Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

github.com

Post reply on HN
Print view View original

1–10 of 33 posts

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

#1

Post by ikessler »

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.

Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud
github.com

Re: Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud

#2

Post by avaer »

There's also the Prompt API, currently in Origin Trial, which supports this api surface for sites:

https://developer.chrome.com/docs/ai/prompt-api

I just checked the stats:

  Model Name: v3Nano
  Version: 2025.06.30.1229
  Backend Type: GPU (highest quality)
  Folder size: 4,072.13 MiB
Different use case but a similar approach.

I expect that at some point this will become a native web feature, but not anytime soon, since the model download is many multiples the size of the browser itself. Maybe at some point these APIs could use LLMs built into the OS, like we do for graphics drivers.

Re: Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud

#4

Post by emregucerr »

I would love to see someone build it as some kind of an SDK. App builders could use it as a local LLM plugin when dealing with data involving sensitive information.

It's usually too much when an app asks someone to setup a local LLM but this I believe could solve that problem?

Re: Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud

#6

Post by winstonp »

emregucerr wrote: post #4

I would love to see someone build it as some kind of an SDK. App builders could use it as a local LLM plugin when dealing with data involving sensitive information. It's usually too much when an app asks someone to setup a local LLM but this I believe could solve that problem?

Which apps have you seen ask for someone to setup a local LLM? Can't recall having ever seen one

Re: Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud

#7

Post by oyebenny »

avaer wrote: post #2

There's also the Prompt API, currently in Origin Trial, which supports this api surface for sites: https://developer.chrome.com/docs/ai/prompt-api I just checked the stats: Model Name: v3Nano Version: 2025.06.30.1229 Backend Type: GPU (highest quality) Folder size: 4,072.13 MiB Different use case but a similar approach. I expect that at some point this will become a native web feature, but not anytime soon, since the…

Interesting!

Re: Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud

#8

Post by sheept »

avaer wrote: post #2

There's also the Prompt API, currently in Origin Trial, which supports this api surface for sites: https://developer.chrome.com/docs/ai/prompt-api I just checked the stats: Model Name: v3Nano Version: 2025.06.30.1229 Backend Type: GPU (highest quality) Folder size: 4,072.13 MiB Different use case but a similar approach. I expect that at some point this will become a native web feature, but not anytime soon, since the…

The Summarizer API is already shipped, and any website can use it to quietly trigger a 2 GB download by simply calling

    Summarizer.create()
(requires user activation)

Re: Show HN: Gemma Gem – AI model embedded in a browser – no API keys, no cloud

#10

Post by veunes »

It’s a neat idea, but giving a 2B model full JS execution privileges on a live page is a bit sketchy from a security standpoint. Plus, why tie inference to the browser lifecycle at all? If Chrome crashes or the tab gets discarded, your agent's state is just gone. A local background daemon with a "dumb" extension client seems way more predictable and robust fwiw
Post reply on HN