Coding agents & developer tools

Testing & QA agents

988 agents · most starred first

Testing & QA agents, page 10 of 10

windupjs

Windup — testes E2E em linguagem natural: a LLM planeja uma vez, o replay roda sozinho

agentcov

AI-agent read coverage for source files, with LCOV and gcov-compatible reports.

autotest-agent

AI-powered Python unit test generation agent with ReAct architecture

kaneai

KaneAI review: compare features, pricing, use cases, access model, and alternatives for this Software Testing agent in 2026. Rated 4.8/5 from 5 verified reviews. GenAI-Native End to End Software Testing Agent.

@anatolykhelmer/deep-cover

Agentic code coverage analyzer

fdnqa

QA Agentic Workflows for OpenCode — 9router edition

adopt-coverage

recompute_coverage and the cache-disagreement alarm. Implemented in S4.

qaos-agent

Quality Assurance Operating System — engine-agnostic, documentation-driven, AI-native QA platform

@qawolf/cli

Run and manage QA Wolf flows from the terminal, CI, or an AI agent

@vitest-agent/plugin

Vitest plugin for the vitest-agent ecosystem: owns persistence, classification, baselines, trends, and dispatches rendering to a configurable reporter.

testroid

AI-powered multi-agent Playwright test framework generator

autotestgpt

A multi agent (GPT-4) test engineer that writes tests for you.

rfazlur-qaflow

QA Agentic Workflows for OpenCode — 9router edition

@mce-bt/microagents-testing

Agentic test framework — declarative test cases, live execution, structured evaluation

coherence-check

Your AI agent says the work is done. Coherence makes it prove it — evidence, not claims, with tamper-evident CI sessions.

karsa-sentinel

Autonomous AI QA automation agent that transforms product intent into validated Playwright BDD test suites

@aarwitz/tapp

Let coding agents verify UI changes on real iOS, Android, and web surfaces, then enforce reviewed proof in deterministic CI.

agentic-playwright

Placeholder — Production-grade Playwright + TypeScript Scaffold for Agentic Testing. Use: npm create agentic-playwright. Full release: September 2026.

create-agentic-playwright

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

@archqa/create-agentic-playwright

Placeholder — Production-grade Playwright + TypeScript Scaffold for Agentic Testing. Full release: September 2026.

gherkin-ai

Enterprise-Grade Closed-Loop Agentic Orchestration Engine & Spec-Driven Verification Framework for AI Coding Agents.

playwright-pom-agent

LLM-assisted Playwright Page Object Model generator with live locator verification.

pytest-agentic-fabric

Pytest fixtures for projects built on agentic-fabric

ai-web-tester

Autonomous browser testing engine & MCP toolset for AI coding agents

agentic-tdd

An npx-executable, agentic TDD pipeline orchestration tool — 8-pass state machine for enterprise software development

agent-build-gates

Quality gates for agent-built code: an anti-simulation tripwire, an AWS-account tripwire, a local-path tripwire, a denylist tripwire, and an eval harness with confidence intervals and significance testing.

agent-crucible

Reproducible testing, benchmarking, and regression testing for Agent Skills.

agentlahon

Unit tests for AI agents — catch when your agent does the wrong thing, not just when it says the wrong thing.

agentprobe-testing

Adaptive chaos-testing for LLM agents: a live model-driven Injector that reads an agent's real trajectory and decides where to break something, instead of scripting perturbations in advance.

agentproof-sim

Stateful simulation and fault-injection testing for AI agents that take actions through tools.

agentraas

Reliability layer for AI agent actions: exactly-once tool calls (@exactly_once, LangChain and CrewAI protect_tool, MCP wrap), an MCP safety scan, a chaos tester for duplicate calls, and the AgentRaaS client for policies, approvals and audit

badgerp_get_lcov_coverage

Report line coverage from lcov.info (produced by grcov or cargo-tarpaulin)

devagent-physical-engine

Verification-first multi-vendor commissioning control plane with flexible guided customer-file intake, deterministic source/evidence authority, exact-Twin lineage, regression, FAT reporting, and pre-site readiness.

fsq-agent

Goal-driven FSQ automated testing agent with a local agent engine, OpenAI-compatible model access, harness actions, local utilities, observation, and reporting.

proofed-agent

A deterministic evidence gate for coding-agent completion claims.

covtrim

Token-efficient coverage report compressor for LLM/agent consumption. Reads lcov, outputs compact TSV.

@kamrankhan027/probe-ai

Autonomous API Schema & Reliability Inspector CLI. Probes OpenAPI specs, generates test suites, executes real-time HTTP calls, and exports Postman collections.

coverage-flashlight

Explore Python coverage and replay execution with a code flashlight.

