GitHub Repository

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

931 starsTypeScript

Gemma Gem – AI model embedded in a browser – no API keys, no cloud

Name: Gemma Gem – AI model embedded in a browser – no API keys, no cloud
Availability: InStock
Author: ikessler

by ikessler·Apr 6, 2026·156 points·21 comments

Visit Project View on HN

AI Analysis

●●●BangerWizardryZero to One

Local LLM agent with DOM tools running entirely in-browser via WebGPU.

Strengths

•WebGPU inference with zero external API dependencies
•Agent loop can extract as standalone library
•Chain-of-thought reasoning visible in chat overlay

Weaknesses

•Multi-step tool chains unreliable per author admission
•Requires Chrome with WebGPU support, ~500MB model download

Post Description

Gemma Gem is a Chrome extension that loads Google's Gemma 4 (2B) through WebGPU in an offscreen document and gives it tools to interact with any webpage: read content, take screenshots, click elements, type text, scroll, and run JavaScript.

You get a small chat overlay on every page. Ask it about the page and it (usually) figures out which tools to call. It has a thinking mode that shows chain-of-thought reasoning as it works.

It's a 2B model in a browser. It works for simple page questions and running JavaScript, but multi-step tool chains are unreliable and it sometimes ignores its tools entirely. The agent loop has zero external dependencies and can be extracted as a standalone library if anyone wants to experiment with it.