agent-browser

A high-performance, native Rust CLI designed for AI agents, providing powerful browser automation and web interaction capabilities.

vercel-labs

Developers / Professionals

AutomationDevelopmentVerifiedOpen-source license: Apache

GitHub Stars39K

Suggested prompts

Use agent-browser to open https://example.com, get the page snapshot, and click the login button.

How can I use agent-browser to take a full-page screenshot and save it to a specific directory?

Use the agent-browser chat mode to automatically fill and submit a web form using natural language instructions.

About this skill

agent-browser

Browser automation CLI for AI agents. Fast native Rust CLI.

What It Does

agent-browser is a command-line tool that lets you control a web browser programmatically. It is designed for AI agents, automation scripts, and developers who need to interact with web pages — navigate, click, fill forms, take screenshots, extract text, and more — without a graphical interface.

Who It's For

AI agents and coding assistants that need to browse the web
Developers automating browser tasks (testing, scraping, monitoring)
Anyone who wants to control a browser from the command line or from scripts

Quick Start

agent-browser open example.com
agent-browser snapshot                    # Get accessibility tree with refs
agent-browser click @e2                   # Click by ref from snapshot
agent-browser fill @e3 "test@example.com" # Fill by ref
agent-browser get text @e1                # Get text by ref
agent-browser screenshot page.png
agent-browser close

Clicks fail early when another element covers the target's click point, for example a consent banner or modal. Dismiss or interact with the reported covering element, then take a fresh snapshot before retrying the original ref.

Headless Chromium screenshots hide native scrollbars for consistent image output. Pass --hide-scrollbars false when launching to keep native scrollbars visible.

Traditional Selectors (also supported)

agent-browser click "#submit"
agent-browser fill "#email" "test@example.com"
agent-browser find role button click --name "Submit"

Core Commands

Navigation & Page Control

agent-browser open — Launch browser (no navigation); stays on about:blank
agent-browser open <url> — Launch + navigate to URL (aliases: goto, navigate)
agent-browser read [url] — Fetch agent-readable text, or read rendered active-tab DOM
agent-browser back — Go back
agent-browser forward — Go forward
agent-browser reload — Reload page
agent-browser pushstate <url> — SPA client-side nav
agent-browser close — Close browser (aliases: quit, exit)
agent-browser close --all — Close all active sessions

Element Interaction

agent-browser click <sel> — Click element (--new-tab to open in new tab)
agent-browser dblclick <sel> — Double-click element
agent-browser focus <sel> — Focus element
agent-browser type <sel> <text> — Type into element
agent-browser fill <sel> <text> — Clear and fill
agent-browser press <key> — Press key (Enter, Tab, Control+a) (alias: key)
agent-browser keyboard type <text> — Type with real keystrokes (no selector, current focus)
agent-browser keyboard inserttext <text> — Insert text without key events (no selector)
agent-browser keydown <key> — Hold key down
agent-browser keyup <key> — Release key
agent-browser hover <sel> — Hover element
agent-browser select <sel> <val> — Select dropdown option
agent-browser check <sel> — Check checkbox
agent-browser uncheck <sel> — Uncheck checkbox
agent-browser scroll <dir> [px] — Scroll (up/down/left/right, --selector )
agent-browser scrollintoview <sel> — Scroll element into view (alias: scrollinto)
agent-browser drag <src> <tgt> — Drag and drop
agent-browser upload <sel> <files> — Upload files

Screenshots & PDF

agent-browser screenshot [path] — Take screenshot (--full for full page, saves to a temporary directory if no path)
agent-browser screenshot --annotate — Annotated screenshot with numbered element labels
agent-browser screenshot --screenshot-dir ./shots — Save to custom directory
agent-browser screenshot --screenshot-format jpeg --screenshot-quality 80
agent-browser pdf <path> — Save as PDF

Snapshot (Accessibility Tree)

agent-browser snapshot — Accessibility tree with refs (best for AI)

Get Info

agent-browser get text <sel> — Get text content
agent-browser get html <sel> — Get innerHTML
agent-browser get value <sel> — Get input value
agent-browser get attr <sel> <attr> — Get attribute
agent-browser get title — Get page title
agent-browser get url — Get current URL
agent-browser get cdp-url — Get CDP WebSocket URL (for DevTools, debugging)
agent-browser get count <sel> — Count matching elements
agent-browser get box <sel> — Get bounding box
agent-browser get styles <sel> — Get computed styles

Read Agent-Friendly Text

agent-browser read
agent-browser read https://example.com/article
agent-browser read https://example.com/article --filter overview
agent-browser read https://example.com/article --outline
agent-browser read https://docs.example.com --llms index --filter auth
agent-browser read https://docs.example.com --llms full --filter auth
agent-browser read example.com/article --require-md
agent-browser read https://example.com/article --json

read fetches a URL without launching Chrome. Omit the URL to read the rendered DOM of the active tab in the current browser session, including browser auth state and client-side updates. Explicit URL reads send Accept: text/markdown by default, try the same URL with .md appended when the first response is not markdown, walk ancestor paths toward / to find the nearest llms.txt for a matching docs link, print markdown or plain text when available, and fall back to readable text extracted from HTML. --llms and --require-md with no URL use the active tab URL because they depend on HTTP resources. read does not read llms-full.txt unless you ask for it.

Options: --raw prints the response body without HTML extraction, --require-md fails unless the server returns Content-Type: text/markdown, --outline prints a compact heading outline for one page, --llms index prints a compact nearest-ancestor llms.txt link list, --llms full reads the nearest-ancestor llms-full.txt, --filter <text> narrows page sections, llms links/sections, or outline headings, and --timeout <ms> changes the request timeout. Global safeguards such as --allowed-domains, --content-boundaries, and --max-output also apply to read fetches and output.

Check State

agent-browser is visible <sel> — Check if visible
agent-browser is enabled <sel> — Check if enabled
agent-browser is checked <sel> — Check if checked

Find Elements (Semantic Locators)

agent-browser find role <role> <action> [value]       # By ARIA role
agent-browser find text <text> <action> [value]       # By text content
agent-browser find label <label> <action> [value]     # By label
agent-browser find placeholder <ph> <action> [value]  # By placeholder
agent-browser find alt <text> <action> [value]        # By alt text
agent-browser find title <text> <action> [value]      # By title attr
agent-browser find testid <id> <action> [value]       # By data-testid
agent-browser find first <sel> <action> [value]       # First match
agent-browser find last <sel> <action> [value]        # Last match
agent-browser find nth <n> <sel> <action> [value]     # Nth match

Actions: click, fill, check, hover, text

Options: --name <name> (filter role by accessible name), --exact (exact, case-sensitive match; for role it applies to the accessible name, whose default is a case-insensitive substring)

Wait

agent-browser wait <selector> — Wait for element to be visible
agent-browser wait <ms> — Wait for time (milliseconds)
agent-browser wait --text "Welcome" — Wait for text to appear (substring match)
agent-browser wait --url "**/dash" — Wait for URL pattern
agent-browser wait --load networkidle — Wait for load state
agent-browser wait --fn "window.ready === true" — Wait for JS condition

Load states: load, domcontentloaded, networkidle

Batch Execution

Execute multiple commands in a single invocation. Commands can be passed as quoted arguments or piped as JSON via stdin.

# Argument mode: each quoted argument is a full command
agent-browser batch "open https://example.com" "snapshot -i" "screenshot"

# With --bail to stop on first error
agent-browser batch --bail "open https://example.com" "click @e1" "screenshot"

# Stdin mode: pipe commands as JSON
echo '[
  ["open", "https://example.com"],
  ["snapshot", "-i"],
  ["click", "@e1"],
  ["screenshot", "result.png"]
]' | agent-browser batch --json

Clipboard

agent-browser clipboard read — Read text from clipboard
agent-browser clipboard write "Hello, World!" — Write text to clipboard
agent-browser clipboard copy — Copy current selection (Ctrl+C)
agent-browser clipboard paste — Paste from clipboard (Ctrl+V)

Mouse Control

agent-browser mouse move <x> <y> — Move mouse
agent-browser mouse down [button] — Press button (left/right/middle)
agent-browser mouse up [button] — Release button
agent-browser mouse wheel <dy> [dx] — Scroll wheel

Browser Settings

agent-browser set viewport <w> <h> [scale] — Set viewport size (scale for retina, e.g. 2)
agent-browser set device <name> — Emulate device ("iPhone 14")
agent-browser set geo <lat> <lng> — Set geolocation
agent-browser set offline [on|off] — Toggle offline mode
agent-browser set headers <json> — Extra HTTP headers
agent-browser set credentials <u> <p> — HTTP basic auth
agent-browser set media [dark|light] — Emulate color scheme

