Browser (clawd-managed)

Clawdbot can run a dedicated Chrome/Chromium profile that the agent controls. It is isolated from your personal browser and is managed through a small local control server. Beginner view:

Think of it as a separate, agent-only browser.
It does not touch your personal Chrome profile.
The agent can open tabs, read pages, click, and type in a safe lane.

What you get

A separate browser profile named clawd (orange accent by default).
Deterministic tab control (list/open/focus/close).
Agent actions (click/type/drag/select), snapshots, screenshots, PDFs.
Optional multi-profile support (clawd, work, remote, …).

This browser is not your daily driver. It is a safe, isolated surface for agent automation and verification.

Quick start

clawdbot browser --browser-profile clawd status
clawdbot browser --browser-profile clawd start
clawdbot browser --browser-profile clawd open https://example.com
clawdbot browser --browser-profile clawd snapshot

If you get “Browser disabled”, enable it in config (see below) and restart the Gateway.

Configuration

Browser settings live in ~/.clawdbot/clawdbot.json.

{
  browser: {
    enabled: true,                    // default: true
    controlUrl: "http://127.0.0.1:18791",
    cdpUrl: "http://127.0.0.1:18792", // defaults to controlUrl + 1
    defaultProfile: "chrome",
    color: "#FF4500",
    headless: false,
    noSandbox: false,
    attachOnly: false,
    executablePath: "/Applications/Chromium.app/Contents/MacOS/Chromium",
    profiles: {
      clawd: { cdpPort: 18800, color: "#FF4500" },
      work: { cdpPort: 18801, color: "#0066CC" },
      remote: { cdpUrl: "http://10.0.0.42:9222", color: "#00AA00" }
    }
  }
}

Notes:

controlUrl defaults to http://127.0.0.1:18791.
If you override the Gateway port (gateway.port or CLAWDBOT_GATEWAY_PORT), the default browser ports shift to stay in the same “family” (control = gateway + 2).
cdpUrl defaults to controlUrl + 1 when unset.
attachOnly: true means “never launch Chrome; only attach if it is already running.”
color + per-profile color tint the browser UI so you can see which profile is active.

Local vs remote control

Local control (default): controlUrl is loopback (127.0.0.1/localhost). The Gateway starts the control server and can launch Chrome.
Remote control: controlUrl is non-loopback. The Gateway does not start a local server; it assumes you are pointing at an existing server elsewhere.
Remote CDP: set browser.profiles.<name>.cdpUrl (or browser.cdpUrl) to attach to a remote Chrome. In this case, Clawdbot will not launch a local browser.

Remote browser (control server)

You can run the browser control server on another machine and point your Gateway at it with a remote controlUrl. This lets the agent drive a browser outside the host (lab box, VM, remote desktop, etc.). Key points:

The control server speaks to Chrome/Chromium via CDP.
The Gateway only needs the HTTP control URL.
Profiles are resolved on the control server side.

Example:

{
  browser: {
    enabled: true,
    controlUrl: "http://10.0.0.42:18791",
    defaultProfile: "work"
  }
}

Use profiles.<name>.cdpUrl for remote CDP if you want the Gateway to talk directly to a Chrome instance without a remote control server.

Running the control server on the browser machine

Run a standalone browser control server (recommended when your Gateway is remote):

# on the machine that runs Chrome
clawdbot browser serve --bind <browser-host> --port 18791 --token <token>

Then point your Gateway at it:

{
  browser: {
    enabled: true,
    controlUrl: "http://<browser-host>:18791",

    // Option A (recommended): keep token in env on the Gateway
    // (avoid writing secrets into config files)
    // controlToken: "<token>"
  }
}

And set the auth token in the Gateway environment:

export CLAWDBOT_BROWSER_CONTROL_TOKEN="<token>"

Option B: store the token in the Gateway config instead (same shared token):

{
  browser: {
    enabled: true,
    controlUrl: "http://<browser-host>:18791",
    controlToken: "<token>"
  }
}

Security

This section covers the browser control server (browser.controlUrl) used for agent browser automation. Key ideas:

Treat the browser control server like an admin API: private network only.
Use token auth always when the server is reachable off-machine.
Prefer Tailnet-only connectivity over LAN exposure.

