GPT doesn't work that way. Any such shell would have to send a GPT request for every single keystroke, and you'd hit the API ratelimit very quickly. It would also be very expensive.

Maybe a solid use case for local models are they're optimized for consumer hardware-- someone clever could preserve as much context as possible between requests

Well, eventually, better models will be made and they can be used locally

Couldn't you just use Fish or zsh-autosuggestions? I don't see the benefit of using a web api or AI for every keystroke when the current solutions work well enough.

I dont want to change from bash to zsh. I don't know what Fish is

I am aware of warp. I guess I could use it but I am looking for something that integrates with gnome-terminal/konsole or iTerm