Cookies & Storage

agent-browser cookies — Get all cookies
agent-browser cookies set <name> <val> — Set cookie
agent-browser cookies set --curl <file> — Import cookies from a Copy-as-cURL dump, JSON array, or bare Cookie header (auto-detected)
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
agent-browser storage session — Same for sessionStorage

Network

agent-browser network route <url> — Intercept requests
agent-browser network route <url> --abort — Block requests
agent-browser network route <url> --body <json> — Mock response
agent-browser network route '*' --abort --resource-type script — Block scripts only
agent-browser network unroute [url] — Remove routes
agent-browser network requests — View tracked requests
agent-browser network requests --filter api — Filter requests
agent-browser network requests --type xhr,fetch — Filter by resource type
agent-browser network requests --method POST — Filter by HTTP method
agent-browser network requests --status 2xx — Filter by status (200, 2xx, 400-499)
agent-browser network request <requestId> — View full request/response detail
agent-browser network har start — Start HAR recording (embeds text response bodies)
agent-browser network har start --content all — Embed all response bodies (binary as base64)
agent-browser network har start --content none — Metadata only, no bodies
agent-browser network har stop [output.har] — Stop and save HAR (temp path if omitted)

Tabs & Windows

agent-browser tab — List tabs (shows tabId and optional label)
agent-browser tab new [url] — New tab (optionally with URL)
agent-browser tab new --label docs [url] — New tab with a user-assigned label
agent-browser tab <t<N>|label> — Switch to a tab by id or label
agent-browser tab close [t<N>|label] — Close a tab (defaults to active)
agent-browser window new — New window

Tab ids are stable strings of the form t1, t2, t3. They're never reused within a session, so scripts and agents can keep referring to the same tab even after other tabs are opened or closed. Positional integers like tab 2 are not accepted; the t prefix disambiguates handles from indices and mirrors the @e1 convention used for element refs.

You can also assign a memorable label (docs, app, admin) and use it interchangeably with the id. Labels are never auto-generated and never rewritten on navigation — they're yours to name and keep.

Switching to a tab discarded by Chrome's Memory Saver reactivates it, since a discarded tab has no renderer to drive. Reactivation reloads the discarded page and resets its unsaved state, and the switch result reports "revived": true. A tab whose page is paused by a JavaScript dialog is alive rather than discarded, so the switch leaves it untouched and reports "dialogBlocked": true; resolve the dialog with dialog accept or dialog dismiss before interacting. Closing the active tab onto a discarded successor revives it the same way and reports "activeTabRevived": true.

Frames

agent-browser frame <sel> — Switch to iframe
agent-browser frame main — Back to main frame

Dialogs

agent-browser dialog accept [text] — Accept (with optional prompt text)
agent-browser dialog dismiss — Dismiss
agent-browser dialog status — Check if a dialog is currently open

By default, alert and beforeunload dialogs are automatically accepted so they never block the agent. confirm and prompt dialogs still require explicit handling. Use --no-auto-dialog (or AGENT_BROWSER_NO_AUTO_DIALOG=1) to disable automatic handling.

When a JavaScript dialog is pending, all command responses include a warning field with the dialog type and message.

Diff

agent-browser diff snapshot — Compare current vs last snapshot
agent-browser diff snapshot --baseline before.txt — Compare current vs saved snapshot file
agent-browser diff snapshot --selector "#main" --compact — Scoped snapshot diff
agent-browser diff screenshot --baseline before.png — Visual pixel diff against baseline
agent-browser diff screenshot --baseline b.png -o d.png — Save diff image to custom path
agent-browser diff screenshot --baseline b.png -t 0.2 — Adjust color threshold (0-1)
agent-browser diff url https://v1.com https://v2.com — Compare two URLs (snapshot diff)
agent-browser diff url https://v1.com https://v2.com --screenshot — Also visual diff
agent-browser diff url https://v1.com https://v2.com --wait-until networkidle — Custom wait strategy
agent-browser diff url https://v1.com https://v2.com --selector "#main" — Scope to element

Debug

agent-browser trace start — Start recording trace
agent-browser trace stop [path] — Stop and save trace
agent-browser profiler start — Start Chrome DevTools profiling
agent-browser profiler stop [path] — Stop and save profile (.json)
agent-browser console — View console messages (log, error, warn, info)
agent-browser console --json — JSON output with raw CDP args for programmatic access
agent-browser console --clear — Clear console
agent-browser errors — View page errors (uncaught JavaScript exceptions)
agent-browser errors --clear — Clear errors
agent-browser highlight <sel> — Highlight element
agent-browser inspect — Open Chrome DevTools for the active page
agent-browser state save <path> — Save auth state
agent-browser state load <path> — Load auth state
agent-browser state list — List saved state files
agent-browser state show <file> — Show state summary
agent-browser state rename <old> <new> — Rename state file
agent-browser state clear [name] — Clear states for session
agent-browser state clear --all — Clear all saved states
agent-browser state clean --older-than <days> — Delete old states

React / Web Vitals

Agent-browser ships with first-class React introspection and universal Web Vitals metrics. The React commands need the React DevTools hook installed at launch; Web Vitals and pushstate are framework-agnostic.

agent-browser open --enable react-devtools <url> — Launch with React hook installed
agent-browser react tree — Full component tree
agent-browser react inspect <fiberId> — props, hooks, state, source
agent-browser react renders start — Begin fiber render recording
agent-browser react renders stop [--json] — Stop and print profile (--json for raw data)
agent-browser react suspense [--only-dynamic] [--json] — Suspense boundaries + classifier
agent-browser vitals [url] [--json] — LCP/CLS/TTFB/FCP/INP + hydration summary

Each react ... subcommand requires --enable react-devtools to have been passed at launch (the React DevTools installHook.js is embedded in the binary). Without it the commands error with React DevTools hook not installed - relaunch with --enable react-devtools.

Works on any React app — Next.js, Remix, Vite+React, CRA, TanStack Start, React Native Web, etc. vitals and pushstate are framework-agnostic. vitals prints a summary by default; pass --json for the full structured payload.

Accessibility audits

Run an axe-core accessibility audit against the current page or a URL. The axe-core engine is embedded in the binary, so it works offline and under strict CSP. It runs private partial audits across the page's frame tree and merges serialized results without page messaging, so page-provided window.axe values remain intact and iframe violations retain their frame selector paths. Accessibility audits require a CDP browser and are not available with Safari or iOS WebDriver sessions.

agent-browser a11y — Audit the current page
agent-browser a11y https://example.com — Navigate, then audit
agent-browser a11y --tags wcag2a,wcag2aa — Only rules with these axe tags
agent-browser a11y --selector "#main" — Scope the audit to a subtree
agent-browser a11y example.com --json — Full structured results

The default output lists each violation with its impact, rule id, fix guidance URL, and the CSS selectors of failing nodes.

Init scripts

agent-browser open --init-script <path> — Register page init script before first navigation (repeatable; also AGENT_BROWSER_INIT_SCRIPTS env)
agent-browser addinitscript <js> — Register at runtime (returns identifier)
agent-browser removeinitscript <identifier> — Remove a previously registered init script

Pre-navigation setup

Some flows (SSR debug, auth cookies for protected origins, init scripts) need state set up before the first navigation. Use open with no URL to launch the browser, then stage cookies / routes / init scripts, then navigate. batch sends it all in one CLI call.

Setup

agent-browser install — Download Chrome from Chrome for Testing (Google's official automation channel)
agent-browser install --with-deps — Also install system deps (Linux)
agent-browser upgrade — Upgrade agent-browser to the latest version
agent-browser doctor — Diagnose the install and auto-clean stale daemon files
agent-browser doctor --fix — Also run destructive repairs (reinstall Chrome, purge old state, ...)
agent-browser doctor --offline --quick — Skip network probes and the live launch test

doctor checks your environment, Chrome install, daemon state, config files, encryption key, providers, network reachability, and runs a live headless browser launch test. Stale socket/pid sidecar files are auto-cleaned. Output is also available as --json for agents.

Skills

agent-browser skills — List available skills
agent-browser skills list — Same as above
agent-browser skills get <name> — Output a skill's full content
agent-browser skills get <name> --full — Include references and templates
agent-browser skills get --all — Output every skill
agent-browser skills path [name] — Print skill directory path

Serves bundled skill content that always matches the installed CLI version. AI agents use this to get current instructions rather than relying on cached copies. Set AGENT_BROWSER_SKILLS_DIR to override the skills directory path.

