,556 tok
NuGuardAI/nuguard nuguard.ai AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests 67 Claude Code, Codex, GitHub Copilot, OpenCode 7 5,030 tok
callstackincubator/skillgym Prove your agent skills work before you ship them. 66 Codex, OpenCode 1 48 tok
ebibibi/ebi-agent-chat-relay One cockpit for all your coding agents: a web console (plus Discord & Teams) to run Claude 66 Claude Code, Codex, GitHub Copilot, Cursor, OpenCode 15 8,545 tok
netlify/axis axis.run Open source tooling and scoring framework to measure how well services work for AI agents. 66 Codex, OpenCode 1 9,543 tok