Coding agents & developer tools

Testing & QA agents

Testing and QA agents write and run tests, drive real browsers or devices, and report failures back to developers or other agents. Keploy spins up isolated sandboxes for API and end-to-end checks, while artemis converts natural-language instructions into Android automation that captures logs as it runs.

988 agents · most starred first

Top 100 of 988

keploy★ 19,890

Open-source platform for creating safe, isolated production sandboxes for API, integration, and E2E testing.

artemis★ 17,811

ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.

midscene★ 15,026

GUI Agent for E2E Testing

supertest★ 14,413

🕷 Super-agent driven library for testing node.js HTTP servers using a fluent API. Maintained for @forwardemail, @ladjs, @spamscanner, @breejs, @cabinjs, and @lassjs.

pest★ 11,781

The elegant testing framework for PHP developers and AI agents.

shortest★ 5,705

QA via natural language AI tests

expect★ 3,562

Expect tests your agent's code in a real browser

cli★ 3,458

QA Wolf from anywhere — your terminal, your CI, your AI agent.

playwright-skill★ 3,307

General-purpose Playwright automation for coding agents

conftest★ 3,288

Write tests against structured configuration data using the Open Policy Agent Rego query language

shrt★ 3,072

A contract-driven gRPC regression harness for AI coding agents, with human-approved baselines. Snapshot the valid call chains of an API so an agent can look one up instead of tracing for it. gRPC today, OpenAPI next

vibium★ 2,935

The verification layer for coding agents

tdd-guard★ 2,384

Automated TDD enforcement for Claude Code

testkube★ 1,682

☸️ The Testing Platform for the agentic SDLC

qa-agent★ 1,335

The open-source Playwright library for AI browser regression testing with intelligent caching, auto-healing, and multi-model verification.

passmark★ 1,273

The open-source Playwright library for AI browser regression testing with intelligent caching, auto-healing, and multi-model verification.

web-eval-agent★ 1,231

An MCP server that autonomously evaluates web applications.

testzeus-hercules★ 1,227

Hercules is the world’s first open-source testing agent, enabling UI, API, Security, Accessibility, and Visual validations – all without code or maintenance. Automate testing effortlessly and let Hercules handle the heavy lifting! ⚡

testsigma★ 1,202

Testsigma is an agentic test automation platform powered by AI-coworkers that work alongside QA teams to simplify testing, accelerate releases and improve quality across web, mobile, desktop, API, and applications like Salesforce and SAP.

alumnium★ 990

End-to-End Testing with AI for Agents and Engineers

dev-proxy★ 848

Simulate API failures, throttling, and chaos — all from your command line.

proofshot★ 840

Give AI coding agents eyes. Records browser sessions, captures screenshots, collects errors, and bundles proof artifacts — so humans can verify what the agent built.

agent-qa★ 819

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

ClaudeCodeAgents★ 782

A set of useful QA agents for Claude Code.

openai-testing-agent-demo★ 770

Demo of a UI testing agent using the OpenAI CUA model and the Responses API.

old-coder★ 760

An old coder's strategy for the agent era: don't read the code — make it run the gauntlet. Evidence-first development skill for coding agents, inspired by Uncle Bob.

Test-Agent★ 726

Agent that empowers software testing with LLMs; industrial-first in China

arbigent★ 658

AI Agent for testing Android, iOS, and Web apps. Get Started in 5 Minutes. Arbigent's intuitive UI and powerful code interface make it accessible to everyone, while its scenario breakdown feature ensures scalability for even the most complex tasks.

agentic-qe★ 534

Agentic QE Fleet is an open-source AI-powered QA/QE platform designed for use with Coding Agents (works best with Claude Code) featuring specialized agents and skills to support testing activities for a product at any stage of the SDLC. Free to use, fork, build, and contribute. Based on the Agentic QE Framework created by Dragan Spiridonov.

Specula★ 498

Specula: An agentic tool for finding deep bugs in system code using TLA+

mobilewright★ 483

Mobilewright is a dev framework for Mobile App Testing and Automation. It allows testing iOS/Android app on real devices, emulators and simulators with a single API.

