nowfound

AI · April 6, 2026

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

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…

Gemma Gem – AI model embedded in a browser – no API keys, no cloud launched on April 6, 2026 with 156 votes, #202 of 21,248 launches that month and more than 95% of that year's launches.

Visit github.com ↗Alternativestop 1% of April 2026

In plain words

Gemma Gem is a Chrome extension that runs Google's Gemma 4 language model locally in the browser using WebGPU, with no API keys or cloud required. It provides a chat overlay on webpages and can read page content, take screenshots, click elements, type text, scroll, and run JavaScript based on user requests. The extension includes a thinking mode that displays its reasoning process. It handles simple page questions and JavaScript execution well, though multi-step interactions and tool use can be unreliable.

written from the facts on this page · September 2026

From the sources

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

Your personal AI assistant living right inside the browser. Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine. It can read pages, click buttons, fill forms, run JavaScript, and answer questions about any site you visit. pnpm install pnpm build Load the extension in chrome://extensions (developer mode) from .output/chrome-mv3-dev/ . Offscreen Document Service Worker Content Script (Gemma 4 + Agent Loop) <-> (Message Router) <-> (Chat UI + DOM Tools) | | WebGPU inference Screenshot capture Token streaming JS execution Offscreen document : Hosts the model via @huggingface/transformers + WebGPU. Runs the agent loop. Service…from github.com

In the maker’s words, at launch

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…

Does a similar job

all alternatives →
  • Gemma2024 · deepmind.google · ▲259

    Google’s new state-of-the-art open source LLMs

  • Gemma 22024 · blog.google · ▲279

    Lightweight, state-of-the-art open models from Google

  • Google Gemma 4Apr 2026 · blog.google · ▲437

    Google's most intelligent open models to date

  • Gemma 32025 · deepmind.google · ▲200

    Build with multimodal AI from Google

  • Cactus Hybrid: We taught Gemma 4 to know when it's wrongJul 2026 · github.com · ▲191

    Hey HN, Henry & Roman here from Cactus. A small, on-device model is fast and private, but sometimes wrong, but frontier models are getting expensive pretty fast. So, we post-trained Gemma 4 E2B post-trained to know when it's wrong. Every response comes with a confidence score between 0 and 1. Developers can accept the on-device when it's high, hand off to a bigger cloud model when it's low. By routing only 15-35% of queries to Gemini 3.1 Flash-Lite, Gemma-4-E2B matches Gemini 3.1 Flash-Lite on most benchmarks. - ChartQA: 15-20% - LibriSpeech: 25-30% - MMBench, GigaSpeech, MMAU: 30-35% -…

  • Gemma 3n2025 · developers.googleblog.com · ▲199

    Run powerful multimodal AI right on your phone

More ai this month

the category →
  • Video model that turns script into viral social media videos

    AI · 17d ago · spira.ai

  • The browser where Claude Code and Codex work beside you

    AI · 16d ago · rill.love

  • Kolibri is Aleph Alpha

    AI · 18d ago · tej.as

  • Paintings by AI models: programs run through a simulation of oil paint.

    AI · 20d ago · stillwet.art

  • Onepin▲384

    AI voiceover with every name, price and date said right

    AI · 30d ago · onepin.ai

  • A real-time world model you can explore and change

    AI · 28d ago · world.pixverse.video

Source: Show HN post ↗ · launch text quoted in part

Launched alongside, April 2026

the whole month →
  • Brila▲1,364

    One-page websites from real Google Maps reviews

    AI · Apr 2026 · brila.ai

  • AG

    Thought the resources for GPU arch were lacking, so here we are

    Life & fun · Apr 2026 · jaso1024.com

  • Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

    AI · Apr 2026 · github.com

  • AI meeting notes: now bot-free, in ChatGPT & Claude + more

    AI · Apr 2026 · fathom.ai

  • I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay

    Life & fun · Apr 2026 · sam-burns.com

  • With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https:&#x2F;&#x2F;text.blogosphere.app&#x2F; Non-minimal: https:&#x2F;&#x2F;blogosphere.app&#x2F; If you don't find your blog (or your favorite ones), please add them. I will review and approve it.

    AI · Apr 2026 · text.blogosphere.app