Agent QA is a source-available, self-improving test harness that allows teams to write end-to-end tests in plain-English YAML for web and mobile applications.
It uses LLMs to interpret screen state and labels, enabling self-healing execution that adapts to UI changes and builds persistent behavioral memory over time.
- 01
Natural language test authoring for web and mobile
- 02
Self-healing execution that adapts to UI drift
- 03
Persistent, file-backed execution memory
- 04
Action plan caching for faster repeated runs
- 05
MCP support for integration with AI coding agents
Freemium
Open-source with a permanent free tier; certain features require the @vostride/agent-qa-subscription-auth package.
Best for
Teams building web and mobile applications who want to reduce maintenance overhead caused by brittle, selector-based test suites.
Not ideal for
Complex test scenarios requiring conditional branching logic based on runtime application state, which are better suited for code-first frameworks.
An excellent choice for teams struggling with selector rot and maintenance, provided their test flows are primarily linear; however, it may feel constrained for highly dynamic or complex programmatic testing needs.
The tool has seen active development through mid-2026, including the refinement of its memory curator, MCP toolset for AI agents, and caching mechanisms to improve execution speed and token efficiency.
As of
Is Agent QA free?+
Agent QA is Freemium. Open-source with a permanent free tier; certain features require the @vostride/agent-qa-subscription-auth package. Check the official site for current plans.
Is Agent QA open source?+
Yes - Agent QA is open source. Open-source with a permanent free tier; certain features require the @vostride/agent-qa-subscription-auth package.
How much does Agent QA cost?+
Open-source with a permanent free tier; certain features require the @vostride/agent-qa-subscription-auth package. Pricing changes often - verify on the official site.
Who is Agent QA best for?+
Teams building web and mobile applications who want to reduce maintenance overhead caused by brittle, selector-based test suites.
Who is Agent QA not ideal for?+
Complex test scenarios requiring conditional branching logic based on runtime application state, which are better suited for code-first frameworks.
What are the best Agent QA alternatives?+
The closest Agent QA alternatives on ai.dosa.dev are GitAuto, AgentDiff, e2e - all listed under AI Testing & Quality Assurance.
Who makes Agent QA?+
Agent QA is developed by Vostride. It is listed in the AI Testing & Quality Assurance category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.