Agent Qa
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 eve…
Users can write tests in plain language for web and mobile apps. It builds persistent memory from validated run evidence. It validates and applies proposed lessons while retiring outdated knowledge.
Intelligent caching reduces token usage and speeds up repeat runs. A single testing platform supports both web and mobile. Users can bring their own model and switch providers without rewriting tests.
It ranks #1 on both AndroidWorld and AppControlBench benchmarks.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.