I just built an experimental VSCode extension called LLM Debugger. It’s a proof-of-concept that lets a large language model take charge of debugging. Instead of only looking at the static code, the LLM also gets to see the live runtime state—actual variable values, function calls, branch decisions, and more. The idea is to give it enough context to help diagnose issues faster and even generate synthetic data from running programs.

Here’s what it does:

* Active Debugging: It integrates with Node.js debug sessions to gather runtime info (like variable states and stack traces).

* Automated Breakpoints: It automatically sets and manages breakpoints based on both code analysis and LLM suggestions.

* LLM Guidance: With live debugging context, the LLM can suggest actions like stepping through code or adjusting breakpoints in real time.

I built this out of curiosity to see if combining static code with runtime data could help LLMs solve bugs more effectively. It’s rough around the edges and definitely not production-ready

I’m not planning on maintaining it further. But I thought it was a fun experiment and wanted to share it with you all.

Check out the attached video demo to see it in action. Would love to hear your thoughts and any feedback you might have!

Cheers.