Back to directory

RA Browser Use

A Chrome browser-automation agent, forked from Nanobrowser, that runs its model on-device inside the extension by default, so a task in plain language runs with no API key, no cloud call and no page content leaving the browser.

RA Browser Use

RA Browser Use is an openly declared fork of Nanobrowser, a multi-agent browser automation extension, adapted to run its model on-device by default instead of only against a cloud LLM provider or a separately installed Ollama process.

Given a task in plain language, it navigates, clicks, types and extracts data on a Chrome page, with the model executing inside the extension itself through WebAssembly and WebGPU via the RunAnywhere SDK. In this default mode nothing needs to be configured, a model is picked automatically for the user's hardware, no page data leaves the browser, and there is no per-token cost. Cloud providers are still supported for tasks that need a larger model.

Upstream's full commit history is merged rather than squashed, and its live git remote is tracked to pull forward Nanobrowser's own fixes. It is Apache-2.0 licensed and, as of this writing, in early development and not yet released.

More in Browser automation

See all 88
  • Loads an unpacked Chrome extension that lets a local AI coding agent click, type and read the tabs, cookies and logins of a Chrome window you already have open.

  • Hronaut

    hronaut.dev

    A visible, persistent Electron browser that exposes durable, named agent workspaces over MCP, so a coding agent's browser session stays open and inspectable independently of any one AI conversation.

  • Prompt OS

    github.com

    A desktop AI agent for Windows that executes terminal commands, manages files, writes and runs code, browses the web and reads the screen, acting on natural-language requests rather than only answering them.