agent-browser

Name: agent-browser
Author: Vercel Engineering

browser automationweb scrapingweb testingdata extractionform fillingweb interactionautomationAI agent

⭐ 36.2k📄 Apache-2.0🕒 2026-06-16Source ↗

Install this skill

npx skills add vercel-labs/agent-browser

Works across Claude Code, Cursor, Codex, Copilot & Antigravity

agent-browser is a CLI tool built by Vercel Labs that provides a programmatic interface for interacting with web pages. It functions by mapping DOM elements to unique identifiers (refs like @e1, @e2), allowing autonomous agents to navigate, fill forms, click buttons, and extract data with high precision. Instead of relying on brittle coordinate-based automation, it generates accessibility snapshots that translate complex web interfaces into machine-readable structures. The tool handles standard browser lifecycle tasks, such as managing cookies, waiting for network transitions, and capturing visual state through screenshots or recordings. It simplifies the bridge between large language models and the live web, making it a foundation for tasks requiring browser-based reasoning, data extraction, or automated verification in isolated, headless, or remote browser environments.

When to Use This Skill

•Automating multi-step registration or form submission flows
•Extracting structured data from modern dynamic web applications
•Generating video evidence for automated test failures
•Performing functional end-to-end testing on web interfaces

How to Invoke This Skill

Example prompts that trigger this skill in Claude Code, Cursor, or Antigravity:

“Navigate to this website and extract the pricing table
“Fill out the login form using these specific credentials
“Wait for the dashboard to load then take a screenshot
“Find the submit button by its label and click it
“Record a video of the checkout process

Pro Tips

💡Always use `agent-browser snapshot -i` after significant page changes or navigation to get updated element references (`@e1`, `@e2`), ensuring reliable interactions.
💡Combine `agent-browser` with other data processing skills to refine extracted information, such as parsing JSON or cleaning text for further analysis.
💡When dealing with dynamic content or waiting for elements to load, implement retry logic or explicit waits in your agent's workflow to enhance robustness and prevent failures.

What this skill does

•Map DOM elements to unique, stable refs for precise interaction
•Perform complex input operations like form filling and drag-and-drop
•Monitor page state with conditional waits, visibility checks, and attribute extraction
•Capture visual output via full-page screenshots, PDFs, and video recording
•Execute semantic searches based on ARIA roles, labels, and text content

When not to use it

✕Highly complex, Canvas-heavy games or advanced 3D visualizers
✕Scenarios requiring deep integration with native OS-level browser extensions
✕Bypassing sophisticated anti-bot fingerprinting services

Example workflow

Open the target URL using agent-browser open
Execute agent-browser snapshot -i to identify input refs
Fill the target fields using agent-browser fill @e1
Perform agent-browser click @e2 to submit
Verify navigation success by checking the current URL

Prerequisites

–Node.js environment
–Local browser installation (Chromium/Chrome)

Pitfalls & limitations

!Relies on DOM structure, so pages with heavy dynamic class obfuscation may require frequent re-snapshotting
!Wait times must be manually configured for complex network-heavy loads
!Lacks native high-level reasoning; expects the user or agent to provide the interaction logic

FAQ

How do I ensure I am clicking the correct element?

Use the snapshot command with the -i flag to see the list of interactive elements, then cross-reference the element type and label provided in the output.

Can it handle pages that load content dynamically?

Yes, use the wait command with options like --load networkidle or a specific CSS selector to pause execution until the page state stabilizes.

How does this differ from standard Playwright or Puppeteer?

This tool provides a simplified, command-line-first abstraction layer that is easier for LLMs to trigger than native scripts written in JavaScript or Python.

Can I use it to record my sessions?

Yes, use agent-browser record start [filename] to begin capturing the session, perform your actions, and use record stop to save the output.

How it compares

Unlike manual browsing which requires human visual feedback, or raw Playwright/Puppeteer scripts which require deep coding knowledge, this tool provides a command-driven bridge that allows non-developers to orchestrate complex web workflows through structured, human-readable commands.