Swift-Testing-Agent-Skill★ 482

An agent skill focused entirely on Swift Testing, helping you write better tests, migrate from XCTest, improve test architecture, and adopt modern Swift testing patterns with confidence.

agent-spec★ 464

`agent-spec` is an AI-native BDD/spec verification tool for task execution.

reticle★ 449

AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web & desktop applications.

flutter-skill★ 410

AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.

specmatic★ 401

Shift-left API Integration | Auto-fix integration drift before integration. Specmatic turns API specifications into executable contracts, continuously verifying that every change made by AI coding agents and engineers stays true to the desired behaviour. Ship AI-ready APIs 10x faster, from intent to implementation, with Spec-Driven API Development.

crab★ 399

CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.

agent-skills★ 392

AI agent skills for TestMu AI (Formerly LambdaTest).

tuistory★ 370

TMUX for agents. let agents control & test terminal user interfaces. Like Playwright & agent-browser but for TUIs

harness★ 365

AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain language; an LLM agent drives the UI and reports friction. macOS 14+, Swift 6.

testdriverai★ 345

Computer-Use SDK for E2E QA Testing

funzzy★ 331

Gives developers and coding agents one reliable edit loop

squirrelscan★ 320

The website QA tool for your coding agent. 350+ audit rules across SEO, performance, security, accessibility and agent experience.

awesome-qa-skills★ 313

Bilingual Agent Skills for software testing and QA workflows from requirements through release. Independently installable for Codex, Claude Code, Cursor, and compatible coding agents. Licensed under PolyForm Noncommercial 1.0.0.

finalrun-agent★ 311

AI QA Agent for mobile apps

debug-gym★ 309

A Text-Based Environment for Interactive Debugging

kaizen★ 306

Automate the tedious development tasks with AI

mutahunter★ 305

Open Source, Language Agnostic Mutation Testing

AUITestAgent★ 303

AUITestAgent is the first automatic, natural language-driven GUI testing tool for mobile apps, capable of fully automating the entire process of GUI interaction and function verification.

agentic-playwright★ 302

Production-grade Playwright + TypeScript Scaffold for Agentic Testing. Harness for all major AI coding agents baked in.

hulken★ 292

Hulken is a stress testing tool for everything speaking HTTP. Hulken supports multiple urls, GETs and POSTs, static and dynamic payloads, multiple agents and more. Hulken is highly configurable but defaults to some reasonable settings. Hulken works both as a library and a stand-alone command line tool. Hulken is swedish for The Hulk.

qa-skills★ 291

50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.

FlowTest★ 275

GenAI powered OpenSource IDE for API first workflows

AI-TDD★ 274

CLI for TDD — you write the test, GPT writes the code to pass it ✅

finalrun-agent★ 272

AI QA Agent for mobile apps

test-automation-skills-agents★ 269

A practical library of agents, instructions, and skills designed specifically for QA Automation Engineers, focusing on production-oriented solutions.

kane-cli★ 267

Kane CLI by TestMu AI (Formerly LambdaTest)

auto-inspector★ 263

Web Testing AI Agent - Write your specs, it does the rest

sample-specship★ 258

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation, and anti-slop quality gates. Packaged as a Kiro Power.

codexqa★ 258

codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testcase generation, browser replay & RCA.

wai-play★ 256

WAI Play - AI web game testing and quality evaluation platform

botium-core★ 250

The Selenium for Chatbots - Bots Testing Bots

qaskills★ 250

QA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude Code, Cursor, Copilot, etc.).

tui-test★ 246

💻 testing framework and cli for controlling terminal apps - makes any terminal accessible for an ai agent

swe-sweep★ 246

How many bugs can LMs find & fix in large codebases?

webqa-agent★ 240

Autonomous web browser agent that audits performance, functionality & UX for engineers and vibe-coding creators. 网站自主评估测试 Agent,支持 GUI/CLI 一键完成性能、功能使用与交互体验的测试评估

jumpstarter★ 234

Hardware testing for the software world. Real or virtual, local or remote, human, automated or agentic.

distributed-system-testing★ 231

AI-agent skills for distributed-systems testing

Axolotl★ 221

AI-powered QA agent for VS Code. Analyzes code changes, generates test plans, runs real browser tests, and delivers evidence-backed merge verdicts.

