Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Every browser automation follows this pattern:
agent-browser open <url>agent-browser snapshot -i (get element refs like @e1, @e2)agent-browser open https://example.com/form
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"
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
Commands can be chained with && in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.
# Chain open + wait + snapshot in one call
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i
# Chain multiple interactions
agent-browser fill @e1 "[email protected]" && agent-browser fill @e2 "password123" && agent-browser click @e3
# Navigate and capture
agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png
When to chain: Use && when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).
# Navigation
agent-browser open <url> # Navigate (aliases: goto, navigate)
agent-browser close # Close browser
# Snapshot
agent-browser snapshot -i # Interactive elements with refs (recommended)
agent-browser snapshot -i -C # Include cursor-interactive elements (divs with onclick, cursor:pointer)
agent-browser snapshot -s "#selector" # Scope to CSS selector
# Interaction (use @refs from snapshot)
agent-browser click @e1 # Click element
agent-browser click @e1 --new-tab # Click and open in new tab
agent-browser fill @e2 "text" # Clear and type text
agent-browser type @e2 "text" # Type without clearing
agent-browser select @e1 "option" # Select dropdown option
agent-browser check @e1 # Check checkbox
agent-browser press Enter # Press key
agent-browser keyboard type "text" # Type at current focus (no selector)
agent-browser keyboard inserttext "text" # Insert without key events
agent-browser scroll down 500 # Scroll page
agent-browser scroll down 500 --selector "div.content" # Scroll within a specific container
# Get information
agent-browser get text @e1 # Get element text
agent-browser get url # Get current URL
agent-browser get title # Get page title
# Wait
agent-browser wait @e1 # Wait for element
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --url "**/page" # Wait for URL pattern
agent-browser wait 2000 # Wait milliseconds
# Downloads
agent-browser download @e1 ./file.pdf # Click element to trigger download
agent-browser wait --download ./output.zip # Wait for any download to complete
agent-browser --download-path ./downloads open <url> # Set default download directory
# Capture
agent-browser screenshot # Screenshot to temp dir
agent-browser screenshot --full # Full page screenshot
agent-browser screenshot --annotate # Annotated screenshot with numbered element labels
agent-browser pdf output.pdf # Save as PDF
# Diff (compare page states)
agent-browser diff snapshot # Compare current vs last snapshot
agent-browser diff snapshot --baseline before.txt # Compare current vs saved file
agent-browser diff screenshot --baseline before.png # Visual pixel diff
agent-browser diff url <url1> <url2> # Compare two pages
agent-browser diff url <url1> <url2> --wait-until networkidle # Custom wait strategy
agent-browser diff url <url1> <url2> --selector "#main" # Scope to element
agent-browser open https://example.com/signup
agent-browser snapshot -i
agent-browser fill @e1 "Jane Doe"
agent-browser fill @e2 "[email protected]"
agent-browser select @e3 "California"
agent-browser check @e4
agent-browser click @e5
agent-browser wait --load networkidle
# Save credentials once (encrypted with AGENT_BROWSER_ENCRYPTION_KEY)
echo "pass" | agent-browser auth save github --url https://github.com/login --username user --password-stdin
# Login using saved profile (LLM never sees password)
agent-browser auth login github
# List/show/delete profiles
agent-browser auth list
agent-browser auth show github
agent-browser auth delete github
# Login once and save state
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
# Reuse in future sessions
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard
# Auto-save/restore cookies and localStorage across browser restarts
agent-browser --session-name myapp open https://app.example.com/login
# ... login flow ...
agent-browser close # State auto-saved to ~/.agent-browser/sessions/
# Next time, state is auto-loaded
agent-browser --session-name myapp open https://app.example.com/dashboard
# Encrypt state at rest
export AGENT_BROWSER_ENCRYPTION_KEY=$(openssl rand -hex 32)
agent-browser --session-name secure open https://app.example.com
# Manage saved states
agent-browser state list
agent-browser state show myapp-default.json
agent-browser state clear myapp
agent-browser state clean --older-than 7
agent-browser open https://example.com/products
agent-browser snapshot -i
agent-browser get text @e5 # Get specific element text
agent-browser get text body > page.txt # Get all page text
# JSON output for parsing
agent-browser snapshot -i --json
agent-browser get text @e1 --json
agent-browser --session site1 open https://site-a.com
agent-browser --session site2 open https://site-b.com
agent-browser --session site1 snapshot -i
agent-browser --session site2 snapshot -i
agent-browser session list
# Auto-discover running Chrome with remote debugging enabled
agent-browser --auto-connect open https://example.com
agent-browser --auto-connect snapshot
# Or with explicit CDP port
agent-browser --cdp 9222 snapshot
# Persistent dark mode via flag (applies to all pages and new tabs)
agent-browser --color-scheme dark open https://example.com
# Or via environment variable
AGENT_BROWSER_COLOR_SCHEME=dark agent-browser open https://example.com
# Or set during session (persists for subsequent commands)
agent-browser set media dark
agent-browser --headed open https://example.com
agent-browser highlight @e1 # Highlight element
agent-browser record start demo.webm # Record session
agent-browser profiler start # Start Chrome DevTools profiling
agent-browser profiler stop trace.json # Stop and save profile (path optional)
Use AGENT_BROWSER_HEADED=1 to enable headed mode via environment variable. Browser extensions work in both headed and headless mode.
