agent-browser-0-2-0A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Install via ClawdBot CLI:
clawdbot install Knightluozichu/agent-browser-0-2-0Requires:
npm install -g agent-browser
agent-browser install
agent-browser install --with-depsgit clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
agent-browser installagent-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 browseragent-browser open agent-browser snapshot -i (returns elements with refs like @e1, @e2)agent-browser open <url> # Navigate to URL
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browseragent-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 selectoragent-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
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
agent-browser scroll down 500 # Scroll page
agent-browser scrollintoview @e1 # Scroll element into view
agent-browser drag @e1 @e2 # Drag and drop
agent-browser upload @e1 file.pdf # Upload filesagent-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 boxagent-browser is visible @e1 # Check if visible
agent-browser is enabled @e1 # Check if enabled
agent-browser is checked @e1 # Check if checkedagent-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 PDFagent-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 recordingRecording 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.
agent-browser wait @e1 # Wait for element
agent-browser wait 2000 # Wait milliseconds
agent-browser wait --text "Success" # Wait for text
agent-browser wait --url "/dashboard" # Wait for URL pattern
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --fn "window.ready" # Wait for JS conditionagent-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 wheelagent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find first ".item" click
agent-browser find nth 2 "a" textagent-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
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
agent-browser set media dark # Emulate color schemeagent-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 allagent-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 requestsagent-browser tab # List tabs
agent-browser tab new [url] # New tab
agent-browser tab 2 # Switch to tab
agent-browser tab close # Close tab
agent-browser window new # New windowagent-browser frame "#iframe" # Switch to iframe
agent-browser frame main # Back to main frameagent-browser dialog accept [text] # Accept dialog
agent-browser dialog dismiss # Dismiss dialogagent-browser eval "document.title" # Run JavaScriptagent-browser state save auth.json # Save session state
agent-browser state load auth.json # Load saved stateagent-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 "user@example.com"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i # Check result# 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/dashboardagent-browser --session test1 open site-a.com
agent-browser --session test2 open site-b.com
agent-browser session listAdd --json for machine-readable output:
agent-browser snapshot -i --json
agent-browser get text @e1 --jsonagent-browser open example.com --headed # Show browser window
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 from current page
agent-browser record stop # Save recording
agent-browser --cdp 9222 snapshot # Connect via CDPGenerated Mar 1, 2026
This scenario involves using the agent-browser to automate the filling and submission of web forms, such as contact forms, registration pages, or online applications. It leverages commands like 'fill', 'click', and 'wait' to interact with form elements, extract data, and handle navigation, making it ideal for repetitive data entry tasks.
In this scenario, the agent-browser navigates e-commerce websites to extract structured product information like prices, descriptions, and availability. It uses 'snapshot' to analyze page elements, 'get text' to retrieve data, and 'scroll' to load dynamic content, enabling efficient inventory monitoring or price comparison.
This scenario applies the agent-browser for automated testing of web interfaces, including checking interactive elements, verifying page states, and capturing screenshots. Commands like 'is visible', 'click', and 'screenshot' help validate functionality and visual consistency, reducing manual testing efforts.
Here, the agent-browser automates tasks on social media platforms, such as posting content, liking posts, or navigating feeds. It uses 'type', 'click', and 'wait' to simulate user actions, with 'record' for creating demo videos, useful for social media management or analytics.
This scenario involves scraping financial data from banking or investment sites, using agent-browser to log in, navigate statements, and extract transaction details. It employs 'set credentials' for authentication, 'get' commands for data retrieval, and 'pdf' for saving reports, aiding in financial analysis.
Offer a cloud-based service where users access agent-browser via an API to automate web tasks like data extraction or form filling. Revenue is generated through subscription tiers based on usage volume, with additional fees for premium features like video recording or advanced analytics.
Provide consulting services to businesses for integrating agent-browser into their workflows, such as automating internal processes or building custom scripts. Revenue comes from project-based fees, ongoing support contracts, and training sessions for teams to leverage the tool effectively.
Run an agency that uses agent-browser to automate marketing tasks like lead generation, social media management, and ad testing for clients. Revenue is earned through service packages, performance-based pricing, and upselling additional automation solutions to improve client campaigns.
💬 Integration Tip
Start by installing via npm and testing with simple commands like 'open' and 'snapshot' to familiarize with the workflow, then gradually incorporate interactions and waits for more complex automations.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection