Agent QA Agent QA
agent-qa is a self-improving, agentic QA harness that lets teams write web and mobile tests in natural language. It builds memory from past runs, self-heals when UI changes, and catches regressions before shipping.
The npm package was updated to version 0.1.21 on June 3, 2026. The GitHub repository was created on May 7, 2026, and has 178 stars. Documentation was last updated in August 2026.
As of
- Natural language test authoring for web, Android, and iOS
- Self-healing test execution that recovers from UI drift
- Execution memory with trust scores and confirmation counts
- Action cache for faster runs and reduced token usage
- Sandboxed hooks (Node, Bun, Python, Bash) in Docker
- CLI, dashboard, and MCP integration for coding agents
- Bring your own LLM (OpenAI, Anthropic, Gemini, local models)
Teams building web and mobile applications that want to reduce selector rot and maintenance overhead on stable user flows, and QA engineers who prefer natural-language test authoring.
Teams whose test suites depend on complex conditional branching across application states, as the linear natural-language step model may not express such logic.
agent-qa is source-available and free to self-host, with no paid tier or seat fees. Users provide their own LLM credentials or use local models. An optional subscription auth plugin supports Codex and Claude Code subscriptions.
agent-qa offers a fresh approach to QA automation with natural-language tests and self-healing memory, making it a strong choice for teams tired of brittle selectors. However, its linear test model may not suit complex branching scenarios, and it requires users to bring their own LLM credentials.
Is Agent QA free?
Agent QA is Freemium. agent-qa is source-available and free to self-host, with no paid tier or seat fees. Users provide their own LLM credentials or use local models. An optional subscription auth plugin supports Codex and Claude Code subscriptions. Check the official site for current plans.
What is Agent QA best for?
Teams building web and mobile applications that want to reduce selector rot and maintenance overhead on stable user flows, and QA engineers who prefer natural-language test authoring.
Who makes Agent QA?
Agent QA is developed by Vostride. It is listed in the AI Testing & Quality Assurance category on ai.dosa.dev.
Sign in with GitHub or Google to Zap tools, vote, and get a README badge showing your stack.
Content on this page is AI-generated. Please verify details with the vendor's website for accuracy.