Test Guard

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

compat-audit

AI Agent skills scaffolder & zero-config browser compatibility engine for production bundles

@testspectra/skills

Installer & manager for modular AI agent skills that standardize TestSpectra script authoring (specs, page objects, steps, actions, hooks, fixtures, matchers)

qa

The CLI for Mo, Momentic's autonomous QA agent.

agent-cli-mocks

Deterministic command-line mocks for isolated agent skill testing

agent-skills-pss

Agent skills for writing and reviewing PSS (Portable Test and Stimulus) models

agentspec-cli

Auto-test and validate agent-generated APIs. CLI + MCP server for the agent era.

aumate-qa-agent

Aumate QA — framework-agnostic auto-healing agent for any language, any test framework

coderecoverage

Project-agnostic agentic code coverage: measure, score, explain gaps, draft tests.

coverage-tool

Multi-compiler (GCC/Clang/MSVC) C++ code coverage report generator

readystack-coverage-gate-lint

Finds the coverage gates in your repo that can never fail a build (bundled Node.js runtime)

@wdio/ai-service

A WebdriverIO service that adds browser.act() and browser.extract(): steps written as intent, recorded as WebdriverIO commands and healed when the page changes

@detiq/agents

AI agents that produce test artifacts grounded in the ZeTa Core, coordinated by orchestrators: - `DualContextOrchestrator` / `SwarmOrchestrator`: Multi-agent pipeline coordinating CAG (Component-Augmented Generation) and KAG (Knowledge-Augmented Generatio

e2e

SDK, runner, and CLI for agentic end-to-end testing

@e2e-dev/web

Web engine for e2e agentic end-to-end testing, built on Playwright

@e2e-dev/mobile

Mobile engine (iOS and Android) for e2e agentic end-to-end testing, built on agent-device

@anatolykhelmer/deepcover

Agentic code coverage analyzer

testronaut

Agentic end-to-end testing with AI agents and Playwright. Define user journeys in plain English and run them in real browsers.

agentic-e2e-testing

Agentic end-to-end testing with Zerocheck: plain-English browser checks with explicit expected outcomes, saved and rerun from CI.

agentic-qa

Agentic QA with Zerocheck: describe each check in plain English, let the QA agent run it in a real browser, and keep the evidence.

agent-handshake

Contract tests for agent handoffs: record what one agent returns, infer what the next one reads, and check it in CI without LLM calls.

agent-reliability-ci

Did your AI agent get worse? Real, noise, or cannot tell: from coding-agent session logs, imported results, or controlled trials with fault injection.

agent-testbench

A test bench your coding agent operates: live kernels and verified runs on Modal GPUs, Colab or your machine, inside a budget.

agentcheck-pytest-plugin

Pytest plugin for testing non-deterministic AI agents with statistical assertions, fault injection, and record/replay cassettes

agentfault

Agent Fault: open-source stateful reliability testing for AI agents

agentflight-cli

An open-source auditing tool to prevent AI coding agents from tampering with test assertions.

agentqakit

Fault-injection and regression testing for AI agents

livery-extensions-coverage

Each package's coverage floor in the livery workshop, judged on the union of what every CI leg measured, the record that carries it across runs, and the site's coverage pages.

llm-fuzz-ci

Generate adversarial test inputs with a coding agent; your pytest assertions judge them

loki-chaos-agent

Autonomous AI Testing & Synthetic Chaos Agent

qagent-pytest

Sistema multiagente que genera y valida pruebas pytest para código Python 3.10+

qmpass-test-agent

Run your Qmpass automated tests on your own machines, securely connected to your Jira projects.

scrutineer-agents

Agent Behavioral Testing Platform — tests what agents DO, not just what they SAY

shopee-skynet-quality-agent-jira-remote-links

A small example package

shopee-skynet-spr-agent-query

A small example package

proctor-agent

The exam proctor for AI coding agents: catch agents that game their tests, and measure whether their code generalizes to tests they never saw.

@karthicknethaji-hcl/agent-test-kit

Agent-agnostic AI agent test execution framework: generate, review, and run rubric-scored test suites against any AI agent in any codebase.

cypress-mcp

MCP server for AI-driven Cypress test execution. Run, debug, and iterate on E2E tests directly from your AI agent.

universal-agentic-qa

Deterministic, zero-hallucination agentic QA verification engine across Web, Mobile, Desktop, and APIs

strest-mcp

Declarative Multi-Step REST API Test & Chaining Engine for AI Agents and DevSecOps

pytest-agent-behavior

Deterministic pytest assertions for AI agent tool calls, approval ordering, and repeated-call limits.

pytest-agent-chaos

Deterministic chaos engineering and fault-injection plugin for multi-agent LLM workflows and tool-calling pipelines.

qa-agent-kit

The QA agent kit: mutation testing for any repo, prose gates with a claims ledger, and real-device QA for Apple apps, with the procedures an AI coding agent follows.

AgentAssure-ai

pytest-based QA framework for enterprise AI agents: routing, tools, state changes, permissions, and LLM metrics.

AgentAssure-ai-agentforce

Salesforce Agentforce adapter for AgentAssure: Agent API sessions, SOQL state diffs, persona permissions, native test integration.

agentqit

Application testing tools for AI agents

jarvisx-evidence-agent

JarvisX verify + Connected-Evidence agent — prove an AI-made (or any) SQL change is behavior-preserving (credential-free row-diff; pass/block/review gate for agents & CI), and reconcile a migration on your OWN engines (push-down fingerprint, 1 TB+) emitting counts+hashes only — optionally with an Ed25519-signed certificate from JarvisX.

Persqo

Persqo sends AI personas, like an impatient user or a non-technical user, through your live web app. They use it the way customers would, find where things break or confuse, and hand you a ready-to-fix list with screenshots and a prompt for Claude Code. Free check at persqo.com/free-check; 3 free sessions, no card.

cpp-coverage

C++ coverage reports, changed-code PR gating with coverage provenance checks, and a static coverage website.

Gamepad Bench

Free online gamepad tester for stick drift, buttons, triggers, and polling rate.

More in Coding agents & developer tools