• Picks
  • Discover
  • Alternatives
  • About

© 2026 Willet

  • Newsletter
  • About
  • FAQ
  • Terms
  • Privacy & Cookies
Join the Discord (opens in a new tab)
google-gemini avatar

Computer Use Preview

Reference browser agent driven by Gemini's computer use models

  • Agent frameworks and tools
  • Developer tools
View on GitHub

What it is

A Python command-line sample that lets a Gemini model operate a Chrome browser from a natural-language request, taking screenshots and issuing clicks and keystrokes. It runs the browser locally through Playwright or remotely on Browserbase, and can authenticate through the Gemini Developer API or through Vertex AI. Developers exploring Gemini's computer use capability can study it as a starting point for their own browser-controlling agents.

Images

Facts

Stars
3,235 GitHub stars.
3,235

Forks
406
Commits
35
Contributors
13
Language
Python
License
Apache-2.0
Last commit
Jul 28, 2026
On GitHub since
May 2025
Platforms
CLI
Self-hostable
No
Tags
  • browser-automation
  • ai-agents
  • computer-use

Last synced from GitHub on Oct 20, 2026

The 10 best overlooked open-source projects, every Monday.

Share and more

Comments

No comments yet. Start the conversation.

Similar projects

  • Browser Use avatar

    Browser Use

    Python library that lets LLM agents drive a web browser to finish tasks

    119k
  • Bytedance Inc. avatar

    UI-TARS-desktop

    Multimodal GUI agent stack that operates your desktop and browser

    39.3k
  • LJQ avatar

    GenericAgent

    Minimal agent that controls your computer and saves solved tasks as skills

    14.3k