Open-Source Agent Runs Autonomous QA Tests

An open-source experiment released on GitHub (github.com/brentkastner/ai-qa-framework) demonstrates a Claude-based autonomous QA framework using Python and Playwright. The system accepts minimal inputs — a URL and optional credentials — then autonomously generates test plans, explores the application, executes tests, collects evidence, asserts outcomes, and tracks regressions. The repository provides runnable code for practitioners to evaluate automated test generation and execution.