AgentScout / Tasks / Writing code / Testing and QA

Testing and QA tools for coding agents

Agents that write and run tests and report what breaks. Of the 492 tools on our writing code page, 11 fit this narrower job. By pricing: 4 open source, 2 free or freemium, 2 paid, usage-based or enterprise, 3 pricing on the maker's site. The most-starred open repos here are Qodo (13,634 stars), Shippie (2,513 stars), OpenHarness (1,375 stars). Most come from the QA & testing (7), coding (2), vision (1) categories.

Updated

Qodo logo

Qodo

QA & testingFreemium

AI code review and testing agents that work in the IDE, the terminal and pull requests to catch issues before merge.

Added

Shippie logo

Shippie

QA & testingOpen source

Extendable code review and QA agent that reads your diff, explores the codebase and posts focused review comments.

Added

OpenHarness logo

OpenHarness

NewcodingOpen source

OpenHarness from Autonomous is a native command center for running coding agents side by side, including Claude Code, Codex, Cursor, OpenCode, Devin, Amp and Copilot. It links your laptop, home server and GPU box into one window with a password instead of SSH keys or port forwarding, keeps code and keystrokes end-to-end encrypted through its relay, and is keyboard first. Agents keep working when you close it, and it extends beyond code to CAD, circuits, robots, games and music.

Added

QA Agent logo

QA Agent

NewQA & testingOpen source

QA Agent is an open-source Playwright library for AI browser regression testing. An agent writes, runs, or maintains tests and reports what broke.

Added

agent-qa (Vostride) logo

agent-qa (Vostride)

QA & testingSee site

A self-improving AI QA agent with persistent memory that tests web, Android and iOS apps from plain-English test steps, for developers and coding agents.

Added

Agentic QE logo

Agentic QE

NewQA & testingOpen source

Agentic QE Fleet is an open-source QA platform that works with coding agents to test software

Added

Encord Agents logo

Encord Agents

visionPaid

Encord's agents that plug foundation models or your own models into labeling workflows to pre-label, segment, track, route and QA image, video and multimodal data, with a no-code catalog and an open-source SDK.

Added

Coldtea logo

Coldtea

codingPaid

Agents that test every pull request on real devices, watch production and file issues before users hit them.

Added

Momentic logo

Momentic

QA & testingFreemium

AI testing platform with an AI QA agent that runs and maintains plain-English tests and reports bugs with repro steps.

Added

TestSprite logo

TestSprite

NewQA & testingSee site

TestSprite is an agentic testing tool that writes and runs end-to-end tests after code changes

Added

Vinsi logo

Vinsi

NewvoiceSee site

VINSI is the all-in-one AI SaaS platform for premier AI voice agents, CX automation, CRM, workflows, ticketing, QA, analytics, and more. We deliver a powerful, secure AI ecosystem built to help you dominate any industry

Added

GitHub repos (7)

RepoGitHub starsLicenceLast push
Qodo ↗13,634MIT2026-10-27
Shippie ↗2,513MIT2026-07-02
OpenHarness ↗1,375—2026-10-27
QA Agent ↗1,293——
agent-qa (Vostride) ↗897—2026-10-24
Agentic QE ↗519——
Encord Agents ↗18Apache License 2.02026-09-23

7 repos. Stars and licence come from each repo, checked when the listing was last verified.

FAQ

What are the best AI tools for writing code focused on testing and QA?

We list 11. The first three by GitHub stars and featured status are Qodo: AI code review and testing agents that work in the IDE, the terminal and pull requests to catch issues before merge.; Shippie: Extendable code review and QA agent that reads your diff, explores the codebase and posts focused review comments.; OpenHarness: OpenHarness from Autonomous is a native command center for running coding agents side by side, including Claude Code, Codex, Cursor, OpenCode, Devin, Amp and Copilot. It links your laptop, home server and GPU box into one window with a password instead of SSH keys or port forwarding, keeps code and keystrokes end-to-end encrypted through its relay, and is keyboard first. Agents keep working when you close it, and it extends beyond code to CAD, circuits, robots, games and music.

Are there free or open-source options?

Yes: 4 open source, 2 free or freemium, 2 paid, usage-based or enterprise, 3 pricing on the maker's site. Pricing is as each maker states it.

More from writing code

Tools are grouped by what each says it does. Missing one? Submit it free.

AgentScout Weekly + Free 50 AI Agents & 50 MCP Servers Cheat Sheets

Get the 5 best new AI agent tools, copy-paste MCP workflows, and our high-res 50 AI Agents & 50 MCP Servers Cheat Sheet Pack free every Tuesday — plus daily founder stack teardowns on X from @clampdown19 & @AgentScoutHQ.