MCP Server

agent-browser mcp
agent-browser mcp --tools all
agent-browser mcp --tools core,network,react

Starts a Model Context Protocol server over stdio. MCP clients launch this command as a subprocess and exchange newline-delimited JSON-RPC on stdin and stdout. The server defaults to MCP protocol 2025-11-25 and accepts older supported client protocol versions during initialization.

The default tools profile is core, which keeps MCP context small for everyday browser automation. Use --tools all for the full typed CLI parity surface, or combine profiles with commas, such as --tools core,network,react.

Profiles:

core — Default. Navigation, snapshots, interaction, waits, reads, screenshots, JavaScript eval, close, tab basics, and profile discovery
network — Network routes, request inspection, HAR, headers, credentials, offline
state — Cookies, storage, auth, saved state, sessions, profiles, skills
debug — Console/errors, tracing, profiling, recording, a11y audit, clipboard, plugins, doctor, dashboard, install, upgrade, chat, diff, batch, confirm/deny
tabs — Back/forward/reload, tabs, windows, frames, dialogs
react — React tree/inspect/renders/suspense, vitals, pushstate
mobile — Viewport/device/geolocation/media, touch, swipe, mouse, keyboard
all — Every MCP tool, including the full typed CLI parity surface

Common tools include:

agent_browser_tools_profiles
agent_browser_open
agent_browser_snapshot
agent_browser_click
agent_browser_fill
agent_browser_type
agent_browser_press
agent_browser_wait_for_selector
agent_browser_screenshot
agent_browser_get_url
agent_browser_eval
agent_browser_close

Each tool has typed fields such as url, selector, text, key, session, and allowedDomains, so MCP clients show meaningful approval prompts instead of raw command arrays. The common allowedDomains array maps to --allowed-domains and activates the same WebRTC containment and launch-mode restrictions. Each tool also accepts extraArgs for advanced CLI flags and exact CLI parity. Tool discovery is paginated and includes read-only/open-world annotations so modern MCP clients can load the large typed surface incrementally.

Example MCP client config:

{
  "mcpServers": {
    "agent-browser": {
      "command": "agent-browser",
      "args": ["mcp"]
    }
  }
}

Full parity MCP client config:

{
  "mcpServers": {
    "agent-browser": {
      "command": "agent-browser",
      "args": ["mcp", "--tools", "all"]
    }
  }
}

Tool invocations use the same config files and environment variables as the CLI. Use session in the tool arguments, or set AGENT_BROWSER_SESSION, to isolate browser state.

Authentication

agent-browser provides multiple ways to persist login sessions so you don't re-authenticate every run.

Approach	Best for	Flag / Env
Chrome profile reuse	Reuse your existing Chrome login state (cookies, sessions) with zero setup	`--profile <name>` / `AGENT_BROWSER_PROFILE`
Persistent profile	Full browser state (cookies, IndexedDB, service workers, cache) across restarts	`--profile <path>` / `AGENT_BROWSER_PROFILE`
Session persistence	Auto-save/restore cookies + localStorage from a stable session key	`--session <id> --restore` / `AGENT_BROWSER_RESTORE`
Import from your browser	Grab auth from a Chrome session you already logged into	`--auto-connect` + `state save`
State file	Load a previously saved state JSON on launch	`--state <path>` / `AGENT_BROWSER_STATE`
Auth vault	Store credentials locally (encrypted), login by name	`auth save` / `auth login`

Import auth from your browser

If you are already logged in to a site in Chrome, you can grab that auth state and reuse it:

# 1. Launch Chrome with remote debugging enabled
#    macOS:
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --remote-debugging-port=9222
#    Or use --auto-connect to discover an already-running Chrome

# 2. Connect and save the authenticated state
agent-browser --auto-connect state save ./my-auth.json

# 3. Use the saved auth in future sessions
agent-browser --state ./my-auth.json open https://app.example.com/dashboard

# 4. Or use --restore for automatic persistence
SESSION="$(agent-browser session id --scope worktree --prefix myapp)"
agent-browser --session "$SESSION" --restore --state ./my-auth.json open https://app.example.com/dashboard
# From now on, --session "$SESSION" --restore auto-saves/restores this state

Security notes:

--remote-debugging-port exposes full browser control on localhost. Any local process can connect. Only use on trusted machines and close Chrome when done.

State files contain session tokens in plaintext. Add them to .gitignore and delete when no longer needed. For encryption at rest, set AGENT_BROWSER_ENCRYPTION_KEY.

Sessions

Run multiple isolated browser instances:

# Different sessions
agent-browser --session agent1 open site-a.com
agent-browser --session agent2 open site-b.com

# Or via environment variable
AGENT_BROWSER_SESSION=agent1 agent-browser click "#btn"

# List active sessions
agent-browser session list
# Output:
# Active sessions:
# -> default
#    agent1

# Show current session
agent-browser session

# Generate a stable worktree-scoped session id
agent-browser session id --scope worktree --prefix next-dev-loop

# Inspect daemon, launch, and restore status
agent-browser session info --json

Each session has its own:

Browser instance
Cookies and storage
Navigation history
Authentication state

Chrome Profile Reuse

The fastest way to use your existing login state: pass a Chrome profile name to --profile:

# List available Chrome profiles
agent-browser profiles

# Reuse your default Chrome profile's login state
agent-browser --profile Default open https://gmail.com

# Use a named profile (by display name or directory name)
agent-browser --profile "Work" open https://app.example.com

# Or via environment variable
AGENT_BROWSER_PROFILE=Default agent-browser open https://gmail.com

This copies your Chrome profile to a temp directory (read-only snapshot, no changes to your original profile), so the browser launches with your existing cookies and sessions.

Note: On Windows, close Chrome before using --profile <name> if Chrome is running, as some profile files may be locked.

Persistent Profiles

For a persistent custom profile directory that stores state across browser restarts, pass a path to --profile:

# Use a persistent profile directory
agent-browser --profile ~/.myapp-profile open myapp.com

# Login once, then reuse the authenticated session
agent-browser --profile ~/.myapp-profile open myapp.com/dashboard

# Or via environment variable
AGENT_BROWSER_PROFILE=~/.myapp-profile agent-browser open myapp.com

The profile directory stores:

Cookies and localStorage
IndexedDB data
Service workers
Browser cache
Login sessions

Tip: Use different profile paths for different projects to keep their browser state isolated.

Session Persistence

Use --restore with a stable --session to automatically save and restore cookies and localStorage across browser restarts:

# Generate a stable id for this worktree and auto-save/load state
SESSION="$(agent-browser session id --scope worktree --prefix twitter)"
agent-browser --session "$SESSION" --restore open twitter.com

# Login once, then state persists automatically
# State files stored in ~/.agent-browser/sessions/

# Optional: validate restored state before auto-saving again
agent-browser --session "$SESSION" --restore --restore-check-text Dashboard open twitter.com

State is saved when the browser closes (explicit close, idle timeout, or daemon shutdown) and also periodically while the browser is open, so a browser window you close by hand still leaves a recent save behind. Periodic autosave waits for commands to settle, then saves at most once per AGENT_BROWSER_AUTOSAVE_INTERVAL_MS (default 30000; set to 0 to save only on close). Idle sessions keep saving on the same interval, so changes the page makes on its own (token refreshes, background requests) are captured too. It respects the --restore-save policy.

State Encryption

Encrypt saved session data at rest with AES-256-GCM:

# Generate key: openssl rand -hex 32
export AGENT_BROWSER_ENCRYPTION_KEY=<64-char-hex-key>

# State files are now encrypted automatically
agent-browser --session secure --restore open example.com

Variable	Description
`AGENT_BROWSER_RESTORE`	Auto-save/load state persistence name
`AGENT_BROWSER_RESTORE_SAVE`	Restore save policy: `auto`, `always`, or `never`
`AGENT_BROWSER_AUTOSAVE_INTERVAL_MS`	Min ms between periodic autosaves (default: 30000, 0 disables)
`AGENT_BROWSER_NAMESPACE`	Namespace for daemon sockets and restore state
`AGENT_BROWSER_SESSION_NAME`	Legacy auto-save/load state persistence name
`AGENT_BROWSER_ENCRYPTION_KEY`	64-char hex key for AES-256-GCM encryption
`AGENT_BROWSER_STATE_EXPIRE_DAYS`	Auto-delete states older than N days (default: 30)

Security

agent-browser includes security features for safe AI agent deployments. All features are opt-in, and existing workflows are unaffected until you explicitly enable a feature:

