Coding agents & developer tools

Testing & QA agents

988 agents · most starred first

Testing & QA agents, page 6 of 10

KrakQL★ 2

[SSBSE'25] This repository provides the artifact for the "KrakQL: LLM-Guided Blind Introspection of GraphQL Schemas" paper

McpTestGenerator★ 2

Standardized Test Case Generation for LLM Agents via Model Context Protocol. Bridging the gap between AI and QA (Xray/Jira).

user-test★ 2

Multi-agent User Testing plugin for Claude Code — AI persona agents test your spec/web/API with research-backed role-playing techniques

qa-auto-agentic★ 2

QA-Auto is an automated QA testing framework powered by LLMs and browser automation. It reads BDD-style feature files, executes all scenarios, and generates Cucumber-style HTML reports.

Cursor-Writing★ 2

An AI functional testing project

selenium-selfhealing-mcp★ 2

An MCP server that automatically fixes broken Selenium test locators when UI changes occur, reducing test maintenance overhead.

ohmyperf★ 2

Real-machine, real-browser web perf measurement with ~99% iframe coverage. LLM-native + AI-agent-loop ready.

testing-full-flow★ 2

gradio region:us

AutoJudge-Project★ 2

🤖 Predict programming problem difficulty with AI using text analysis and machine learning for accurate complexity scoring.

CodeSampleX★ 2

An open compatibility testing network: does this library API actually run on your version, OS and runtime? Real build evidence, verified samples, and the environment each result came from.

deepseek-rust-harness★ 2

Rust dev plugin: fmt-clippy-build-miri/audit verification pyramid + 12 semantic practice cards + problem-oriented docs map

agentbarrier★ 2

Deterministic approval, rejection, cancellation, timeout, replay, and side-effect safety tests for AI agents—no API keys required.

witness★ 2

Built for AI agents: drive and debug a running app from one config file, and come back with proof a person can watch and an agent can read — not a pass/fail, and not a guess.

schema-parity★ 2

Differential harness that finds values a generated JSON Schema accepts but the runtime validator it came from rejects. Zero runtime dependencies. Works with Zod, Valibot, ArkType and TypeBox via three-line adapters.

witness★ 2

Built for AI agents: drive and debug a running app from one config file, and come back with proof a person can watch and an agent can read — not a pass/fail, and not a guess.

harness-evolver★ 2

Self-owned TerminalBench 2.0 coding-agent harness with a Rust Worker, Harbor/verifier-grounded evaluation, and guarded Heuristic Learning.

opencase★ 2

Declarative test-case management: git-native case files, agent execution, human review gate

agent-test-hub★ 2

Agent 自动测试系统:LangGraph + LLM 编排的 API/Web UI 自动化测试,从 OpenAPI 契约生成用例、执行测试、自动重试与缺陷归因,产出可视化报告

deepcover★ 2

100% coverage, still broken. Finds tests that run your code but verify nothing. TypeScript · Jest · Vitest

runboth★ 2

An AI changed your code. RunBoth runs both versions and tells you what actually behaves differently, including the functions nobody touched.

omniTrace★ 2

A privacy-first, local AI background daemon that autonomously intercepts and patches Python crashes using Ollama and regex.

negative-test-first★ 2

Agent skill: a general testing discipline — a requirement is covered only when a test shows that violating it fails. Business rules, data invariants, persistence, concurrency, API contracts, security.

ttsem★ 2

Runs Triton kernels from their IR on the CPU and checks every launch (races, out-of-bounds, per-pass validation). Found silent torch.compile miscompiles without a GPU.

Huggingface_AI_Agent_Function_Testing★ 1

gradio region:us

API_Testing_AI_Agent★ 1

gradio region:us

ai-software-testing-agent★ 1

docker region:us

dealii_assistant_test_suite_standard★ 1

gradio region:us

dealii_assistant_test_suite_plus★ 1

gradio region:us

QA-Assistant★ 1

gradio region:us

auto_test_case_gen_llm★ 1

streamlit region:us

self-auditing-agent★ 1

Other AIs prove they can work; this one proves it can be audited. A public audit log where every claim carries a rerunnable command — plus gatecheck, mutation testing for your quality gates.

credit-card-generator

Credit Card Generator review: compare features, pricing, use cases, access model, and alternatives for this Software Testing agent in 2026. RandomoCard is customizable random credit card numbers

digitalemployeesio

DigitalEmployees.io review: compare features, pricing, use cases, access model, and alternatives for this Digital Workers agent in 2026. Rated 4.4/5 from 7 verified reviews. Digital Workers for TechOps & QA - augmenting teams, automating workflows, and accelerating.

micro-agent

Micro Agent review: compare features, pricing, use cases, access model, and alternatives for this Coding Agent agent in 2026. An AI Agent that writes and fixes test-driven code from natural language descriptions.

