Offline GPT is made possible thanks to the amazing folks at WebLLM, a project which brings Local LLMs to the web browser, accelerated with WebGPU, and of course, the whole community of open-source LLMs and AI enthusiasts.
Offline GPT downloads a small large language model that stays cached in your browser, allowing you to chat with the AI on your local machine, even without an internet connection.
This also means that your privacy is guaranteed, as your conversation never leaves your device. What's between you and the bot, stays between you and the bot.
If you enjoy the project and are interested in more stuff about LLMs, follow me on Twitter for more updates on it and other cool projects.