# Open local files with file:// URLs
agent-browser --allow-file-access open file:///path/to/document.pdf
agent-browser --allow-file-access open file:///path/to/page.html
agent-browser screenshot output.png
# List available iOS simulators
agent-browser device list
# Launch Safari on a specific device
agent-browser -p ios --device "iPhone 16 Pro" open https://example.com
# Same workflow as desktop - snapshot, interact, re-snapshot
agent-browser -p ios snapshot -i
agent-browser -p ios tap @e1 # Tap (alias for click)
agent-browser -p ios fill @e2 "text"
agent-browser -p ios swipe up # Mobile-specific gesture
# Take screenshot
agent-browser -p ios screenshot mobile.png
# Close session (shuts down simulator)
agent-browser -p ios close
Requirements: macOS with Xcode, Appium (npm install -g appium && appium driver install xcuitest)
All security features are opt-in. By default, agent-browser imposes no restrictions on navigation, actions, or output.
Enable --content-boundaries to wrap page-sourced output in markers that help LLMs distinguish tool output from untrusted page content:
export AGENT_BROWSER_CONTENT_BOUNDARIES=1
agent-browser snapshot
Restrict navigation to trusted domains:
export AGENT_BROWSER_ALLOWED_DOMAINS="example.com,*.example.com"
agent-browser open https://example.com # OK
agent-browser open https://malicious.com # Blocked
Use a policy file to gate destructive actions:
export AGENT_BROWSER_ACTION_POLICY=./policy.json
Example policy.json:
{"default": "deny", "allow": ["navigate", "snapshot", "click", "scroll", "wait", "get"]}
Prevent context flooding from large pages:
export AGENT_BROWSER_MAX_OUTPUT=50000
Use diff snapshot after performing an action to verify it had the intended effect.
agent-browser snapshot -i # Take baseline snapshot
agent-browser click @e2 # Perform action
agent-browser diff snapshot # See what changed (auto-compares to last snapshot)
The default Playwright timeout is 25 seconds. Override with AGENT_BROWSER_DEFAULT_TIMEOUT (milliseconds). For slow pages:
agent-browser wait --load networkidle
agent-browser wait "#content"
agent-browser wait @e1
agent-browser wait --url "**/dashboard"
agent-browser wait --fn "document.readyState === 'complete'"
agent-browser wait 5000
Always use named sessions when running multiple agents:
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com
agent-browser session list
Always close your browser session when done:
agent-browser close
agent-browser --session agent1 close
Refs (@e1, @e2, etc.) are invalidated when the page changes. Always re-snapshot after clicking links, form submissions, or dynamic content loading.
agent-browser click @e5 # Navigates to new page
agent-browser snapshot -i # MUST re-snapshot
agent-browser click @e1 # Use new refs
Use --annotate to take a screenshot with numbered labels overlaid on interactive elements. Each label [N] maps to ref @eN.
agent-browser screenshot --annotate
# Output: [1] @e1 button "Submit", [2] @e2 link "Home", [3] @e3 textbox "Email"
agent-browser click @e2
When refs are unavailable or unreliable:
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "[email protected]"
agent-browser find role button click --name "Submit"
agent-browser find placeholder "Search" type "query"
agent-browser find testid "submit-btn" click
Use eval to run JavaScript in the browser context. For complex expressions, use --stdin or -b to avoid shell quoting issues.
agent-browser eval 'document.title'
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(
Array.from(document.querySelectorAll("img"))
.filter(i => !i.alt)
.map(i => ({ src: i.src.split("/").pop(), width: i.width }))
)
EVALEOF
agent-browser eval -b "$(echo -n 'Array.from(document.querySelectorAll("a")).map(a => a.href)' | base64)"
Create agent-browser.json in the project root:
{
"headed": true,
"proxy": "http://localhost:8080",
"profile": "./browser-data"
}
Priority: ~/.agent-browser/config.json < ./agent-browser.json < env vars < CLI flags.
npx agent-browser <command> (downloads on first use).npx agent-browser install to download Chromium. Optional: install globally for faster runs: npm install -g agent-browser.