Source & trust

⭐ 36k stars📄 Apache-2.0🕒 Updated 2026-06-16

View original skill on GitHub →

📄 Full skill instructions — original source: vercel-labs/agent-browser

# Browser Automation with agent-browser

## Quick start

agent-browser open <url>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

## Core workflow

1. Navigate: agent-browser open <url>
2. Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
3. Interact using refs from the snapshot
4. Re-snapshot after navigation or significant DOM changes

## Commands

### Navigation

agent-browser open <url>      # Navigate to URL (aliases: goto, navigate)
                              # Supports: https://, http://, file://, about:, data://
                              # Auto-prepends https:// if no protocol given
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser (aliases: quit, exit)
agent-browser connect 9222    # Connect to browser via CDP port

### Snapshot (page analysis)

agent-browser snapshot            # Full accessibility tree
agent-browser snapshot -i         # Interactive elements only (recommended)
agent-browser snapshot -c         # Compact output
agent-browser snapshot -d 3       # Limit depth to 3
agent-browser snapshot -s "#main" # Scope to CSS selector

### Interactions (use @refs from snapshot)

agent-browser click @e1           # Click
agent-browser dblclick @e1        # Double-click
agent-browser focus @e1           # Focus element
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing
agent-browser press Enter         # Press key (alias: key)
agent-browser press Control+a     # Key combination
agent-browser keydown Shift       # Hold key down
agent-browser keyup Shift         # Release key
agent-browser hover @e1           # Hover
agent-browser check @e1           # Check checkbox
agent-browser uncheck @e1         # Uncheck checkbox
agent-browser select @e1 "value"  # Select dropdown option
agent-browser select @e1 "a" "b"  # Select multiple options
agent-browser scroll down 500     # Scroll page (default: down 300px)
agent-browser scrollintoview @e1  # Scroll element into view (alias: scrollinto)
agent-browser drag @e1 @e2        # Drag and drop
agent-browser upload @e1 file.pdf # Upload files

### Get information

agent-browser get text @e1        # Get element text
agent-browser get html @e1        # Get innerHTML
agent-browser get value @e1       # Get input value
agent-browser get attr @e1 href   # Get attribute
agent-browser get title           # Get page title
agent-browser get url             # Get current URL
agent-browser get count ".item"   # Count matching elements
agent-browser get box @e1         # Get bounding box
agent-browser get styles @e1      # Get computed styles (font, color, bg, etc.)

### Check state

agent-browser is visible @e1      # Check if visible
agent-browser is enabled @e1      # Check if enabled
agent-browser is checked @e1      # Check if checked

### Screenshots & PDF

agent-browser screenshot          # Screenshot to stdout
agent-browser screenshot path.png # Save to file
agent-browser screenshot --full   # Full page
agent-browser pdf output.pdf      # Save as PDF

### Video recording

agent-browser record start ./demo.webm    # Start recording (uses current URL + state)
agent-browser click @e1                   # Perform actions
agent-browser record stop                 # Stop and save video
agent-browser record restart ./take2.webm # Stop current + start new recording

Recording creates a fresh context but preserves cookies/storage from your session. If no URL is provided, it
automatically returns to your current page. For smooth demos, explore first, then start recording.

### Wait

agent-browser wait @e1                     # Wait for element
agent-browser wait 2000                    # Wait milliseconds
agent-browser wait --text "Success"        # Wait for text (or -t)
agent-browser wait --url "**/dashboard"    # Wait for URL pattern (or -u)
agent-browser wait --load networkidle      # Wait for network idle (or -l)
agent-browser wait --fn "window.ready"     # Wait for JS condition (or -f)

### Mouse control

agent-browser mouse move 100 200      # Move mouse
agent-browser mouse down left         # Press button
agent-browser mouse up left           # Release button
agent-browser mouse wheel 100         # Scroll wheel

