Average Ratings 1 Rating
Average Ratings 0 Ratings
Description
Browser Use provides hosted AI agents and remote browser infrastructure for automating work on websites. It helps developers connect software to tasks such as signing into portals, completing forms, collecting information, and downloading documents, especially where no usable API exists.
Browser Use Agents accepts natural-language tasks and operates a managed browser to carry them out. Teams can delegate multi-step website work without building and maintaining their own agent loop. Use cases include cross-site research, authenticated document collection, data extraction, and repetitive portal workflows.
Browser Infrastructure supplies remote Chromium sessions for teams running their own agents, Playwright scripts, or Puppeteer automation. It combines browser stealth, residential proxy options, and automatic handling of supported CAPTCHAs. Developers retain control of their automation logic while Browser Use manages the browsers.
The MIT-licensed browser-use Python library supports running and customizing agents in your own environment with local or cloud browsers. Browser Harness, CLI tools, SDKs, and Model Context Protocol (MCP) interfaces provide additional ways to give existing applications and agents browser capabilities.
Cloud services use pay-as-you-go pricing with no required subscription and no expiry on purchased credits. Browser runtime starts at $0.02/hour; network traffic is charged separately. Hosted agents add model costs and a 20% service fee. Eligible signups receive a one-time $15 cloud credit. The open-source library is free to use, with model and infrastructure costs depending on your setup.
Description
Gemini Computer Use is an agentic computer interaction capability built into Gemini 3.5 Flash. It enables developers and enterprises to create AI agents that can work across browser, desktop, and mobile environments by seeing interfaces, reasoning through tasks, and taking action. The capability was previously offered through a standalone Gemini 2.5 computer use model, but is now natively integrated into Gemini 3.5 Flash. This gives developers access to stronger performance for agentic computer use tasks while also combining with Gemini’s existing strengths in function calling, Search grounding, Maps grounding, and built-in tools. Gemini Computer Use is designed for long-horizon automation, continuous software testing, enterprise knowledge work, and workflows that span multiple professional applications. Developers can start building with the feature through the Gemini API or Gemini Enterprise Agent Platform. Google also provides a demo environment through Browserbase for testing the capability. Safety controls include targeted adversarial training for live-environment risks, optional explicit user confirmation for sensitive or irreversible actions, and automatic task stopping when indirect prompt injection is identified. Gemini Computer Use helps organizations build practical AI agents that can complete complex digital tasks while supporting sandboxing, human review, and strict access controls.
API Access
Has API
Yes
API Access
Has API
No
Integrations
Claude
Yes
Claude Haiku 3
Yes
Claude Opus 3
Yes
GPT-4
Yes
Gemini
No
Gemini 3.5 Flash
No
Gemini 3.5 Flash Cyber
No
Gemini 3.5 Flash-Lite
No
Gemini 3.6 Flash
No
Gemini 3.7 Flash
No
Integrations
Claude
No
Claude Haiku 3
No
Claude Opus 3
No
GPT-4
No
Gemini
Yes
Gemini 3.5 Flash
Yes
Gemini 3.5 Flash Cyber
Yes
Gemini 3.5 Flash-Lite
Yes
Gemini 3.6 Flash
Yes
Gemini 3.7 Flash
Yes
Pricing Details
Pay as you go, no subscription
Browser time: $0.02/hour
Residential proxy traffic: $5/GB
Hosted agents: model cost + 20% fee
Residential proxy traffic: $5/GB
Hosted agents: model cost + 20% fee
Free Trial
Yes
Free Version
Yes
Pricing Details
Free
Free Trial
No
Free Version
Yes
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
Yes
Mac
Yes
Linux
Yes
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
Yes
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
Yes
Live Training (Online)
Yes
In Person
Yes
Vendor Details
Company Name
Browser Use
Founded
2024
Country
United States
Website
browser-use.com
Vendor Details
Company Name
Founded
1998
Country
United States
Website
gemini.google.com
Product Features
Data Extraction
Disparate Data Collection
No
Document Extraction
No
Email Address Extraction
No
IP Address Extraction
No
Image Extraction
No
Phone Number Extraction
No
Pricing Extraction
No
Web Data Extraction
No
Data Preparation
Collaboration Tools
No
Data Access
No
Data Blending
No
Data Cleansing
No
Data Governance
No
Data Mashup
No
Data Modeling
No
Data Transformation
No
Machine Learning
No
Visual User Interface
No