agent-qa

Self-improving QA **harness** for web and mobile apps: natural-language tests, memory-backed self-healing, dashboard/CLI, MCP and skills support, plus sandboxed hooks for production regression checks.

mcpmemorysandboxclitypescript

Stars: 915
Adoption surface: slightly complex
Autonomy: headless
Recovery: retry
License: ⚠️ FSL-1.1-ALv2 restricted (FSL-1.1-ALv2)
Category: Evaluation and benchmarking harnesses

Repository ↗ Example: Natural-language QA harness ↗

Related in Evaluation and benchmarking harnesses

Agent Lightning
SWE-bench
AgentBench
inspect_ai
WebArena
ClawBench

Maintain agent-qa? Add the badge

Paste this into your README so readers can find the list and see how agent-qa compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)