### Semantic locators (alternative to refs)

agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find text "Sign In" click --exact      # Exact match only
agent-browser find label "Email" fill "[email protected]"
agent-browser find placeholder "Search" type "query"
agent-browser find alt "Logo" click
agent-browser find title "Close" click
agent-browser find testid "submit-btn" click
agent-browser find first ".item" click
agent-browser find last ".item" click
agent-browser find nth 2 "a" hover

### Browser settings

agent-browser set viewport 1920 1080          # Set viewport size
agent-browser set device "iPhone 14"          # Emulate device
agent-browser set geo 37.7749 -122.4194       # Set geolocation (alias: geolocation)
agent-browser set offline on                  # Toggle offline mode
agent-browser set headers '{"X-Key":"v"}'     # Extra HTTP headers
agent-browser set credentials user pass       # HTTP basic auth (alias: auth)
agent-browser set media dark                  # Emulate color scheme
agent-browser set media light reduced-motion  # Light mode + reduced motion

### Cookies & Storage

agent-browser cookies                     # Get all cookies
agent-browser cookies set name value      # Set cookie
agent-browser cookies clear               # Clear cookies
agent-browser storage local               # Get all localStorage
agent-browser storage local key           # Get specific key
agent-browser storage local set k v       # Set value
agent-browser storage local clear         # Clear all

### Network

agent-browser network route <url>              # Intercept requests
agent-browser network route <url> --abort      # Block requests
agent-browser network route <url> --body '{}'  # Mock response
agent-browser network unroute [url]            # Remove routes
agent-browser network requests                 # View tracked requests
agent-browser network requests --filter api    # Filter requests

### Tabs & Windows

agent-browser tab                 # List tabs
agent-browser tab new [url]       # New tab
agent-browser tab 2               # Switch to tab by index
agent-browser tab close           # Close current tab
agent-browser tab close 2         # Close tab by index
agent-browser window new          # New window

### Frames

agent-browser frame "#iframe"     # Switch to iframe
agent-browser frame main          # Back to main frame

### Dialogs

agent-browser dialog accept [text]  # Accept dialog
agent-browser dialog dismiss        # Dismiss dialog

### JavaScript

agent-browser eval "document.title"   # Run JavaScript

## Global options

agent-browser --session <name> ...    # Isolated browser session
agent-browser --json ...              # JSON output for parsing
agent-browser --headed ...            # Show browser window (not headless)
agent-browser --full ...              # Full page screenshot (-f)
agent-browser --cdp <port> ...        # Connect via Chrome DevTools Protocol
agent-browser --proxy <url> ...       # Use proxy server
agent-browser --headers <json> ...    # HTTP headers scoped to URL's origin
agent-browser --executable-path <p>   # Custom browser executable
agent-browser --extension <path> ...  # Load browser extension (repeatable)
agent-browser --help                  # Show help (-h)
agent-browser --version               # Show version (-V)
agent-browser <command> --help        # Show detailed help for a command

### Proxy support

agent-browser --proxy http://proxy.com:8080 open example.com
agent-browser --proxy http://user:[email protected]:8080 open example.com
agent-browser --proxy socks5://proxy.com:1080 open example.com

## Environment variables

AGENT_BROWSER_SESSION="mysession"            # Default session name
AGENT_BROWSER_EXECUTABLE_PATH="/path/chrome" # Custom browser path
AGENT_BROWSER_EXTENSIONS="/ext1,/ext2"       # Comma-separated extension paths
AGENT_BROWSER_STREAM_PORT="9223"             # WebSocket streaming port
AGENT_BROWSER_HOME="/path/to/agent-browser"  # Custom install location (for daemon.js)

## Example: Form submission

agent-browser open https://example.com/form
agent-browser snapshot -i
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]

agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

## Example: Authentication with saved state

# Login once
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "username"
agent-browser fill @e2 "password"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json

