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
What is 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 every run, adapts to UI changes, and catches regressions before you ship.
Overview of agent-qa
What it is
agent-qa is an open-source, self-improving QA agent for software teams. It is a test harness with memory that allows writing tests in natural language for web and mobile applications. agent-qa learns from every run, adapts to UI changes, and catches regressions before shipping.
Key features
- Write tests in natural language for web and mobile: define actions and assertions in human language while agents work from visible roles, labels, and screen state.
- Self-healing test execution: when a sub-action fails, agent-qa re-observes the UI and tries a different path in the same run, recovering from UI drift and flaky interactions.
- Self-improves with Memory: builds execution memory from product, suite, and test observations, and curates memory from healed steps to help future runs avoid the same mistake.
- Built for humans and machines: includes a polished dashboard and CLI for developers, plus MCP and skills for coding agents.
- Accelerate runs with smart Cache: reuses validated plans across similar subsequent test runs, reducing planner work, token usage, and runtime overhead.
- Run sandboxed hooks during tests: run Node, Bun, Python, or Bash hooks in isolated Docker containers to set up environments, call APIs, seed fixtures, tear down state, or pass structured outputs back into the active test run.
- Open source, reviewable QA: tests, configs, hooks, memory, and suite logic live as version-controlled code, so every change can be diffed, reviewed, reused, and shared across teams.
Use cases
Writing and executing tests for web and mobile applications in natural language. Catching regressions before shipping. Running sandboxed hooks for test environment setup, API calls, fixture seeding, and state teardown. Using with coding agents via MCP and skills for automated QA.
Getting started
Requires Node.js 24 or newer (npm comes with it). sh npm install -D agent-qa @vostride/agent-qa-subscription-auth npx agent-qa install-browsers --chromium npx agent-qa init --llm claude-code With an API key, install agent-qa alone and pass another --llm value. See the repository README for the full getting-started guide.
License and pricing
The license is not explicitly stated in the README. Metadata indicates NOASSERTION and the project is open source.
Based on the project's public README and repository metadata.