KaneAI

KaneAI is an AI tool that simplifies software testing. You create and run complete tests for applications using everyday language, no coding needed. It checks v

AutoQA

AI agents automatically test your software, stopping flaky UI bugs.

Momentic AI

Momentic AI writes, fixes, and runs software tests in plain English.

KushoAI

KushoAI automates software testing, saving hours and finding bugs.

TestSprite

Automate web app testing with AI. Fast, no-code, and smart.

@netlify/axis

Agent Experience Index Score — synthetic testing for AI agent interaction

testdriverai

Next generation autonomous AI agent for end-to-end testing of web & desktop

@dreamcatcher-ai/cli

AI Agent testing suites

@testdriverai/mcp

Next generation autonomous AI agent for end-to-end testing of web & desktop

st4ck

Record tests with your AI agent. Replay them forever, for free. Two npx commands: `st4ck author <url> "<steps>"` + `st4ck run <file>`. No install required.

@testdriverai/agent

Next generation autonomous AI agent for end-to-end testing of web & desktop

@zenai/playwright-coding-agent-reporter

A coding agent friendly reporter for playwright, so that your coding agent finally really understands what is going wrong

@allurereport/plugin-agent

Allure Agent Plugin – AI-friendly markdown report generator

jat-feedback

Embeddable feedback widget for bug reports and feature requests. Captures screenshots, console logs, and user context as a web component.

@wix-pilot/detox

Detox driver for Wix Pilot usage

@lythos/test-utils

![Coverage](https://img.shields.io/badge/coverage-94%25-brightgreen) ![CI](https://img.shields.io/badge/CI-78%20unit%20tests-brightgreen) ![Intent/Plan](https://img.shields.io/badge/arch-intent%2Fplan%2Fexecute-8A2BE2) ![LLM Audit](https://img.shields.io/

ccqa

Browser test recorder powered by Claude Code and agent-browser

@blazediff/agent

Agentic visual regression for BlazeDiff. Auto-discovers routes, captures deterministic screenshots, runs CI checks.

codeloop

CLI tool for CodeLoop — automated verification for AI coding agents

agent-qa

The self-improving Agentic QA harness with Memory

@clipboard-health/playwright-reporter-llm

Playwright reporter that outputs structured JSON for LLM agents. Minimal console output, flat schema, easy to filter to failures.

endorphin-ai

E2E Testing Reinvented with AI - A powerful TypeScript browser automation framework using AI-powered testing with LangChain, OpenAI GPT-4o, and Playwright

@reportportal/agent-js-playwright

Agent to integrate Playwright with ReportPortal.

@a5c-ai/agent-mux-harness-mock

Mock harness simulator for testing agent-mux adapters — simulates claude-code, codex, and other CLI harnesses

playclaw-openai

Connect your OpenAI agent to PlayClaw — the professional testing playground

visual-agent

AI-driven browser testing tool with live headed browser, video evidence, and per-session artifacts.

ai-ctrf

Generate AI summaries of test results using a wide range of AI models like OpenAI, Anthropic, Gemini, Mistral, Grok, DeepSeek, Azure, Perplexity, OpenRouter, and custom OpenAI-compatible APIs

runsight

Autonomous agent that runs projects, explores them, captures screenshots, and records demo videos automatically

@aldine/confucius-agent

Confucius Agent - Ralph Protocol v3 + Browser QA MCP Server with AI agent focusing system (ESLint strict mode). Autonomous agent scaffold with visual QA, accessibility testing, and typo/linting prevention.