# Later sessions: load saved state
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard

## Sessions (parallel browsers)

agent-browser --session test1 open site-a.com
agent-browser --session test2 open site-b.com
agent-browser session list

## JSON output (for parsing)

Add --json for machine-readable output:

agent-browser snapshot -i --json
agent-browser get text @e1 --json

## Debugging

agent-browser --headed open example.com   # Show browser window
agent-browser --cdp 9222 snapshot         # Connect via CDP port
agent-browser connect 9222                # Alternative: connect command
agent-browser console                     # View console messages
agent-browser console --clear             # Clear console
agent-browser errors                      # View page errors
agent-browser errors --clear              # Clear errors
agent-browser highlight @e1               # Highlight element
agent-browser trace start                 # Start recording trace
agent-browser trace stop trace.zip        # Stop and save trace
agent-browser record start ./debug.webm   # Record video from current page
agent-browser record stop                 # Save recording

## Deep-dive documentation

For detailed patterns and best practices, see:

| Reference | Description |
|-----------|-------------|
| [references/snapshot-refs.md](references/snapshot-refs.md) | Ref lifecycle, invalidation rules, troubleshooting |
| [references/session-management.md](references/session-management.md) | Parallel sessions, state persistence, concurrent scraping |
| [references/authentication.md](references/authentication.md) | Login flows, OAuth, 2FA handling, state reuse |
| [references/video-recording.md](references/video-recording.md) | Recording workflows for debugging and documentation |
| [references/proxy-support.md](references/proxy-support.md) | Proxy configuration, geo-testing, rotating proxies |

## Ready-to-use templates

Executable workflow scripts for common patterns:

| Template | Description |
|----------|-------------|
| [templates/form-automation.sh](templates/form-automation.sh) | Form filling with validation |
| [templates/authenticated-session.sh](templates/authenticated-session.sh) | Login once, reuse state |
| [templates/capture-workflow.sh](templates/capture-workflow.sh) | Content extraction with screenshots |

Usage:

./templates/form-automation.sh https://example.com/form
./templates/authenticated-session.sh https://app.example.com/login
./templates/capture-workflow.sh https://example.com ./output

By Vercel Engineering

How to Use This Skill Unit

Option A: Project-Specific (Recommended)

Click "Download" above
In your project, create the directory: .agent/skills/agent-browser/
Save the file as SKILL.md
The agent will automatically discover the skill based on its description.

Option B: Global Installation (All Agents)

Save the file to these locations to make it available across all projects:

Claude Code: ~/.claude/skills/vercel-labs/agent-browser/agent-browser/SKILL.md
Cursor: ~/.cursor/skills/vercel-labs/agent-browser/agent-browser/SKILL.md
Antigravity: ~/.gemini/antigravity/skills/vercel-labs/agent-browser/agent-browser/SKILL.md

🚀 Install with CLI:
npx skills add vercel-labs/agent-browser

Read the Master Guide: Mastering Agent Skills →

Recommended Rules

View more rules →

Recommended Workflows

View more workflows →

Automatic commit message generator

GitAIAutomation

--- description: Automatic commit message generator and fast AI-powered commit for all current changes --- // turbo-all This workflow automatically ...

Setup Husky Git Hooks

GitAutomationQuality

--- description: Automate code quality checks with pre-commit and pre-push hooks --- 1. **Install Husky**: - Install husky and lint-staged. // ...

Setup Vercel Cron Jobs

VercelCronAutomation

--- description: Create and test scheduled tasks in Next.js --- 1. **Create Cron Config**: - Add `crons` to `vercel.json`. ```json { "c...

Recommended MCP Servers

View more MCP servers →

Hyperbrowser

Official

[Hyperbrowser](https://www.hyperbrowser.ai/) is the next-generation platform empowering AI agents and enabling effortless, scalable browser automation.

Playwright

Official

— Browser automation MCP server using Playwright to run tests, navigate pages, capture screenshots, scrape content, and automate web interactions reliably.