Testing

2,615 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
TIGER-AI-Lab/ClawBench claw-bench.com Open-source benchmark for browser AI agents on daily tasks. 1,153 Codex, OpenCode 1 1,826 tok
massgen/MassGen docs.massgen.ai 🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autono 1,145 Claude Code, Codex, OpenCode 2 9,136 tok
rdi-berkeley/agents-last-exam agents-last-exam.org Agents' Last Exam 1,145 Codex, OpenCode 1 1,547 tok
EliasOenal/multimon-ng 1,144 GitHub Copilot 5 3,936 tok
wbopan/cui A web UI for Claude Code agents 1,139 Claude Code 1 700 tok
safedep/vet safedep.io Protect against malicious open source packages 🤖 1,122 Claude Code, Codex, OpenCode 3 2,106 tok
raindrop-ai/workshop raindrop.ai Give your coding agent the power to write and run agent evals. 1,115 Codex, OpenCode 1 451 tok
AlexSergey/rockpack alexsergey.github.io Zero-config React with built-in SSR, automated quality gates, and AI-ready project structu 1,103 Claude Code 1 530 tok
Mininglamp-OSS/octo-server 🐙 The Go backend powering OCTO — an open workplace built for humans × AI agents. REST & W 1,101 Claude Code, Codex, OpenCode 7 4,907 tok
MGdaasLab/WHartTest wharttest.mgdaas.com WHartTest is an AI-driven test automation platform that automates the generation and manag 1,084 GitHub Copilot 1 1,629 tok
stackql/stackql stackql.io Query, provision and operate Cloud, SaaS, API and Model Context Protocol (MCP) resources t 1,075 Claude Code, Codex, OpenCode 2 2,592 tok
takahirom/roborazzi takahirom.github.io Make JVM Android integration test visible 🤖📸 1,073 Codex, OpenCode 1 777 tok
rogue-security/rogue qualifire.ai AI Agent Evaluator & Red Team Platform 1,071 Codex, OpenCode 1 1,055 tok
cBioPortal/cbioportal cbioportal.org cBioPortal for Cancer Genomics 1,059 Claude Code, Codex, OpenCode 2 1,028 tok
a16z/jolt jolt.a16zcrypto.com The simplest and most extensible zkVM. Fast and fully open source from a16z crypto and fri 1,059 Claude Code, Codex, OpenCode 11 4,273 tok
beizhu-1209/AIHelms aihelms.cn An enterprise-grade AI resource management platform providing a unified AI gateway and tok 1,029 Claude Code 6 943 tok
scaleway/scaleway-cli cli.scaleway.com Command Line Interface for Scaleway 1,019 Claude Code, Codex, OpenCode 3 1,409 tok
Pantheon-Security/medusa pantheonsecurity.io AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ 1,013 Claude Code 1 2,806 tok
johnhuang316/code-index-mcp A Model Context Protocol (MCP) server that helps large language models index, search, and 1,007 Claude Code, Codex 2 —
CopilotKit/aimock aimock.copilotkit.dev Mock everything your AI app talks to — LLM APIs, MCP, A2A, AG-UI, vector DBs, search. One 997 Claude Code 2 649 tok
janreges/siteone-crawler crawler.siteone.io SiteOne Crawler is a cross-platform website crawler and analyzer for SEO, security, access 987 Claude Code 1 7,724 tok
microsoft/wassette microsoft.github.io Wassette: A security-oriented runtime that runs WebAssembly Components via MCP 972 Claude Code, Codex, GitHub Copilot, OpenCode 9 510 tok
desplega-ai/agent-swarm agent-swarm.dev Your Company Agentic Operating System 966 Claude Code, Codex, OpenCode 8 10,646 tok
QuantGeekDev/mcp-framework mcp-framework.com The Typescript MCP Framework 931 Claude Code 1 2,151 tok
Auties00/Cobalt Standalone unofficial fully-featured Whatsapp Web and Mobile API for Java and Kotlin 926 Claude Code 6 10,056 tok
