window.ai VS gpt-migrate

Window AI (https://windowai.io/) is an attempt to do something like this with a browser extension.

totally agreed that diff projects need to be careful w/ sharing proprietary code w/ third parties.

openai's official stance is that it will never use API calls as training data, and that in my understanding it may retain API call data for up to 30 days for compliance purposes, but that it legally won't store it beyond that (whereas chatgpt convos are meant to be stored and used for training purposes).

as a next step, they could provide a swappable version of the LLM provider using something like https://github.com/imartinez/privateGPT, https://github.com/alexanderatallah/window.ai, etc. would love to have a standard develop here as the community matures around LLM usage

You can actually try out a version of your idea with the sample chat app on windowai.io (will need to grab the extension, the app and the extension work together). In `window.ai` extension, you will want to set the model as `local`, and all call will be routed to `local.ai` for inferencing! <- This enables user of window to test out AI app without incurring any cloud cost :D

Web: https://windowai.io/

To make it even more privacy friendly, why not use https://windowai.io to let the user choose which language model to use?

+1 With Window, the user brings their own AI model and plugs it into the app, so the cost is on the user side, while also giving privacy benefits to the user and removing liabilities for the dev. https://windowai.io/

Also, even if it didn't have it you could use GPT-Migrate (shameless plug) https://github.com/0xpayne/gpt-migrate

GPT-Migrate: Easily migrate your codebase from one framework or language to another [Link].

Migrate code from one language/framework to another. I think this is very cool. Though you have to ensure all copyrights are in place. You cannot simply take a non-commercial code and convert it to something else and use it.

Github