Find tools › Open-source projects › Keep data private

pooled

Open-source project · by Nehanth

Run big open-source AI models across your phone, tablet, and laptop browser tabs together.

Some setup294 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Run large open-source models across multiple local devices
  • Chat with shared models in browser rooms
  • Build and test mini applications using Code mode

How to start

  1. Clone the repository to your local machine

  2. Run a local static server like npx -y serve -l 8080 .

  3. Open http://localhost:8080/room in your browser to start a room

Good to know. Requires WebGPU-compatible browsers and devices. Pushed to GitHub over 4 months ago.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-03

More detail

Peer-to-peer LLM inference in the browser, allowing multiple devices to pool resources and run large open models together.

Enables users to run models that require more memory than any single device has by splitting layers across connected phones, laptops, and desktops over WebRTC.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map