Authentication Vault: Store credentials locally (always encrypted), reference by name. The LLM never sees passwords. auth login navigates with load and then waits for login form selectors to appear (SPA-friendly, timeout follows the default action timeout). A key is auto-generated at ~/.agent-browser/.encryption-key if AGENT_BROWSER_ENCRYPTION_KEY is not set: echo "pass" | agent-browser auth save github --url https://github.com/login --username user --password-stdin then agent-browser auth login github
Plugin System: Extend agent-browser with external executable plugins. Plugins run out-of-process over the agent-browser.plugin.v1 stdio JSON protocol and declare capabilities such as credential.read, browser.provider, launch.mutate, or command.run.
Content Boundary Markers: Wrap page output in delimiters so LLMs can distinguish tool output from untrusted content: --content-boundaries
Domain Allowlist: Restrict navigation to trusted domains (wildcards like *.example.com also match the bare domain): --allowed-domains "example.com,*.example.com". Sub-resource requests (scripts, images, fetch), WebSocket/EventSource connections, and sendBeacon calls to non-allowed domains are blocked. WebRTC peer connections are disabled in supported Chromium sessions while the allowlist is active to prevent STUN, TURN, and DNS traffic from bypassing HTTP interception. Dedicated and shared workers are guarded with a bootstrap wrapper; if a page CSP forbids that wrapper, the worker fails closed rather than running without the allowlist guard. Pre-existing CDP sessions, auto-connect, Chrome profiles, direct-page provider plugins, agent-browser restore or state-file replay, raw Chrome args that select profiles, restore sessions, or open startup pages, iOS, and Safari reject this option because agent-browser cannot install equivalent containment before page scripts run. Include any CDN domains your target pages depend on (e.g., *.cdn.example.com).
Action Policy: Gate destructive actions with a static policy file: --action-policy ./policy.json
Action Confirmation: Require explicit approval for sensitive action categories: --confirm-actions eval,download
Output Length Limits: Prevent context flooding: --max-output 50000

Variable	Description
`AGENT_BROWSER_CONTENT_BOUNDARIES`	Wrap page output in boundary markers
`AGENT_BROWSER_MAX_OUTPUT`	Max characters for page output
`AGENT_BROWSER_ALLOWED_DOMAINS`	Comma-separated allowed domain patterns; requires a fresh controllable browser context without profile/session startup args, restore/state replay, or direct-page provider plugins
`AGENT_BROWSER_ACTION_POLICY`	Path to action policy JSON file
`AGENT_BROWSER_CONFIRM_ACTIONS`	Action categories requiring confirmation
`AGENT_BROWSER_CONFIRM_INTERACTIVE`	Enable interactive confirmation prompts
`AGENT_BROWSER_PLUGINS`	JSON plugin registry override

Plugin System

Plugins let third-party tools integrate without becoming built-in agent-browser dependencies. Add a plugin from npm or GitHub:

agent-browser plugin add agent-browser-plugin-captcha
agent-browser plugin add @company/agent-browser-plugin-vault --name vault
agent-browser plugin add org/agent-browser-plugin-cloud-browser

References are resolved by shape: name uses npm, @scope/name uses npm, and owner/repo uses GitHub. plugin add writes ./agent-browser.json by default; use --global for ~/.agent-browser/config.json.

Plugin packages should support plugin.manifest so plugin add can discover their name and capabilities automatically. If a plugin does not support manifests, pass --capability <name> during add.

Plugins can also be configured manually in agent-browser.json:

{
  "plugins": [
    {
      "name": "vault",
      "command": "agent-browser-plugin-vault",
      "capabilities": ["credential.read"]
    },
    {
      "name": "cloud-browser",
      "command": "agent-browser-plugin-cloud-browser",
      "capabilities": ["browser.provider"]
    },
    {
      "name": "stealth",
      "command": "agent-browser-plugin-stealth",
      "capabilities": ["launch.mutate"]
    },
    {
      "name": "captcha",
      "command": "agent-browser-plugin-captcha",
      "capabilities": ["command.run", "captcha.solve"]
    }
  ]
}

Inspect configured plugins:

agent-browser plugin list
agent-browser plugin show vault

Use a credential provider plugin for one login:

agent-browser auth login my-app --credential-provider vault --item "My App"
agent-browser auth login my-app --credential-provider vault --item "My App" --url https://app.example.com/login --username-selector "#email" --password-selector "#password" --submit-selector "button[type=submit]"

Use a browser provider plugin:

agent-browser --provider cloud-browser open https://example.com

Use a launch mutator plugin for stealth or local launch customization. The plugin can append Chrome args, extensions, and init scripts before the browser starts:

agent-browser open https://example.com

Use a generic plugin command for domain-specific tools such as CAPTCHA solvers:

agent-browser plugin run captcha captcha.solve --payload '{"siteKey":"...","url":"https://example.com"}'

The protocol request always includes protocol, type, capability, and request. A credential plugin receives credential.resolve, a browser provider receives browser.launch, a launch mutator receives launch.mutate, and generic commands receive the supplied request type. plugin run is for command.run and custom capabilities; core capabilities and protocol request types use their dedicated command paths. agent-browser keeps browser automation, redaction-sensitive output, and policy enforcement in core.

Gate plugin access by capability action:

agent-browser --confirm-actions plugin:vault:credential.read auth login my-app --credential-provider vault --item "My App"
agent-browser --confirm-actions plugin:cloud-browser:browser.provider --provider cloud-browser open https://example.com
agent-browser --confirm-actions plugin:stealth:launch.mutate open https://example.com

Do not put vault tokens or passwords in plugin command args. Use the vault vendor's own login/session mechanism or environment outside agent-browser config.

Snapshot Options

The snapshot command supports filtering to reduce output size:

agent-browser snapshot                    # Full accessibility tree
agent-browser snapshot -i                 # Interactive elements only (buttons, inputs, links)
agent-browser snapshot -i --urls          # Interactive elements with link URLs
agent-browser snapshot -c                 # Compact (remove empty structural elements)
agent-browser snapshot -d 3               # Limit depth to 3 levels
agent-browser snapshot -s "#main"         # Scope to CSS selector
agent-browser snapshot -i -c -d 5         # Combine options

Option	Description
`-i, --interactive`	Only show interactive elements (buttons, links, inputs)
`-u, --urls`	Include href URLs for link elements
`-c, --compact`	Remove empty structural elements
`-d, --depth <n>`	Limit tree depth
`-s, --selector <sel>`	Scope to CSS selector

Annotated Screenshots

The --annotate flag overlays numbered labels on interactive elements in the screenshot. Each label [N] corresponds to ref @eN, so the same refs work for both visual and text-based workflows.

Annotated screenshots are supported on the CDP-backed browser path (Chrome/Lightpanda). The Safari/WebDriver backend does not yet support --annotate.

agent-browser screenshot --annotate
# -> Screenshot saved to /tmp/screenshot-2026-02-17T12-00-00-abc123.png
#    [1] @e1 button "Submit"
#    [2] @e2 link "Home"
#    [3] @e3 textbox "Email"

After an annotated screenshot, refs are cached so you can immediately interact with elements:

agent-browser screenshot --annotate ./page.png
agent-browser click @e2     # Click the "Home" link labeled [2]

This is useful for multimodal AI models that can reason about visual layout, unlabeled icon buttons, canvas elements, or visual state that the text accessibility tree cannot capture.