Tokens (what is shared with what?)

browser.controlToken / CLAWDBOT_BROWSER_CONTROL_TOKEN is only for authenticating browser control HTTP requests to browser.controlUrl.
It is not the Gateway token (gateway.auth.token) and not a node pairing token.
You can reuse the same string value, but it’s better to keep them separate to reduce blast radius.

Binding (don’t expose to your LAN by accident)

Recommended:

Keep clawdbot browser serve bound to loopback (127.0.0.1) and publish it via Tailscale.
Or bind to a Tailnet IP only (never 0.0.0.0) and require a token.

Avoid:

--bind 0.0.0.0 (LAN-visible). Even with token auth, traffic is plain HTTP unless you also add TLS.

TLS / HTTPS (recommended approach: terminate in front)

Best practice here: keep clawdbot browser serve on HTTP and terminate TLS in front. If you’re already using Tailscale, you have two good options:

Tailnet-only, still HTTP (transport is encrypted by Tailscale):

Keep controlUrl as http://… but ensure it’s only reachable over your tailnet.

Serve HTTPS via Tailscale (nice UX: https://… URL):

# on the browser machine
clawdbot browser serve --bind 127.0.0.1 --port 18791 --token <token>
tailscale serve https / http://127.0.0.1:18791

Then set your Gateway config browser.controlUrl to the HTTPS URL (MagicDNS/ts.net) and keep using the same token. Notes:

Do not use Tailscale Funnel for this unless you explicitly want to make the endpoint public.
For Tailnet setup/background, see Gateway web surfaces and the Gateway CLI.

Profiles (multi-browser)

Clawdbot supports multiple named profiles (routing configs). Profiles can be:

clawd-managed: a dedicated Chrome instance with its own user data directory + CDP port
remote: an explicit CDP URL (Chrome running elsewhere)
extension relay: your existing Chrome tab(s) via the local relay + Chrome extension

Defaults:

The clawd profile is auto-created if missing.
The chrome profile is built-in for the Chrome extension relay (points at http://127.0.0.1:18792 by default).
Local CDP ports allocate from 18800–18899 by default.
Deleting a profile moves its local data directory to Trash.

All control endpoints accept ?profile=<name>; the CLI uses --browser-profile.

Chrome extension relay (use your existing Chrome)

Clawdbot can also drive your existing Chrome tabs (no separate “clawd” Chrome instance) via a local CDP relay + a Chrome extension. Full guide: Chrome extension Flow:

You run a browser control server (Gateway on the same machine, or clawdbot browser serve).
A local relay server listens at a loopback cdpUrl (default: http://127.0.0.1:18792).
You click the Clawdbot Browser Relay extension icon on a tab to attach (it does not auto-attach).
The agent controls that tab via the normal browser tool, by selecting the right profile.

If the Gateway runs on the same machine as Chrome (default setup), you usually do not need clawdbot browser serve. Use browser serve only when the Gateway runs elsewhere (remote mode).

Sandboxed sessions

If the agent session is sandboxed, the browser tool may default to target="sandbox" (sandbox browser). Chrome extension relay takeover requires host browser control, so either:

run the session unsandboxed, or
set agents.defaults.sandbox.browser.allowHostControl: true and use target="host" when calling the tool.

Setup

Load the extension (dev/unpacked):

clawdbot browser extension install

Chrome → chrome://extensions → enable “Developer mode”
“Load unpacked” → select the directory printed by clawdbot browser extension path
Pin the extension, then click it on the tab you want to control (badge shows ON).

Use it:

CLI: clawdbot browser --browser-profile chrome tabs
Agent tool: browser with profile="chrome"

Optional: if you want a different name or relay port, create your own profile:

clawdbot browser create-profile \
  --name my-chrome \
  --driver extension \
  --cdp-url http://127.0.0.1:18792 \
  --color "#00AA00"

Notes:

This mode relies on Playwright-on-CDP for most operations (screenshots/snapshots/actions).
Detach by clicking the extension icon again.

Isolation guarantees

Dedicated user data dir: never touches your personal Chrome profile.
Dedicated ports: avoids 9222 to prevent collisions with dev workflows.
Deterministic tab control: target tabs by targetId, not “last tab”.

