Free to browse, every day. Go Pro for unlimited installs and Airsc MCP.

See Pro
MCP serverCautionTesting & debuggingSome setup

agent-qa

vostride · vostride/agent-qa

An open-source, self-improving QA agent that writes tests in natural language for web and mobile, learns from runs, adapts to UI changes, and catches regressions.

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.

891 stars22License: No licenseUpdated yesterday0 opens

Preview

▍

What you can do with it

  • Write end-to-end tests for web applications using plain English descriptions.
  • Automate mobile app testing that adapts to UI changes without constant test updates.
  • Integrate AI-driven QA into your CI/CD pipeline to catch regressions early and reduce manual effort.

Safety check

Caution

Usable, but read the notes first.

  • ●No clear license: check with the author before using it in a commercial product.

Automated scan of the repo files. Always review code you run.

From the README

English · 中文

Website · Docs · Demo · Blog · Changelog

Your AI QA engineer, with memory. Describe a user journey in plain language. agent-qa tests it on web, Android or iOS and keeps the evidence. Use the CLI, the dashboard, or your coding agent through MCP and skills.

  • memidex: remembers facts and working procedures as reviewable files in your repository.
  • Self-improvement: validates lessons from runs, retires stale knowledge, and uses your feedback to correct mistakes.
BenchmarkRankPublished result
AndroidWorld#1100% pass@1 (116/116 tasks)
AppControlBench#199.6% completion (114.5/115 points)

Read the full benchmark reports, with run evidence and methodology, on our blog. Both used gpt-6-sol with memory and self-improvement off; AppControlBench gives half credit for partial completion.

See it in action

Inspect a failure. The demo catches a cart showing $29 instead of $53, with the failed step and its screenshot side by side.

See what memory contributed. Inspect the knowledge supplied to a run and trace it back to the steps that used it.

Run from your terminal. Real output from the demo suite: checkout passes; the deliberate cart-total bug fails.

Get started

Requires Node.js 24+.

npm install -D agent-qa
npx agent-qa init

Follow the quickstart to connect a model and run the demo, or set up with your coding agent.

[!NOTE] Early stage. Expect bugs. Report an issue when something breaks.

License

Functional Source License (FSL-1.1-ALv2).

View source on GitHub