agent-browser

# Browser Automation with agent-browser ## Agent Guidelines & Restrictions 1. **NO Command Line Output to User**: Do NOT output any terminal commands (like `agent-browser ...`) to the user. The user cannot execute these commands. If you need the user to make a choice or provide input, use clear, natural language to ask them. 2. **Sensitive Operations & User Takeover (IMPORTANT)**: When encountering sensitive operations such as login, authentication, or payment, you must call the `browser_wait_user_action` tool to trigger the user takeover flow. After successfully calling this tool, inform the user that their manual action is required. The user will notify you once they have completed (or cancelled) the operation, after which you can continue the automation. You are no longer restricted to using only QR code login. During task execution, pause and wait for user completion before continuing when any of the following actions are required: - Entering passwords, verification codes, or fingerprint authentication - Confirming payments, transfers, or subscription charges - Permanently deleting data or deactivating/closing accounts - Changing passwords or security settings - Registering a new account - Granting sensitive permissions (contacts, location, microphone, etc.) 3. **Screenshots**: When capturing screenshots, **ALL** screenshot files MUST be saved to the `/app/data/所有对话/主对话/browser/screenshots/` directory. For different tasks, you should create separate subdirectories under this directory to store screenshots independently. Please ensure that the directory structure is clear and easy to understand (e.g., `agent-browser screenshot /app/data/所有对话/主对话/browser/screenshots/task_name/page.png`). 4. **Background Execution(Sub Session)**: When using this skill, try to execute tasks in the background as much as possible. You can create a background session via using `sessions_spawn`. **CRITICAL**: The sub-session MUST report the execution status of the current task back to the main session, and explicitly state whether `browser_wait_user_action` has been called. If this tool has already been called, do NOT call it repeatedly. 5. **Profile Lock Resolution**: If you encounter an error indicating that the profile file is locked, you can try deleting the `$AGENT_BROWSER_PROFILE/Singleton*` lock files. ## Core Workflow Every browser automation follows this pattern: 1. **Navigate**: `agent-browser open <url>` && agent-browser tab 0 2. **Snapshot**: `agent-browser snapshot -i` (get element refs like `@e1`, `@e2`) 3. **Interact**: Use refs to click, fill, select 4. **Re-snapshot**: After navigation or DOM changes, get fresh refs ```bash agent-browser open https://example.com/form && agent-browser tab 0 agent-browser snapshot -i # Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit" 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 ``` ## Command Chaining 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. ```bash # Chain open + wait + snapshot in one call agent-browser open https://example.com && agent-browser tab 0 && agent-browser wait --load networkidle && agent-browser snapshot -i # Chain multiple interactions agent-browser fill @e1 "user@example.com" && agent-browser fill @e2 "password123" && agent-browser click @e3 # Navigate and capture agent-browser open https://example.com && agent-browser tab 0 && 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). ## Essential Commands ```bash # Navigation agent-browser open <url> && agent-browser tab 0 # 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 && agent-browser click @e1 --new-tab && agent-browser tab 1 # Click and tab 0 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> && agent-browser --download-path ./downloads tab 0 # Set default download directory # Viewport & Device Emulation agent-browser set viewport 1920 1080 # Set viewport size (default: 1280x720) agent-browser set viewport 1920 1080 2 # 2x retina (same CSS size, higher res screenshots) agent-browser set device "iPhone 14" # Emulate device (viewport + user agent) # 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 ``` ## Common Patterns ### Form Submission ```bash agent-browser open https://example.com/signup && agent-browser tab 0 agent-browser snapshot -i agent-browser fill @e1 "Jane Doe" agent-browser fill @e2 "jane@example.com" agent-browser select @e3 "California" agent-browser check @e4 agent-browser click @e5 agent-browser wait --load networkidle ``` ### Authentication with Auth Vault (Recommended) ```bash # Save credentials once (encrypted with AGENT_BROWSER_ENCRYPTION_KEY) # Recommended: pipe password via stdin to avoid shell history exposure 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 ``` ### Authentication with State Persistence ```bash # Login once and save state agent-browser open https://app.example.com/login && agent-browser tab 0 agent-browser snapshot -i agent-browser fill @e1 "$USERNAME" agent-browser fill @e2 "$PASSWORD" agent-browser click @e3 agent-browser wait --url "**/dashboard" agent-browser state save auth.json # Reuse in future sessions agent-browser state load auth.json agent-browser open https://app.example.com/dashboard && agent-browser tab 0 ``` ### Session Persistence ```bash # Auto-save/restore cookies and localStorage across browser restarts agent-browser --session-name myapp open https://app.example.com/login && agent-browser --session-name myapp tab 0 # ... login flow ... agent-browser close # State auto-saved to ~/.agent-browser/sessions/ # Next time, state is auto-loaded agent-browser --session-name myapp open https://app.example.com/dashboard && agent-browser --session-name myapp tab 0 # Encrypt state at rest export AGENT_BROWSER_ENCRYPTION_KEY=$(openssl rand -hex 32) agent-browser --session-name secure open https://app.example.com && agent-browser --session-name secure tab 0 # 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 ``` ### Data Extraction ```bash agent-browser open https://example.com/products && agent-browser tab 0 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 ``` ### Parallel