Agent-QA

Open-source agentic QA harness — write end-to-end tests in natural language and run them across browsers

Servicemvpfreeglobal

An open-source QA harness that lets teams write end-to-end tests in plain natural language and execute them across browsers. It reduces brittleness by using visible roles, labels, and screen state instead of fragile selectors, and builds execution memory across runs to help catch regressions. Intended for developers and QA engineers working on apps built with coding agents and small teams without dedicated QA.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Agent-QA - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Agent-QA to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Agent-QA (or something else) actually fits.

Try a problem