Browser selection

When launching locally, Clawdbot picks the first available:

Chrome Canary
Chromium
Chrome

You can override with browser.executablePath. Platforms:

macOS: checks /Applications and ~/Applications.
Linux: looks for google-chrome, chromium, etc.
Windows: checks common install locations.

Control API (optional)

If you want to integrate directly, the browser control server exposes a small HTTP API:

Status/start/stop: GET /, POST /start, POST /stop
Tabs: GET /tabs, POST /tabs/open, POST /tabs/focus, DELETE /tabs/:targetId
Snapshot/screenshot: GET /snapshot, POST /screenshot
Actions: POST /navigate, POST /act
Hooks: POST /hooks/file-chooser, POST /hooks/dialog
Downloads: POST /download, POST /wait/download
Debugging: GET /console, POST /pdf
Debugging: GET /errors, GET /requests, POST /trace/start, POST /trace/stop, POST /highlight
Network: POST /response/body
State: GET /cookies, POST /cookies/set, POST /cookies/clear
State: GET /storage/:kind, POST /storage/:kind/set, POST /storage/:kind/clear
Settings: POST /set/offline, POST /set/headers, POST /set/credentials, POST /set/geolocation, POST /set/media, POST /set/timezone, POST /set/locale, POST /set/device

All endpoints accept ?profile=<name>.

Playwright requirement

Some features (navigate/act/AI snapshot/role snapshot, element screenshots, PDF) require Playwright. If Playwright isn’t installed, those endpoints return a clear 501 error. ARIA snapshots and basic screenshots still work for clawd-managed Chrome. For the Chrome extension relay driver, ARIA snapshots and screenshots require Playwright.

How it works (internal)

High-level flow:

A small control server accepts HTTP requests.
It connects to Chrome/Chromium via CDP.
For advanced actions (click/type/snapshot/PDF), it uses Playwright on top of CDP.
When Playwright is missing, only non-Playwright operations are available.

This design keeps the agent on a stable, deterministic interface while letting you swap local/remote browsers and profiles.

CLI quick reference

All commands accept --browser-profile <name> to target a specific profile. All commands also accept --json for machine-readable output (stable payloads). Basics:

clawdbot browser status
clawdbot browser start
clawdbot browser stop
clawdbot browser tabs
clawdbot browser tab
clawdbot browser tab new
clawdbot browser tab select 2
clawdbot browser tab close 2
clawdbot browser open https://example.com
clawdbot browser focus abcd1234
clawdbot browser close abcd1234

Inspection:

clawdbot browser screenshot
clawdbot browser screenshot --full-page
clawdbot browser screenshot --ref 12
clawdbot browser screenshot --ref e12
clawdbot browser snapshot
clawdbot browser snapshot --format aria --limit 200
clawdbot browser snapshot --interactive --compact --depth 6
clawdbot browser snapshot --efficient
clawdbot browser snapshot --labels
clawdbot browser snapshot --selector "#main" --interactive
clawdbot browser snapshot --frame "iframe#main" --interactive
clawdbot browser console --level error
clawdbot browser errors --clear
clawdbot browser requests --filter api --clear
clawdbot browser pdf
clawdbot browser responsebody "**/api" --max-chars 5000

Actions:

clawdbot browser navigate https://example.com
clawdbot browser resize 1280 720
clawdbot browser click 12 --double
clawdbot browser click e12 --double
clawdbot browser type 23 "hello" --submit
clawdbot browser press Enter
clawdbot browser hover 44
clawdbot browser scrollintoview e12
clawdbot browser drag 10 11
clawdbot browser select 9 OptionA OptionB
clawdbot browser download e12 /tmp/report.pdf
clawdbot browser waitfordownload /tmp/report.pdf
clawdbot browser upload /tmp/file.pdf
clawdbot browser fill --fields '[{"ref":"1","type":"text","value":"Ada"}]'
clawdbot browser dialog --accept
clawdbot browser wait --text "Done"
clawdbot browser wait "#main" --url "**/dash" --load networkidle --fn "window.ready===true"
clawdbot browser evaluate --fn '(el) => el.textContent' --ref 7
clawdbot browser highlight e12
clawdbot browser trace start
clawdbot browser trace stop

