agent-browser

agent-browser

Vercel Labs
+
+

Related Products

  • Gemini Enterprise Agent Platform
    1,161 Ratings
    Visit Website
  • Gemini Credit Card
    2 Ratings
    Visit Website
  • Evertune
    1 Rating
    Visit Website
  • Google Workspace
    69,271 Ratings
    Visit Website
  • Creatio
    589 Ratings
    Visit Website
  • HubSpot AEO
    151 Ratings
    Visit Website
  • Apify
    1,800 Ratings
    Visit Website
  • Kitecyber
    87 Ratings
    Visit Website
  • Bright Data
    1,430 Ratings
    Visit Website
  • AthenaHQ
    50 Ratings
    Visit Website

About

Gemini Computer Use is a built-in capability in Gemini 3.5 Flash that helps developers build agents that can interact with browser, mobile, and desktop environments. The feature allows agents to see, reason, and take action across platforms, making it useful for long-horizon automation and enterprise workflows. Previously available as a standalone Gemini 2.5 computer use model, computer use is now integrated directly into the main Gemini Flash model. Developers can use it through the Gemini API and Gemini Enterprise Agent Platform to build custom agents for tasks such as software testing and professional application workflows. Gemini Computer Use also includes safety measures such as targeted adversarial training, optional user confirmation for sensitive actions, and task stopping when indirect prompt injection is detected. Gemini Computer Use helps teams create safer, more capable AI agents that can operate across digital environments with stronger reliability and control.

About

agent-browser is a browser automation CLI designed specifically for AI agents, with compact text output that minimizes context usage and a 100% native Rust architecture. Its agent-first approach uses concise output instead of verbose JSON, helping reduce token consumption during browser automation. The snapshot command returns an accessibility tree where every interactive element receives a unique reference, allowing agents to select elements deterministically without repeatedly querying the DOM. More than 50 commands cover navigation, forms, screenshots, network activity, storage, files, tabs, frames, and debugging. Built-in observability features include video recording, streaming, debugging, profiling, and page diffing, while dedicated workflows support modern applications through network control, React and Web Vitals analysis, init scripts, and Next.js and Vercel integrations.

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Supported
Mac Supported
Linux Supported
Cloud Not Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

Gemini Computer Use is best suited for developers, enterprises, AI teams, automation engineers, QA teams, product teams, and organizations that need agentic computer use, browser automation, mobile and desktop interaction, software testing, enterprise workflow automation, secure agent controls, and Gemini API integration

Audience

AI developers and agent builders seeking to automate browser interactions efficiently through deterministic, context-efficient command-line workflows

Support

Phone Support Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Supported
Online Supported

API

Offers API Not Supported

API

Offers API Not Supported

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Free Version Supported
Free Trial Not Supported

Pricing

Free
Free Version Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation Supported
Webinars Supported
Live Online Supported
In Person Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Company Information

Google
Founded: 1998
United States
gemini.google.com

Company Information

Vercel Labs
Founded: 2015
United States
agent-browser.dev/

Alternatives

Alternatives

Lux

Lux

OpenAGI Foundation
Agent S

Agent S

Simular

Categories

Agentic AI Supported
AI Agents Supported
Browser Automation Supported

Categories

Agentic AI Supported
Browser Automation Supported

Integrations

Chrome DevTools Not Supported
Gemini Supported
Gemini 3.5 Flash Supported
Gemini 3.5 Flash Cyber Supported
Gemini 3.5 Flash-Lite Supported
Gemini 3.6 Flash Supported
Gemini 3.7 Flash Supported
Gemini 3.8 Flash Supported
Gemini 3.8 Flash Cyber Supported
Gemini 4 Argon Supported
Gemini Enterprise Supported
Gemini Enterprise Agent Platform Supported
Google AI Studio Supported
Next.js Not Supported
Rust Not Supported
Vercel Not Supported

Integrations

Chrome DevTools Supported
Gemini Not Supported
Gemini 3.5 Flash Not Supported
Gemini 3.5 Flash Cyber Not Supported
Gemini 3.5 Flash-Lite Not Supported
Gemini 3.6 Flash Not Supported
Gemini 3.7 Flash Not Supported
Gemini 3.8 Flash Not Supported
Gemini 3.8 Flash Cyber Not Supported
Gemini 4 Argon Not Supported
Gemini Enterprise Not Supported
Gemini Enterprise Agent Platform Not Supported
Google AI Studio Not Supported
Next.js Supported
Rust Supported
Vercel Supported
Claim Gemini Computer Use and update features and information
Claim Gemini Computer Use and update features and information
Claim agent-browser and update features and information
Claim agent-browser and update features and information