Gemini Chrome AI - Offline is an open-source Chrome extension that allows you to use Google Gemini AI capabilities offline, directly in your Chrome browser. The extension is built on the Prompt API, which is part of the Built-in AI Early Preview Program by Google Chrome.
This project is based on the proof of concept from kseth's kharms project.
The extension utilizes the Prompt API, which is part of the Built-in AI Early Preview Program by Google Chrome.
The extension icon is based on the UI Icon by Freepik from Flaticon.
chrome://flags/#optimization-guide-on-device-model
Enabled BypassPerfRequirement
"chrome://flags/#prompt-api-for-gemini-nano
Enabled
"chrome://components/
- You'll want to see the "Optimization Guide On Device Model
" - Click
on "Check for update
" and update the component.Relaunch Chrome for the changes to take effect.
Install the Gemini Chrome AI - Offline extension (installation instructions to be added).
This project is still in development. Features and functionality may change as the project evolves.
We welcome contributions! Please feel free to submit issues, feature requests, or pull requests.
git clone
npm install
npm run dev:chrome
chrome://extensions/
and enable Developer mode. Click on "Load
unpacked" and select the build/chrome
folder in the project directory.This project is licensed under the MIT License. For more information, please see the LICENSE file.
This extension is not officially associated with Google, the Gemini AI team, or the Chrome team. It is an independent project based on publicly available APIs and information.