LvcidPsyche/auto-browser Give your AI agent a real browser — with a human in the loop. Open-source MCP-native brows 914 Codex, OpenCode 1 673 tok
vostride/agent-qa vostride.com Open-source self-improving QA agent for software teams. A test harness with memory. Write 910 Codex, OpenCode 1 1,569 tok
Jakedismo/codegraph-rust 100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB 908 Claude Code, Codex, OpenCode 2 7,563 tok
vinhnx/VTCode vtcode.vinhnx.chatgpt.site VT Code is an open-source Rust terminal coding agent. 895 Codex, GitHub Copilot, OpenCode 2 8,037 tok
s0ld13rr/pentestcode PentestCode - Multi-agent AI penetration testing system with persistent engagement state, 889 Claude Code, Codex, OpenCode 2 11,646 tok
xiaolai/vmark vmark.app An AI friendly markdown editor. 882 Claude Code, Codex, OpenCode 27 3,228 tok
tanem/react-svg npm.im :art: A React component that injects SVG into the DOM. 881 Codex, OpenCode 1 940 tok
kawamataryo/sky-follower-bridge sky-follower-bridge.dev Instantly find and follow the same users from your X(Twitter) follower on Bluesky. 879 Codex, OpenCode 1 91 tok
open-mercato/cezar cezar.run Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI 873 Claude Code, Codex, OpenCode 4 9,998 tok
rtlopez/esp-fc Flight controller software for hobbyist - build your own flight controller. 873 Codex, OpenCode 1 1,072 tok
bastani-inc/atomic bastani.ai The verifiable coding agent runtime. Define your coding agent's process in natural languag 871 Claude Code, Codex, OpenCode 9 7,376 tok
AmElmo/proofshot Give AI coding agents eyes. Records browser sessions, captures screenshots, collects error 870 Claude Code 1 1,221 tok
jamaljsr/polar lightningpolar.com One-click Bitcoin Lightning networks for local app development & testing 861 Claude Code, GitHub Copilot 2 3,710 tok
Purewhiter/mobilegym mobilegym.dev [EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GU 842 Claude Code, Codex, OpenCode 5 6,882 tok
sockudo/sockudo sockudo.io Blazingly fast pusher drop-in replacement written in rust 839 Claude Code, Codex, OpenCode 4 5,564 tok
groq/openbench openbench.dev Provider-agnostic, open-source evaluation infrastructure for language models 831 Claude Code 3 1,099 tok
SpaiR/imgui-java JNI based binding for Dear ImGui 826 Claude Code, Codex, OpenCode 2 3,728 tok
spylang/spy SPy language 824 Claude Code, Codex, OpenCode 2 1,602 tok
hackerai-tech/hackerai hackerai.co Find and fix vulnerabilities by chatting with AI 816 Claude Code, Codex, OpenCode 6 3,604 tok
openclaw/clawpatch clawpatch.ai Review code. Patch bugs. Land PRs. 815 Claude Code, Codex, OpenCode 3 657 tok
AltimateAI/altimate-code altimate.sh Open-source agentic data engineering harness for dbt, SQL, and cloud warehouses. 100+ tool 814 Claude Code, OpenCode 33 —
bosun-ai/swiftide swiftide.rs Fast, streaming indexing, query, and agentic LLM applications in Rust 800 Codex, OpenCode 1 830 tok
getumbrel/umbrel-apps apps.umbrel.com The official app repository of the Umbrel App Store. Submit apps and updates here. Learn h 791 Claude Code, Codex, OpenCode 5 104 tok
kitfunso/hippo-memory hippo-memory.com Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-ter 786 Claude Code, Codex, OpenCode 2 1,147 tok
faiscadev/fakecloud fakecloud.dev Free, open-source AWS emulator. LocalStack alternative: 107 services, 7,657 operations, tr 775 Codex, OpenCode 1 3,973 tok