@arcadialdev/arcality

El primer ingeniero QA Autónomo integrado al CI/CD. Creado por Arcadial.

vigil-qa

AI agents that test your web app like a human would — describe what to test in plain English, and an autonomous agent navigates, clicks, types, and verifies the result in a real browser

@browserstack/ai-sdk-node

Browserstack integrations

aws-sdk-client-mock

Easy and powerful mocking of AWS SDK v3 Clients

ai-qa-framework

Universal AI QA Automation Framework — project-agnostic, enterprise-grade. Install with npx ai-qa-framework install.

@zibby/core

Core test automation engine with multi-agent and multi-MCP support

@cef-ai/testing

Simulator harness for CEF agents — `testAgent` for single-agent in-process tests, `testPlatform` for multi-agent tests with a vault simulation.

qaa-agent

QA Automation Agent for Claude Code — multi-agent pipeline that analyzes repos, generates tests, validates, and creates PRs

@keber/qa-framework

Reusable spec-driven QA framework for IDE-agent-assisted automated testing. Installable as an npm package. Provides structure, templates, agent instructions, and optional integrations for Playwright and Azure DevOps.

create-agentic-qa

Official scaffolder for the Agentic QA ecosystem — bootstraps a project from agentic-qa-boilerplate and runs its interactive installer.

agentic-qe

Agentic Quality Engineering V3 - Domain-Driven Design Architecture with 13 Bounded Contexts, O(log n) coverage analysis, ReasoningBank learning, 60 specialized QE agents, mathematical Coherence verification, deep Claude Flow integration

agentic-testari

Agentic Testari CLI — autonomous QA testing under AIOS development discipline (Node.js wrapper around the Python wheel).

@agentic-qe/v3

Agentic QE v3 - Domain-Driven Design Architecture with 12 Bounded Contexts, O(log n) coverage analysis, ReasoningBank learning, 47 specialized QE agents

tailtest

LLM-first test layer for AI coding tools. https://tailtest.com

dingdawg-test-agent

Validate and test your DingDawg marketplace agent before publishing. Checks manifest, MCP tools, governance policies.

ai-testing-suite

LangGraph Multi-Agent Automated Testing Suite for Node.js/TypeScript — 8 AI agents that analyze, test, review, secure & document your project. OWASP Top 10, Zero-Day scanning, 100+ vulnerability patterns.

AtherisLiteLLM

AI-powered Python fuzzer using LiteLLM and Atheris to automatically generate and execute fuzzing harnesses.

InspectorAgent

lib to assert perf test result to Inspector

LDB_Setuptools_Coverage

Package to add coverage command to setuptools

PyLLMut

An LLM-driven mutant generator library for Python

agency-pytest-agent-reporter

pytest plugin that prints unit test results in an agent-friendly way

agent-cooking-cli

Evidence-first, artifact-driven bug triage workflow for CLI agents

agent-flow-tdd

Agent Flow TDD - Biblioteca para desenvolvimento orientado a testes com agentes

agent-output

Drastically reduce token consumption for unittest and pytest runs

agent-qa-console

Visual browser QA console for AI coding agents — live browser, element selection, source mapping, RTL/a11y/perf audits, and test-fix-verify loops.

agentassay

Formal regression testing for non-deterministic AI agent workflows

agentassert

Behavioral testing framework for AI agents — pytest for AI agents

agentassert-abc

Formal behavioral specification and runtime enforcement for autonomous AI agents. Agent Behavioral Contracts (ABC).

agentclip

Turn AI agent QA runs into shareable slideshows.

agentguardCI

Open-source CI contract testing for tool-using AI agents.

agentic-harness

Deterministic quality gates for AI-assisted development

agentic-test-framework

AI-powered browser testing framework using natural language and OpenAI

agentic-testari

Agentic Testari — autonomous QA testing under AIOS development discipline

agentic-testing

Multi-agent orchestration and testing framework with LangGraph, CrewAI, and FastAPI.

agentops-ai

AI-powered development platform: Multi-agent system for requirements discovery, conversational document building, and test automation

agenttester

Run a prompt against multiple coding agents in parallel and compare results

ai-agent-vcr

The undo button for coding agents: record runs, roll back state and files, replay verified work, and gate regressions in CI.

More in Coding agents & developer tools