Qpilot released: executes plain-text manual test cases in Chrome
Understand this story
broxhq releases Qpilot: after users paste plain-text manual test cases, an AI agent executes them step by step in a real Chrome, returning pass, fail, or warning for each step, along with screenshot evidence. The install command is npx qpilot, requiring Node.js 20.12+, Chrome, and an Anthropic API key or any OpenAI-compatible endpoint (such as Qwen, vLLM, Ollama, enterprise gateways); the model used must support tool calling. According to the release notes, apart from model calls, everything runs locally, so it can be used for staging and internal networks; run records are kept only in memory, retaining at most the most recent 50 runs, and are cleared when the service restarts.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: Qpilot – an AI agent that runs plain-text manual test cases in Chrome
Qpilot is an AI agent that executes plain-text manual test cases in real Chrome via `npx qpilot`, requiring Node.js 20.12+, Chrome, and an Anthropic API key or any OpenAI-compatible endpoint. It reports each step as pass, fail, or warn with expected vs. actual results and screenshots, and re-checks every pass with a separate model call that can only object. It also supports request mocking and inspection, file uploads, tab and dialog handling, and batch runs of a folder of test cases, with everything running locally except model calls.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 18 19:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.