On-Device/Local LLM Option

Would love for there to be an option to use local models for our avatars' quips and for event reminder text, like what Apple Intelligence does, or maybe Ollama if you do a desktop integration. (Although from what I know of it, I don't know how many people would have the GPU to run their models.)

Alternatively, more transparency in-app about where our data is going and how it's being processed would be great! I'd like the guarantee that my calendar isn't being used as part of training data or something similar. Thank you!