First of all, great job creating this and opening yourself up to feedback by sharing here.

How opinionated are the answers? In the screenshot example, the AI favors DRY and SOLID code - which are not necessarily things I value as much for small, personal projects. Is it possible to configure the type of review it provides?

Hi thanks for the feedback! It’s opinionated since it specifies those principles in the prompt. However I should probably make the prompt more extensible. I do have a prompt class with the prompt in there for anyone to edit ofc.

Can you add instructions on how one can run this on local instead of Colab? Cool project BTW!

Absolutely, I'll add llama.cpp support soon.