Hello! I didn't realise my project was posted here but I can actually answer this.

I do use LLM's (specifically Ollama) particularly for test summarisation, writing up some boilerplate and also I've used Claude/Chatgpt on the web when my free tier allows. It's good for when I hit problems such as AMD SOP prefixes being different than I expected.

I looked through several of the source files and if you had said it's 100% handrolled I would have believed you too.

It looks like a project made by a human and I mean that in a good way.

since nobody else seems to have said it, this is exciting! keep up the fun work!