RunTheRepo★ 219

An AI agent for running, testing, and hardening GitHub Docker Compose apps.一个用于运行、测试和加固 GitHub Docker Compose 应用的 AI Agent。

labwired-core★ 204

Open-source circuit and MCU firmware simulator for mixed-signal co-simulation, deterministic CI, and MCP workflows. STM32, ESP32, RP2040.

KillSwitch★ 194

An esoteric programming language built to break LLMs and coding agents.

rocketship★ 182

A QA testing framework for your coding agent.

ConcoLLMic★ 169

ConcoLLMic: the first language- and theory-agonistic concolic execution engine via LLM agents

AISquare-Studio-QA★ 168

Setting up QA testing agents using playwright and crewAI

coder_eval★ 160

Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.

antigravity-testing-kit★ 155

Đây là bộ SKILL, WORKFLOW, RULE do Anh Tester xây dựng dành riêng cho cộng đồng Tester để thiết lập AI Agent trên Antigravity hỗ trợ kiểm thử phần mềm.

AutoQA-Agent★ 136

AutoQA-Agent 是一个基于 Claude Agent SDK 构建的开源自动化测试 CLI 工具

rayfernando-skills★ 132

Ray Fernando's collection of Skill files for AI coding agents. First up: running-bug-review-board, a real-user QA workflow with a Bug Review Board (BRB) feedback loop.

xverif★ 121

xverif is a local toolkit for chip-verification debug agents. It contains deterministic tools for design and waveform debug, coverage, bit calculations, structured entry decoding, log source locations, SVA semantics, persistent verification knowledge, and a unified MCP entry point

assertify.io★ 120

AI-powered assistant that turns your project context into end-to-end test strategies, detailed scenarios, and ready-to-run boilerplate across popular frameworks.

hwatu★ 118

Headless verification browser for AI coding agents: 35 ms one-call checks, pixel diffs, live human hand-off

coverup★ 117

Automatic AI-powered test suite generator

a11y-checker★ 117

Accessibility scanner for humans and AI agents.

botsim★ 116

BotSIM - a data-efficient end-to-end Bot SIMulation toolkit for evaluation, diagnosis, and improvement of commercial chatbots

subagent-example-script★ 115

Claude Sub Agent Test Generator Command

wacat★ 113

wacat - Challenge Your Web App with Cat Chaos and AI-Driven Testing!

agent-python-pytest★ 111

Framework integration with PyTest

assay★ 110

An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

open-design-system-bench★ 108

How AI-ready is your design system? A plug-in benchmark that runs coding agents against your component library and grades the output. Built against a production design system and generalized for any React + TypeScript component library.

verdict-community★ 103

A modern, all-in-one competitive programming environment. Solve Codeforces problems with a built-in IDE, Whiteboard, and Custom Judge—no more tab switching.

mobile-tester-agent★ 100

AI-powered test automation tool which allows developers to run mobile automated tests

explorbot★ 100

AI Agent for Exploratory Browser Testing

agentic-pbt★ 100
Active-SWE★ 100

Pytorch Implementation of Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports

optics-framework★ 100

Open-source test automation for Android, iOS, web, smart TV (Android TV, Tizen, webOS) and Bluetooth (BLE) devices. Write tests as CSV/YAML, record them live, or let an AI agent build them over MCP. Self-healing locators: XPath, text, OCR, image.

speedrun★ 100

Fastest cross-platform E2E Automation for Mobile & Web

tero★ 99

Collaborative and secure AI agents platform that empowers software quality

autoheal★ 98

AutoGPT Agent which automatically fixes your tests. GPT-powered TDD.

da-code★ 98

[EMNLP 2024] DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models

More in Coding agents & developer tools