Hey HN! I built QA Panda — an AI QA agent that runs inside VSCode.
You describe what to test in plain English, and it launches headless Chrome, navigates your app, clicks through flows, finds bugs, takes screenshots, and gives you a structured QA report with test cases and bug tracking.
It uses Codex CLI under the hood, so it works with a ChatGPT subscription — no API tokens needed.
When it finds bugs, you can let the built-in Developer agent fix and re-test automatically, or just copy the report into Claude Code / Cursor / whatever you use.
It's free and MIT licensed. Would love feedback — especially on what you'd want from an AI QA tool.
Nice idea. I added it now and it's on the latest VSCode extension and also the Github repository (you can add any API key even OpenAI, Anthropic etc, not just OpenRouter)
I also added tons of other things like live test updates, copy buttons on all test cards and issue cards (so you can just copy and paste to claude code to fix the given issue) and also a QA report card which is emitted as the final summary of a test which shows you everything that was tested at one place (no need to scroll up) and allows you to even export it as a PDF (all tests performed / their outcome and all issues found)
Let me know if there is anything else
Hey HN! I built QA Panda — an AI QA agent that runs inside VSCode.
You describe what to test in plain English, and it launches headless Chrome, navigates your app, clicks through flows, finds bugs, takes screenshots, and gives you a structured QA report with test cases and bug tracking.
It uses Codex CLI under the hood, so it works with a ChatGPT subscription — no API tokens needed.
When it finds bugs, you can let the built-in Developer agent fix and re-test automatically, or just copy the report into Claude Code / Cursor / whatever you use.
It's free and MIT licensed. Would love feedback — especially on what you'd want from an AI QA tool.
Demo: https://www.youtube.com/watch?v=4XdG6p-HByM
Nice. It would be great if it could be used with something like Openrouter BYOK, to give more modern flexibility and costs.
Nice idea. I added it now and it's on the latest VSCode extension and also the Github repository (you can add any API key even OpenAI, Anthropic etc, not just OpenRouter) I also added tons of other things like live test updates, copy buttons on all test cards and issue cards (so you can just copy and paste to claude code to fix the given issue) and also a QA report card which is emitted as the final summary of a test which shows you everything that was tested at one place (no need to scroll up) and allows you to even export it as a PDF (all tests performed / their outcome and all issues found) Let me know if there is anything else
Awesome, I'll definitely take a look asap.