Options

Option	Description
`--session <name>`	Use isolated session (or `AGENT_BROWSER_SESSION` env)
`--restore [name]`	Auto-save/restore session state. Bare `--restore` uses `--session` as the key
`--restore-save <policy>`	Restore save policy: `auto`, `always`, or `never`
`--restore-check-url <glob>`	Validate restored state against a URL pattern
`--restore-check-text <text>`	Validate restored state against page text
`--restore-check-fn <js>`	Validate restored state against a truthy JavaScript expression
`--namespace <name>`	Isolate daemon sockets and restore-state directories
`--session-name <name>`	Legacy alias for restore persistence key
`--profile <name	path>`
`--state <path>`	Load storage state from JSON file (or `AGENT_BROWSER_STATE` env)
`--headers <json>`	Set HTTP headers scoped to the URL's origin
`--executable-path <path>`	Custom browser executable (or `AGENT_BROWSER_EXECUTABLE_PATH` env)
`--extension <path>`	Load browser extension (repeatable; or `AGENT_BROWSER_EXTENSIONS` env)
`--init-script <path>`	Register a page init script before the first navigation (repeatable; or `AGENT_BROWSER_INIT_SCRIPTS` env)
`--enable <feature>`	Built-in init scripts: `react-devtools` (repeatable or comma-list; or `AGENT_BROWSER_ENABLE` env)
`--args <args>`	Browser launch args, comma or newline separated (or `AGENT_BROWSER_ARGS` env)
`--user-agent <ua>`	Custom User-Agent string (or `AGENT_BROWSER_USER_AGENT` env)
`--proxy <url>`	Proxy server URL with optional auth (or `AGENT_BROWSER_PROXY` env)
`--proxy-bypass <hosts>`	Hosts to bypass proxy (or `AGENT_BROWSER_PROXY_BYPASS` env)
`--ignore-https-errors`	Ignore HTTPS certificate errors (useful for self-signed certs)
`--allow-file-access`	Allow file:// URLs to access local files (Chromium only)
`--hide-scrollbars <bool>`	Hide native scrollbars in headless Chromium screenshots, enabled by default (or `AGENT_BROWSER_HIDE_SCROLLBARS` env)
`-p, --provider <name>`	Browser provider, including configured `browser.provider` plugins (or `AGENT_BROWSER_PROVIDER` env)
`--device <name>`	iOS device name, e.g. "iPhone 15 Pro" (or `AGENT_BROWSER_IOS_DEVICE` env)
`--json`	JSON output (for agents)
`--annotate`	Annotated screenshot with numbered element labels (or `AGENT_BROWSER_ANNOTATE` env)
`--screenshot-dir <path>`	Default screenshot output directory (or `AGENT_BROWSER_SCREENSHOT_DIR` env)
`--screenshot-quality <n>`	JPEG quality 0-100 (or `AGENT_BROWSER_SCREENSHOT_QUALITY` env)
`--screenshot-format <fmt>`	Screenshot format: `png`, `jpeg` (or `AGENT_BROWSER_SCREENSHOT_FORMAT` env)
`--headed`	Show browser window (not headless) (or `AGENT_BROWSER_HEADED` env)
`--webgpu`	Enable WebGPU; SwiftShader software Vulkan on Linux, no GPU required (or `AGENT_BROWSER_WEBGPU` env)
`--cdp <port	url>`
`--auto-connect`	Auto-discover and connect to running Chrome (or `AGENT_BROWSER_AUTO_CONNECT` env)
`--color-scheme <scheme>`	Color scheme: `dark`, `light`, `no-preference` (or `AGENT_BROWSER_COLOR_SCHEME` env)
`--download-path <path>`	Default download directory (or `AGENT_BROWSER_DOWNLOAD_PATH` env)
`--content-boundaries`	Wrap page output in boundary markers for LLM safety (or `AGENT_BROWSER_CONTENT_BOUNDARIES` env)
`--max-output <chars>`	Truncate page output to N characters (or `AGENT_BROWSER_MAX_OUTPUT` env)
`--allowed-domains <list>`	Comma-separated allowed domain patterns; also disables WebRTC peer connections in supported Chromium sessions and rejects CDP, auto-connect, Chrome profiles, restore/state replay, direct-page provider plugins, unsafe startup `--args`, iOS, and Safari (or `AGENT_BROWSER_ALLOWED_DOMAINS` env)
`--action-policy <path>`	Path to action policy JSON file (or `AGENT_BROWSER_ACTION_POLICY` env)
`--confirm-actions <list>`	Action categories requiring confirmation (or `AGENT_BROWSER_CONFIRM_ACTIONS` env)
`--confirm-interactive`	Interactive confirmation prompts; auto-denies if stdin is not a TTY (or `AGENT_BROWSER_CONFIRM_INTERACTIVE` env)
`--engine <name>`	Browser engine: `chrome` (default), `lightpanda` (or `AGENT_BROWSER_ENGINE` env)
`--idle-timeout <time>`	Shut down the daemon after inactivity (`10s`, `3m`, `1h`, or raw ms). Defaults to `1h`; use `0` to disable (or `AGENT_BROWSER_IDLE_TIMEOUT_MS` env)
`--no-auto-dialog`	Disable automatic dismissal of `alert`/`beforeunload` dialogs (or `AGENT_BROWSER_NO_AUTO_DIALOG` env)
`--model <name>`	AI model for chat command (or `AI_GATEWAY_MODEL` env)
`-v`, `--verbose`	Show tool commands and their raw output (chat)
`-q`, `--quiet`	Show only AI text responses, hide tool calls (chat)
`--config <path>`	Use a custom config file (or `AGENT_BROWSER_CONFIG` env)
`--debug`	Debug output

Observability Dashboard

Monitor agent-browser sessions in real time with a local web dashboard showing a live viewport and command activity feed.

# Start the dashboard server (runs in background on port 4848)
agent-browser dashboard start
agent-browser dashboard start --port 8080   # Custom port

# All sessions are automatically visible in the dashboard
agent-browser open example.com

# Stop the dashboard
agent-browser dashboard stop

The dashboard runs as a standalone background process on port 4848, independent of browser sessions. It stays available even when no sessions are running, and it works from http://localhost:4848 or a proxied/forwarded URL that reaches the dashboard server, such as https://dashboard.agent-browser.localhost or a Coder workspace URL. The browser stays on the dashboard origin; session-specific tabs, status, and stream traffic are proxied internally, so session ports do not need to be exposed.

The dashboard displays:

Live viewport: real-time JPEG frames from the browser
Activity feed: chronological command/result stream with timing and expandable details
Console output: browser console messages (log, warn, error)
Session creation: create new sessions from the UI with local engines (Chrome, Lightpanda) or cloud providers (AgentCore, Browserbase, Browserless, Browser Use, Kernel)
AI Chat: chat with an AI assistant directly in the dashboard (requires Vercel AI Gateway configuration)

AI Chat

The dashboard includes an optional AI chat panel powered by the Vercel AI Gateway. The same functionality is available directly from the CLI via the chat command. Set these environment variables to enable AI chat:

export AI_GATEWAY_API_KEY=gw_your_key_here
export AI_GATEWAY_MODEL=anthropic/claude-sonnet-4.6           # optional, this is the default
export AI_GATEWAY_URL=https://ai-gateway.vercel.sh           # optional, this is the default

CLI usage:

agent-browser chat "open google.com and search for cats"     # Single-shot
agent-browser chat                                           # Interactive REPL
agent-browser -q chat "summarize this page"                  # Quiet mode (text only)
agent-browser -v chat "fill in the login form"               # Verbose (show command output)
agent-browser --model openai/gpt-4o chat "take a screenshot" # Override model

The chat command translates natural language instructions into agent-browser commands, executes them, and streams the AI response. In interactive mode, type quit to exit. Use --json for structured output suitable for agent consumption.

Dashboard usage:

The Chat tab is always visible in the dashboard. When AI_GATEWAY_API_KEY is set, the Rust server proxies requests to the gateway and streams responses back using the Vercel AI SDK's UI Message Stream protocol. Without the key, sending a message shows an error inline.

Configuration

Create an agent-browser.json file to set persistent defaults instead of repeating flags on every command.

Locations (lowest to highest priority):

~/.agent-browser/config.json: user-level defaults
./agent-browser.json: project-level overrides (in working directory)
AGENT_BROWSER_* environment variables override config file values
CLI flags override everything

Example agent-browser.json:

{
  "headed": true,
  "proxy": "http://localhost:8080",
  "profile": "./browser-data",
  "userAgent": "my-agent/1.0",
  "hideScrollbars": false,
  "ignoreHttpsErrors": true,
  "plugins": [
    {
      "name": "vault",
      "command": "agent-browser-plugin-vault",
      "capabilities": ["credential.read"]
    }
  ]
}

Use --config <path> or AGENT_BROWSER_CONFIG to load a specific config file instead of the defaults:

agent-browser --config ./ci-config.json open example.com
AGENT_BROWSER_CONFIG=./ci-config.json agent-browser open example.com

All options from the table above can be set in the config file using camelCase keys (e.g., --executable-path becomes "executablePath", --proxy-bypass becomes "proxyBypass"). Plugins are configured with the "plugins" array shown above. Unknown keys are ignored for forward compatibility.

A JSON Schema is available for IDE autocomplete and validation. Add a $schema key to your config file to enable it:

{
  "$schema": "https://agent-browser.dev/schema.json",
  "headed": true
}

Boolean flags accept an optional true/false value to override config settings. For example, --headed false disables "headed": true from config. A bare --headed is equivalent to --headed true.

Auto-discovered config files that are missing are silently ignored. If --config <path> points to a missing or invalid file, agent-browser exits with an error. Extensions from user and project configs are merged (concatenated), not replaced.

Tip: If your project-level agent-browser.json contains environment-specific values (paths, proxies), consider adding it to .gitignore.

Default Timeout

The default timeout for standard operations (clicks, waits, fills, etc.) is 25 seconds. This is intentionally below the CLI's 30-second IPC read timeout so that the daemon returns a proper error instead of the CLI timing out with EAGAIN.

