Key Features
No-Code Browser Automation
Provide a URL and an instruction in plain English. The agent handles navigation, clicking, typing, and extraction, all from a visual workflow builder.
AI Agent Modes
Choose between CUA (vision-based), DOM (selector-based), or Hybrid mode depending on your use case and performance needs.
Built-in Browser Features
Advanced stealth mode, residential proxies, automatic captcha solving, ad blocking, session recording, and multi-region support out of the box.
400+ Integration Ecosystem
Chain browser automation results with n8n’s extensive node library. Send extracted data to Slack, store it in Google Sheets, trigger webhooks, and more.
Agent Modes
The node supports three modes that determine how the agent interacts with web pages:| Mode | Description | Best For |
|---|---|---|
| CUA | Computer Use Agent, uses vision and screen coordinates | Complex UIs, visual interactions, dynamic content |
| DOM | Uses DOM selectors, works with any LLM | Speed, simple pages, structured content |
| Hybrid | Combines vision and DOM approaches | Fallback reliability, mixed content types |
Model Configuration
The Browserbase Agent node requires two model selections:- Driver Model: Powers the browser session (navigation, DOM interactions)
- Agent Model: Orchestrates the high-level task execution
What You Can Build
- Data extraction pipelines: Scrape product prices, news headlines, or job listings and pipe them into databases or spreadsheets
- Form automation: Fill out and submit forms across multiple sites as part of a larger workflow
- Competitive monitoring: Track competitor pricing, features, or content changes on a schedule
- Lead enrichment: Visit company websites to gather contact info, tech stacks, or social profiles
- Automated testing: Validate web flows and capture results alongside your CI/CD pipeline