Sessions ```bash agent-browser --session site1 open https://site-a.com && agent-browser --session site1 tab 0 agent-browser --session site2 open https://site-b.com && agent-browser --session site2 tab 0 agent-browser --session site1 snapshot -i agent-browser --session site2 snapshot -i agent-browser session list ``` ### Connect to Existing Chrome ```bash # Auto-discover running Chrome with remote debugging enabled agent-browser --auto-connect open https://example.com && agent-browser --auto-connect tab 0 agent-browser --auto-connect snapshot # Or with explicit CDP port agent-browser --cdp 9222 snapshot ``` ### Color Scheme (Dark Mode) ```bash # Persistent dark mode via flag (applies to all pages and new tabs) agent-browser --color-scheme dark open https://example.com && agent-browser --color-scheme dark tab 0 # Or via environment variable AGENT_BROWSER_COLOR_SCHEME=dark agent-browser open https://example.com && agent-browser tab 0 # Or set during session (persists for subsequent commands) agent-browser set media dark ``` ### Viewport & Responsive Testing ```bash # Set a custom viewport size (default is 1280x720) agent-browser set viewport 1920 1080 agent-browser screenshot desktop.png # Test mobile-width layout agent-browser set viewport 375 812 agent-browser screenshot mobile.png # Retina/HiDPI: same CSS layout at 2x pixel density # Screenshots stay at logical viewport size, but content renders at higher DPI agent-browser set viewport 1920 1080 2 agent-browser screenshot retina.png # Device emulation (sets viewport + user agent in one step) agent-browser set device "iPhone 14" agent-browser screenshot device.png ``` The `scale` parameter (3rd argument) sets `window.devicePixelRatio` without changing CSS layout. Use it when testing retina rendering or capturing higher-resolution screenshots. ### Visual Browser (Debugging) ```bash agent-browser --headed open https://example.com && agent-browser --headed tab 0 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. ### Local Files (PDFs, HTML) ```bash # Open local files with file:// URLs agent-browser --allow-file-access open file:///path/to/document.pdf && agent-browser --allow-file-access tab 0 agent-browser --allow-file-access open file:///path/to/page.html && agent-browser --allow-file-access tab 0 agent-browser screenshot output.png ``` ### iOS Simulator (Mobile Safari) ```bash # 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 && agent-browser -p ios --device "iPhone 16 Pro" tab 0 # 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`) **Real devices:** Works with physical iOS devices if pre-configured. Use `--device "<UDID>"` where UDID is from `xcrun xctrace list devices`. ## Security All security features are opt-in. By default, agent-browser imposes no restrictions on navigation, actions, or output. ### Content Boundaries (Recommended for AI Agents) Enable `--content-boundaries` to wrap page-sourced output in markers that help LLMs distinguish tool output from untrusted page content: ```bash export AGENT_BROWSER_CONTENT_BOUNDARIES=1 agent-browser snapshot # Output: # --- AGENT_BROWSER_PAGE_CONTENT nonce=<hex> origin=https://example.com --- # [accessibility tree] # --- END_AGENT_BROWSER_PAGE_CONTENT nonce=<hex> --- ``` ### Domain Allowlist Restrict navigation to trusted domains. Wildcards like `*.example.com` also match the bare domain `example.com`. Sub-resource requests, WebSocket, and EventSource connections to non-allowed domains are also blocked. Include CDN domains your target pages depend on: ```bash export AGENT_BROWSER_ALLOWED_DOMAINS="example.com,*.example.com" agent-browser open https://example.com && agent-browser tab 0 # OK agent-browser open https://malicious.com && agent-browser tab 0 # Blocked ``` ### Action Policy Use a policy file to gate destructive actions: ```bash export AGENT_BROWSER_ACTION_POLICY=./policy.json ``` Example `policy.json`: ```json {"default": "deny", "allow": ["navigate", "snapshot", "click", "scroll", "wait", "get"]} ``` Auth vault operations (`auth login`, etc.) bypass action policy but domain allowlist still applies. ### Output Limits Prevent context flooding from large pages: ```bash export AGENT_BROWSER_MAX_OUTPUT=50000 ``` ## Diffing (Verifying Changes) Use `diff snapshot` after performing an action to verify it had the intended effect. This compares the current accessibility tree against the last snapshot taken in the session. ```bash # Typical workflow: snapshot -> action -> diff 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) ``` For visual regression testing or monitoring: ```bash # Save a baseline screenshot, then compare later agent-browser screenshot baseline.png # ... time passes or changes are made ... agent-browser diff screenshot --baseline baseline.png # Compare staging vs production agent-browser diff url https://staging.example.com https://prod.example.com --screenshot ``` `diff snapshot` output uses `+` for additions and `-` for removals, similar to git diff. `diff screenshot` produces a diff image with changed pixels highlighted in red, plus a mismatch percentage. ## Timeouts and Slow Pages The default Playwright timeout is 25 seconds for local browsers. This can be overridden with the `AGENT_BROWSER_DEFAULT_TIMEOUT` environment variable (value in milliseconds). For slow websites or large pages, use explicit waits instead of relying on the default timeout: ```bash # Wait for network activity to settle (best for slow pages) agent-browser wait --load networkidle # Wait for a specific element to appear agent-browser wait "#content" agent-browser wait @e1 # Wait for a specific URL pattern (useful after redirects) agent-browser wait --url "**/dashboard" # Wait for a JavaScript condition agent-browser wait --fn "document.readyState === 'complete'" # Wait a fixed duration (milliseconds) as a last resort agent-browser wait 5000 ``` When dealing with consistently slow websites, use `wait --load networkidle` after `open` to ensure the page is fully loaded before taking a snapshot. If a specific element is slow to render, wait for it directly with `wait <selector>` or `wait @ref`.