Override the default timeout via environment variable:

# Set a longer timeout for slow pages (in milliseconds)
export AGENT_BROWSER_DEFAULT_TIMEOUT=45000

Note: Setting this above 30000 (30s) may cause EAGAIN errors on slow operations because the CLI's read timeout will expire before the daemon responds. The CLI retries transient errors automatically, but response times will increase.

Variable	Description
`AGENT_BROWSER_DEFAULT_TIMEOUT`	Default operation timeout in ms (default: 25000)

Selectors

Refs (Recommended for AI)

Refs provide deterministic element selection from snapshots:

# 1. Get snapshot with refs
agent-browser snapshot
# Output:
# - heading "Example Domain" [ref=e1] [level=1]
# - button "Submit" [ref=e2]
# - textbox "Email" [ref=e3]
# - link "Learn more" [ref=e4]

# 2. Use refs to interact
agent-browser click @e2                   # Click the button
agent-browser fill @e3 "test@example.com" # Fill the textbox
agent-browser get text @e1                # Get heading text
agent-browser hover @e4                   # Hover the link

When a ref click is blocked by an overlay, the error includes the covering element, such as covered by <div#consent-banner>. Click the banner or dialog control first, then run snapshot again before reusing refs.

Why use refs?

Deterministic: Ref points to exact element from snapshot
Fast: No DOM re-query needed
AI-friendly: Snapshot + ref workflow is optimal for LLMs

CSS Selectors

agent-browser click "#id"
agent-browser click ".class"
agent-browser click "div > button"

Text & XPath

agent-browser click "text=Submit"
agent-browser click "xpath=//button"

Semantic Locators

agent-browser find role button click --name "Submit"
agent-browser find label "Email" fill "test@test.com"

Agent Mode

Use --json for machine-readable output:

agent-browser snapshot --json
# Returns: {"success":true,"data":{"snapshot":"...","refs":{"e1":{"role":"heading","name":"Title"},...}}}

agent-browser get text @e1 --json
agent-browser is visible @e2 --json

Optimal AI Workflow

# 1. Navigate and get snapshot
agent-browser open example.com
agent-browser snapshot -i --json   # AI parses tree and refs

# 2. AI identifies target refs from snapshot
# 3. Execute actions using refs
agent-browser click @e2
agent-browser fill @e3 "input text"

# 4. Get new snapshot if page changed
agent-browser snapshot -i --json

Command Chaining

Commands can be chained with && in a single shell invocation. The browser persists via a background daemon, so chaining is safe and more efficient:

# Open, wait for load, and snapshot in one call
agent-browser open example.com && agent-browser wait --load networkidle && agent-browser snapshot -i

# Chain multiple interactions
agent-browser fill @e1 "user@example.com" && agent-browser fill @e2 "pass" && agent-browser click @e3

# Navigate and screenshot
agent-browser open example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png

Use && when you don't need intermediate output. Run commands separately when you need to parse output first (e.g., snapshot to discover refs before interacting).

Headed Mode

Show the browser window for debugging:

agent-browser open example.com --headed

This opens a visible browser window instead of running headless.

On Linux hosts with no display (servers, containers), --headed still works: when DISPLAY is unset and Xvfb is installed, agent-browser starts a private virtual display for the browser and cleans it up on close (opt out with AGENT_BROWSER_NO_XVFB=1).

Note: Browser extensions work in both headed and headless mode (Chrome's --headless=new).

WebGPU

Headless Chrome does not expose WebGPU by default, so pages using it (three.js WebGPURenderer, Babylon.js, etc.) silently render black. The --webgpu flag enables a launch preset that makes WebGPU work, including in GPU-less containers and CI:

agent-browser --webgpu open https://my-webgpu-app.example.com
agent-browser screenshot app.png

On macOS and Windows this uses the hardware Metal/D3D backend. On Linux it routes WebGPU through SwiftShader's software Vulkan (no GPU needed), which requires the system Vulkan loader and Mesa ICD:

apt-get install -y libvulkan1 mesa-vulkan-drivers

One upstream caveat: headless Chrome cannot capture WebGPU canvas presentation in screenshots on Windows and Linux (rendering and in-page readbacks work; the capture is black). Screenshots of WebGPU pages work headless on macOS; on Windows run --headed in a logged-in desktop session; on Linux just add --headed — when no DISPLAY is set and Xvfb is installed, agent-browser starts a private virtual display automatically (opt out with AGENT_BROWSER_NO_XVFB=1).

Verify the full pipeline (adapter, render pass, and screenshot capture) with:

agent-browser doctor --webgpu

Notes for WebGPU pages:

WebGPU only exists in secure contexts (https://, http://localhost, or file://).
three.js WebGPURenderer initializes asynchronously and silently falls back to WebGL2 when no adapter is available — wait for the app to render its first frame before taking a screenshot.
To prefer a real GPU on Linux instead of SwiftShader, override both the Vulkan driver and the adapter with --args "--use-vulkan=native,--use-webgpu-adapter=default" (user args win over the preset; --use-webgpu-adapter alone still enumerates only SwiftShader).

Authenticated Sessions

Use --headers to set HTTP headers for a specific origin, enabling authentication without login flows:

# Headers are scoped to api.example.com only
agent-browser open api.example.com --headers '{"Authorization": "Bearer <token>"}'

# Requests to api.example.com include the auth header
agent-browser snapshot -i --json
agent-browser click @e2

# Navigate to another domain - headers are NOT sent (safe!)
agent-browser open other-site.com

This is useful for:

Skipping login flows - Authenticate via headers instead of UI
Switching users - Start new sessions with different auth tokens
API testing - Access protected endpoints directly
Security - Headers are scoped to the origin, not leaked to other domains

To set headers for multiple origins, use --headers with each open command:

agent-browser open api.example.com --headers '{"Authorization": "Bearer token1"}'
agent-browser open api.acme.com --headers '{"Authorization": "Bearer token2"}'

For global headers (all domains), use set headers:

agent-browser set headers '{"X-Custom-Header": "value"}'

Custom Browser Executable

Use a custom browser executable instead of the bundled Chromium. This is useful for:

Serverless deployment: Use lightweight Chromium builds like @sparticuz/chromium (~50MB vs ~684MB)
System browsers: Use an existing Chrome/Chromium installation
Custom builds: Use modified browser builds

CLI Usage

# Via flag
agent-browser --executable-path /path/to/chromium open example.com

# Via environment variable
AGENT_BROWSER_EXECUTABLE_PATH=/path/to/chromium agent-browser open example.com

Local Files

Open and interact with local files (PDFs, HTML, etc.) using file:// URLs:

# Enable file access (required for JavaScript to access local files)
agent-browser --allow-file-access open file:///path/to/document.pdf
agent-browser --allow-file-access open file:///path/to/page.html

# Take screenshot of a local PDF
agent-browser --allow-file-access open file:///Users/me/report.pdf
agent-browser screenshot report.png

The --allow-file-access flag adds Chromium flags (--allow-file-access-from-files, --allow-file-access) that allow file:// URLs to:

Load and render local files
Access other local files via JavaScript (XHR, fetch)
Load local resources (images, scripts, stylesheets)

Note: This flag only works with Chromium. For security, it's disabled by default.

CDP Mode

Connect to an existing browser via Chrome DevTools Protocol:

# Start Chrome with: google-chrome --remote-debugging-port=9222

# Connect once, then run commands without --cdp
agent-browser connect 9222
agent-browser snapshot
agent-browser tab
agent-browser close

# Or pass --cdp on each command
agent-browser --cdp 9222 snapshot

# Connect to remote browser via WebSocket URL
agent-browser --cdp "wss://your-browser-service.com/cdp?token=..." snapshot

The --cdp flag accepts either:

A port number (e.g., 9222) for local connections via http://localhost:{port}
A full WebSocket URL (e.g., wss://... or ws://...) for remote browser services

This enables control of:

Electron apps
Chrome/Chromium instances with remote debugging
WebView2 applications
Any browser exposing a CDP endpoint

Auto-Connect

Use --auto-connect to automatically discover and connect to a running Chrome instance without specifying a port:

# Auto-discover running Chrome with remote debugging
agent-browser --auto-connect open example.com
agent-browser --auto-connect snapshot

# Or via environment variable
AGENT_BROWSER_AUTO_CONNECT=1 agent-browser snapshot

Auto-connect discovers Chrome by:

Reading Chrome's DevToolsActivePort file from the default user data directory
Falling back to probing common debugging ports (9222, 9229)
If HTTP-based discovery (/json/version, /json/list) fails, falling back to a direct WebSocket connection

Streaming (Browser Preview)

Stream the browser viewport via WebSocket for live preview or "pair browsing" where a human can watch and interact alongside an AI agent.

