andrsschultz moves Mike's AI engine in-house
This fork cuts the cords to outside AI services and runs the model on hardware you control.
andrsschultz tore out Mike's connections to the big cloud AI providers - Anthropic's Claude and Google's Gemini - along with the screens where each user pastes in their own provider keys. In their place sits a single client pointed at a model running locally, by default the kind you'd host on your own machine with a tool like Ollama (a popular way to run AI models on local hardware).
The plumbing underneath is well done: it handles streaming replies, step-by-step reasoning from capable models, and multi-round tool use without leaning on any outside service. The trade-off is that this version assumes a local-only setup, so it's built for self-hosting rather than a shared, hosted deployment.
Spotted something wrong? Or know the PR text has fresher detail than the writeup above?