This is an early release preview. You may encounter bugs.
QA Use logo
Unclaimed

App interface

QA Use

AI-powered E2E testing platform powered by Browser Use agents.

01 / Summary

About QA Use.

QA Use is a self-hosted end-to-end testing platform in which Browser Use agents execute web tests written in plain English. You describe test steps and a success criterion in natural language, and an agent navigates the site, interacts with elements, handles popups and dynamic content, and then evaluates the final page state against your criterion to produce a pass or fail report with screenshots and recordings.

The platform runs with Docker Compose and is built on Next.js 15 and TypeScript with a PostgreSQL database. It needs a Browser Use API key; a Resend key enables email notifications and Inngest handles background job processing in production. The project serves as a reference implementation of a testing platform built on Browser Use.

  • Natural-language tests: define steps and success criteria in English rather than selectors or scripts
  • Agent execution: Browser Use agents navigate, interact, and adapt to layout changes and unexpected dialogs
  • AI validation: the agent compares the final page state with the expected outcome and reports pass or fail
  • Test suites: group tests and run several in parallel
  • Scheduling: run suites hourly or daily
  • Notifications: email alerts when a suite fails, via Resend
  • Evidence: screenshots and recordings attached to each run

02 / Discussion CREDIBILITY-GATED

Discussion

Reading is open to everyone. Posting and voting need a verified identity or a GitHub grade of B or higher.

  • No discussions yet.

04 / Build

Build with QA Use.

Browse the catalog for frameworks, tools, and harnesses, each scored on real GitHub credibility.

Get QA Use →

Browse the catalog