Streaming

Every session automatically starts a WebSocket stream server on an OS-assigned port. Use stream status to see the bound port and connection state:

agent-browser stream status

To bind to a specific port, set AGENT_BROWSER_STREAM_PORT:

AGENT_BROWSER_STREAM_PORT=9223 agent-browser open example.com

Frame encoding is daemon-wide:

Variable	Default	Description
`AGENT_BROWSER_STREAM_QUALITY`	`80`	JPEG quality, 0 to 100
`AGENT_BROWSER_STREAM_MAX_WIDTH`	the viewport	Caps frame width in pixels
`AGENT_BROWSER_STREAM_MAX_HEIGHT`	the viewport	Caps frame height in pixels

Width and height cap the encoded frame and leave the page size alone, so a portrait or HiDPI viewport keeps its resolution unless you cap it. The live stream requests jpeg. An explicit screencast_start reconfigures the same screencast, so a client can see the format change mid-stream. On a busy page at 1280x720, quality 80 costs about 54 KB per frame, quality 20 about 25 KB, and quality 20 at 640x360 about 9 KB.

# Cheaper frames for a constrained link
AGENT_BROWSER_STREAM_QUALITY=20 \
AGENT_BROWSER_STREAM_MAX_WIDTH=640 \
AGENT_BROWSER_STREAM_MAX_HEIGHT=360 \
agent-browser open example.com

You can also manage streaming at runtime with stream enable, stream disable, and stream status:

agent-browser stream enable --port 9223   # Re-enable on a specific port
agent-browser stream disable              # Stop streaming for the session

The WebSocket server streams the browser viewport and accepts input events.

WebSocket Protocol

Connect to ws://localhost:9223 to receive frames and send input:

Receive frames:

{
  "type": "frame",
  "seq": 41,
  "data": "<base64-encoded-jpeg>",
  "metadata": {
    "deviceWidth": 1280,
    "deviceHeight": 720,
    "pageScaleFactor": 1,
    "offsetTop": 0,
    "scrollOffsetX": 0,
    "scrollOffsetY": 0,
    "timestamp": 1785038682238
  }
}

seq is a monotonic frame id, echoed back in an ack message under ack pacing. metadata.timestamp is the capture time in epoch milliseconds, so a client can tell how old a frame is by the time it draws it.

Send mouse events:

{
  "type": "input_mouse",
  "eventType": "mousePressed",
  "x": 100,
  "y": 200,
  "button": "left",
  "clickCount": 1
}

Send keyboard events:

{
  "type": "input_keyboard",
  "eventType": "keyDown",
  "key": "Enter",
  "code": "Enter"
}

Send touch events:

{
  "type": "input_touch",
  "eventType": "touchStart",
  "touchPoints": [{ "x": 100, "y": 200 }]
}

Cap the frame rate (per client):

{
  "type": "config",
  "maxFps": 10
}

Frames are delivered latest-first: the server picks the newest frame at send time, so frames produced while an earlier one is still being written are skipped rather than queued. maxFps (1 to 120, 0 = uncapped) limits delivery for that client only. A client that sends {"type":"config","pacing":"ack"} receives one frame at a time and acknowledges it with {"type":"ack","seq":N}, so nothing stale reaches the socket even if that client stalls; in the default push pacing, frames already handed to the transport are still delivered in order. Both settings can also be declared on the URL (ws://127.0.0.1:<port>/?pacing=ack&maxFps=10), which is the only way to cover the connection's opening frame. Input events are read on a dedicated task per connection, so clicks and keystrokes dispatch immediately even while frames are mid-write to a slow client. They are sent to the browser without waiting for its reply, so a click stays responsive behind a burst of mouse moves, and ordering is preserved.

Architecture

agent-browser uses a client-daemon architecture:

Rust CLI - Parses commands, communicates with daemon
Rust Daemon - Pure Rust daemon using direct CDP, no Node.js required

The daemon starts automatically on first command and persists between commands for fast subsequent operations. After 1 hour with no commands or dashboard input it saves configured restore state, closes the browser, and exits, so an integration that dies without calling close cannot leak the daemon and its browser indefinitely; the next command starts a fresh daemon and configured state restore works as usual. A session without --restore or another restore key does not save browser state, so its transient state and open tabs are discarded at shutdown. Set --idle-timeout to a duration such as 30s, 5m, or 1h, or set AGENT_BROWSER_IDLE_TIMEOUT_MS to a value in milliseconds. Use 0 to disable idle shutdown entirely. The default never closes a headed browser, including Safari and iOS WebDriver sessions, or a user-attached browser because those may be in direct human use. Provider-owned cloud browsers remain eligible for cleanup. An explicitly set timeout applies to every browser.

Browser Engine: Uses Chrome (from Chrome for Testing) by default. The --engine flag selects between chrome and lightpanda. Supported browsers: Chromium/Chrome (via CDP) and Safari (via WebDriver for iOS).

Platforms

Platform	Binary
macOS ARM64	Native Rust
macOS x64	Native Rust
Linux ARM64	Native Rust
Linux x64	Native Rust
Windows x64	Native Rust

Usage with AI Agents

Just ask the agent

The simplest approach is to tell your agent to use it:

Use agent-browser to test the login flow. Run agent-browser --help to see available commands.

The --help output is comprehensive and most agents can figure it out from there.

AGENTS.md / CLAUDE.md

For more consistent results, add to your project or global instructions file:

## Browser Automation

Use `agent-browser` for web automation. Run `agent-browser --help` for all commands.

Core workflow:

1. `agent-browser open <url>` - Navigate to page
2. `agent-browser snapshot -i` - Get interactive elements with refs (@e1, @e2)
3. `agent-browser click @e1` / `fill @e2 "text"` - Interact using refs
4. Re-snapshot after page changes

Integrations

iOS Simulator

Control real Mobile Safari in the iOS Simulator for authentic mobile web testing. Requires macOS with Xcode.

Setup:

# Install Appium and XCUITest driver
npm install -g appium
appium driver install xcuitest

Usage:

# 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 commands as desktop
agent-browser -p ios snapshot -i
agent-browser -p ios tap @e1
agent-browser -p ios fill @e2 "text"
agent-browser -p ios screenshot mobile.png

# Mobile-specific commands
agent-browser -p ios swipe up
agent-browser -p ios swipe down 500

# Close session
agent-browser -p ios close

Or use environment variables:

export AGENT_BROWSER_PROVIDER=ios
export AGENT_BROWSER_IOS_DEVICE="iPhone 16 Pro"
agent-browser open https://example.com

Variable	Description
`AGENT_BROWSER_PROVIDER`	Set to `ios` to enable iOS mode
`AGENT_BROWSER_IOS_DEVICE`	Device name (e.g., "iPhone 16 Pro", "iPad Pro")
`AGENT_BROWSER_IOS_UDID`	Device UDID (alternative to device name)

Supported devices: All iOS Simulators available in Xcode (iPhones, iPads), plus real iOS devices.

Note: The iOS provider boots the simulator, starts Appium, and controls Safari. First launch takes ~30-60 seconds; subsequent commands are fast.

Real Device Support

Appium also supports real iOS devices connected via USB. This requires additional one-time setup:

1. Get your device UDID:

xcrun xctrace list devices
# or
system_profiler SPUSBDataType | grep -A 5 "iPhone\|iPad"

2. Sign WebDriverAgent (one-time):

# Open the WebDriverAgent Xcode project
cd ~/.appium/node_modules/appium-xcuitest-driver/node_modules/appium-webdriveragent
open WebDriverAgent.xcodeproj

In Xcode:

Select the WebDriverAgentRunner target
Go to Signing & Capabilities
Select your Team (requires Apple Developer account, free tier works)
Let Xcode manage signing automatically

3. Use with agent-browser:

# Connect device via USB, then:
agent-browser -p ios --device "<DEVICE_UDID>" open https://example.com

# Or use the device name if unique
agent-browser -p ios --device "John's iPhone" open https://example.com

Real device notes:

First run installs WebDriverAgent to the device (may require Trust prompt)
Device must be unlocked and connected via USB
Slightly slower initial connection than simulator
Tests against real Safari performance and behavior

Browserless

Browserless provides cloud browser infrastructure with a Sessions API. Use it when running agent-browser in environments where a local browser isn't available.

