It enables page reading, button clicking, form filling, JavaScript execution, and question answering through tools like read_page_content, take_screenshot, and click_element. Setup involves pnpm install/build and loading in chrome://extensions; models are E2B (500MB) or E4B (1.5GB).

Topics

Browser AI Gemma Model WebGPU On-Device Inference Chrome Extension

View on GitHub All Bookmarks

Discover Similar Content

William's Bookmark Library

/**/

GitHub - kessler/gemma-gem: Gemma Gem runs Google’s Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

github.comSaved April 6, 20263 min

kessler · via GitHub

Summary

Gemma Gem is a Chrome extension that runs Google's Gemma 4 model on-device via WebGPU, requiring no API keys or cloud.

Topics

Browser AI Gemma Model WebGPU On-Device Inference Chrome Extension

View on GitHub All Bookmarks