To enable Browserless, use the -p flag:

export BROWSERLESS_API_KEY="your-api-token"
agent-browser -p browserless open https://example.com

Or use environment variables for CI/scripts:

export AGENT_BROWSER_PROVIDER=browserless
export BROWSERLESS_API_KEY="your-api-token"
agent-browser open https://example.com

Optional configuration via environment variables:

Variable	Description	Default
`BROWSERLESS_API_URL`	Base API URL (for custom regions or self-hosted)	`https://production-sfo.browserless.io`
`BROWSERLESS_BROWSER_TYPE`	Type of browser to use (chromium or chrome)	chromium
`BROWSERLESS_TTL`	Session TTL in milliseconds	`300000`
`BROWSERLESS_STEALTH`	Enable stealth mode (`true`/`false`)	`true`

When enabled, agent-browser connects to a Browserless cloud session instead of launching a local browser. All commands work identically.

Get your API token from the Browserless Dashboard.

Browserbase

Browserbase provides remote browser infrastructure to make deployment of agentic browsing agents easy. Use it when running the agent-browser CLI in an environment where a local browser isn't feasible.

To enable Browserbase, use the -p flag:

export BROWSERBASE_API_KEY="your-api-key"
agent-browser -p browserbase open https://example.com

Or use environment variables for CI/scripts:

export AGENT_BROWSER_PROVIDER=browserbase
export BROWSERBASE_API_KEY="your-api-key"
agent-browser open https://example.com

When enabled, agent-browser connects to a Browserbase session instead of launching a local browser. All commands work identically.

Get your API key from the Browserbase Dashboard.

Browser Use

Browser Use provides cloud browser infrastructure for AI agents. Use it when running agent-browser in environments where a local browser isn't available (serverless, CI/CD, etc.).

To enable Browser Use, use the -p flag:

export BROWSER_USE_API_KEY="your-api-key"
agent-browser -p browseruse open https://example.com

Or use environment variables for CI/scripts:

export AGENT_BROWSER_PROVIDER=browseruse
export BROWSER_USE_API_KEY="your-api-key"
agent-browser open https://example.com

When enabled, agent-browser connects to a Browser Use cloud session instead of launching a local browser. All commands work identically.

Get your API key from the Browser Use Cloud Dashboard. Free credits are available to get started, with pay-as-you-go pricing after.

Kernel

Kernel provides cloud browser infrastructure for AI agents with features like stealth mode and persistent profiles.

To enable Kernel, use the -p flag:

export KERNEL_API_KEY="your-api-key"
agent-browser -p kernel open https://example.com

Or use environment variables for CI/scripts:

export AGENT_BROWSER_PROVIDER=kernel
export KERNEL_API_KEY="your-api-key"
agent-browser open https://example.com

Optional configuration via environment variables:

Variable	Description	Default
`KERNEL_HEADLESS`	Run browser in headless mode (`true`/`false`)	`true`
`KERNEL_STEALTH`	Enable stealth mode to avoid bot detection (`true`/`false`)	`false`
`KERNEL_TIMEOUT_SECONDS`	Session timeout in seconds	`300`
`KERNEL_PROFILE_NAME`	Browser profile name for persistent cookies/logins (created if it doesn't exist)	(none)

When enabled, agent-browser connects to a Kernel cloud session instead of launching a local browser. All commands work identically.

Profile Persistence: When KERNEL_PROFILE_NAME is set, the profile will be created if it doesn't already exist. Cookies, logins, and session data are automatically saved back to the profile when the browser session ends, making them available for future sessions.

Get your API key from the Kernel Dashboard.

AgentCore

AWS Bedrock AgentCore provides cloud browser sessions with SigV4 authentication.

To enable AgentCore, use the -p flag:

agent-browser -p agentcore open https://example.com

Or use environment variables for CI/scripts:

export AGENT_BROWSER_PROVIDER=agentcore
agent-browser open https://example.com

Credentials are automatically resolved from environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY) or the AWS CLI (aws configure export-credentials), which supports SSO, profiles, and IAM roles.

Optional configuration via environment variables:

Variable	Description	Default
`AGENTCORE_REGION`	AWS region for the AgentCore endpoint	`us-east-1`
`AGENTCORE_BROWSER_ID`	Browser identifier	`aws.browser.v1`
`AGENTCORE_PROFILE_ID`	Browser profile for persistent state (cookies, localStorage)	(none)
`AGENTCORE_SESSION_TIMEOUT`	Session timeout in seconds	`3600`
`AWS_PROFILE`	AWS CLI profile for credential resolution	`default`

Browser profiles: When AGENTCORE_PROFILE_ID is set, browser state (cookies, localStorage) is persisted across sessions automatically.

When enabled, agent-browser connects to an AgentCore cloud browser session instead of launching a local browser. All commands work identically.

Requirements

Chrome - Run agent-browser install to download Chrome from Chrome for Testing (Google's official automation channel). Existing Chrome, Brave, Playwright, and Puppeteer installations are detected automatically. No Playwright or Node.js required for the daemon.

Limitations & Notes

Clicks fail early when another element covers the target's click point. Dismiss the covering element, then take a fresh snapshot before retrying.
Headless Chromium screenshots hide native scrollbars by default. Use --hide-scrollbars false to keep them.
Annotated screenshots are supported on CDP-backed browser path (Chrome/Lightpanda), not on Safari/WebDriver.
Accessibility audits (a11y) require a CDP browser and are not available with Safari or iOS WebDriver sessions.
React commands require --enable react-devtools at launch.
WebGPU screenshots have caveats on Windows and Linux (black capture in headless mode). Use --headed on those platforms.
--allowed-domains cannot be used with pre-existing CDP sessions, auto-connect, Chrome profiles, restore/state replay, direct-page provider plugins, or iOS/Safari.
State files contain session tokens in plaintext unless encrypted with AGENT_BROWSER_ENCRYPTION_KEY.
The default timeout for operations is 25 seconds. Setting it above 30 seconds may cause EAGAIN errors.
The daemon shuts down after 1 hour of inactivity by default (configurable via --idle-timeout). Headed browsers and user-attached browsers are not subject to idle shutdown unless explicitly set.
On Linux, --headed with no display requires Xvfb.
--auto-connect discovers Chrome by reading DevToolsActivePort file or probing common ports.
--allow-file-access only works with Chromium.
The iOS provider requires macOS with Xcode and Appium.
Cloud providers (Browserless, Browserbase, Browser Use, Kernel, AgentCore) require API keys or credentials.
The read command with --llms and --require-md with no URL uses the active tab URL.
Batch execution with --json accepts commands as JSON arrays via stdin.
Tab ids are stable strings starting with t (e.g., t1). Positional integers are not accepted.
Labels for tabs are user-assigned and persist across navigation.
The dashboard runs on port 4848 by default.
AI chat requires Vercel AI Gateway configuration.
The MCP server defaults to core tools profile.
Plugin system uses a stdio JSON protocol.
The agent-browser install command downloads Chrome from Chrome for Testing.
The agent-browser upgrade command detects installation method and updates accordingly.
The agent-browser doctor command diagnoses and can fix installation issues.
The agent-browser skills command lists and retrieves bundled skill content.
The agent-browser mcp command starts an MCP stdio server.
The agent-browser chat command requires model configuration (environment variables or --model).
The agent-browser dashboard command starts a background web server.
The agent-browser connect command connects to an existing CDP endpoint.
The agent-browser stream command enables/disables WebSocket streaming.
The agent-browser diff command compares snapshots, screenshots, or URLs.
The agent-browser eval command runs JavaScript in the page context.
The agent-browser set command changes browser settings at runtime.
The agent-browser tab command manages tabs and windows.
The agent-browser frame command switches to iframes.
The agent-browser dialog command handles JavaScript dialogs.
The agent-browser network command intercepts and inspects network requests.
The agent-browser cookies and agent-browser storage commands manage cookies and storage.
The agent-browser keyboard and agent-browser mouse commands simulate input.
The agent-browser clipboard commands read/write clipboard.
The agent-browser batch command executes multiple commands in one invocation.
The agent-browser press command presses a key.
The agent-browser type and agent-browser fill commands input text.
The agent-browser upload command uploads files.
The agent-browser drag command performs drag-and-drop.
The agent-browser scroll and agent-browser scrollintoview commands scroll.
The agent-browser select command selects dropdown options.
The agent-browser check and agent-browser uncheck commands handle checkboxes.
The agent-browser hover command hovers over elements.
The agent-browser find command locates elements by semantic criteria.
The agent-browser is visible, is enabled, is checked commands check element state.
The agent-browser wait command waits for conditions.
The agent-browser screenshot command captures screenshots.
The agent-browser pdf command saves page as PDF.
The agent-browser snapshot command outputs accessibility tree.
The agent-browser read command fetches agent-friendly text.
The agent-browser open command launches browser and navigates.
The agent-browser close command closes browser.
The agent-browser back, forward, reload commands navigate.
The agent-browser pushstate command handles SPA navigation.
The agent-browser get commands retrieve page information.

License

Apache-2.0