State:

clawdbot browser cookies
clawdbot browser cookies set session abc123 --url "https://example.com"
clawdbot browser cookies clear
clawdbot browser storage local get
clawdbot browser storage local set theme dark
clawdbot browser storage session clear
clawdbot browser set offline on
clawdbot browser set headers --json '{"X-Debug":"1"}'
clawdbot browser set credentials user pass
clawdbot browser set credentials --clear
clawdbot browser set geo 37.7749 -122.4194 --origin "https://example.com"
clawdbot browser set geo --clear
clawdbot browser set media dark
clawdbot browser set timezone America/New_York
clawdbot browser set locale en-US
clawdbot browser set device "iPhone 14"

Notes:

upload and dialog are arming calls; run them before the click/press that triggers the chooser/dialog.
upload can also set file inputs directly via --input-ref or --element.
snapshot:
- --format ai (default when Playwright is installed): returns an AI snapshot with numeric refs (aria-ref="<n>").
- --format aria: returns the accessibility tree (no refs; inspection only).
- --efficient (or --mode efficient): compact role snapshot preset (interactive + compact + depth + lower maxChars).
- Role snapshot options (--interactive, --compact, --depth, --selector) force a role-based snapshot with refs like ref=e12.
- --frame "<iframe selector>" scopes role snapshots to an iframe (pairs with role refs like e12).
- --interactive outputs a flat, easy-to-pick list of interactive elements (best for driving actions).
- --labels adds a viewport-only screenshot with overlayed ref labels (prints MEDIA:<path>).
click/type/etc require a ref from snapshot (either numeric 12 or role ref e12). CSS selectors are intentionally not supported for actions.

Snapshots and refs

Clawdbot supports two “snapshot” styles:

AI snapshot (numeric refs): clawdbot browser snapshot (default; --format ai)
- Output: a text snapshot that includes numeric refs.
- Actions: clawdbot browser click 12, clawdbot browser type 23 "hello".
- Internally, the ref is resolved via Playwright’s aria-ref.
Role snapshot (role refs like e12): clawdbot browser snapshot --interactive (or --compact, --depth, --selector, --frame)
- Output: a role-based list/tree with [ref=e12] (and optional [nth=1]).
- Actions: clawdbot browser click e12, clawdbot browser highlight e12.
- Internally, the ref is resolved via getByRole(...) (plus nth() for duplicates).
- Add --labels to include a viewport screenshot with overlayed e12 labels.

Ref behavior:

Refs are not stable across navigations; if something fails, re-run snapshot and use a fresh ref.
If the role snapshot was taken with --frame, role refs are scoped to that iframe until the next role snapshot.

Wait power-ups

You can wait on more than just time/text:

Wait for URL (globs supported by Playwright):
- clawdbot browser wait --url "**/dash"
Wait for load state:
- clawdbot browser wait --load networkidle
Wait for a JS predicate:
- clawdbot browser wait --fn "window.ready===true"
Wait for a selector to become visible:
- clawdbot browser wait "#main"

These can be combined:

clawdbot browser wait "#main" \
  --url "**/dash" \
  --load networkidle \
  --fn "window.ready===true" \
  --timeout-ms 15000

Debug workflows

When an action fails (e.g. “not visible”, “strict mode violation”, “covered”):

clawdbot browser snapshot --interactive
Use click <ref> / type <ref> (prefer role refs in interactive mode)
If it still fails: clawdbot browser highlight <ref> to see what Playwright is targeting
If the page behaves oddly:
- clawdbot browser errors --clear
- clawdbot browser requests --filter api --clear
For deep debugging: record a trace:
- clawdbot browser trace start
- reproduce the issue
- clawdbot browser trace stop (prints TRACE:<path>)

JSON output

--json is for scripting and structured tooling. Examples:

clawdbot browser status --json
clawdbot browser snapshot --interactive --json
clawdbot browser requests --filter api --json
clawdbot browser cookies --json

Role snapshots in JSON include refs plus a small stats block (lines/chars/refs/interactive) so tools can reason about payload size and density.

State and environment knobs

These are useful for “make the site behave like X” workflows:

Cookies: cookies, cookies set, cookies clear
Storage: storage local|session get|set|clear
Offline: set offline on|off
Headers: set headers --json '{"X-Debug":"1"}' (or --clear)
HTTP basic auth: set credentials user pass (or --clear)
Geolocation: set geo <lat> <lon> --origin "https://example.com" (or --clear)
Media: set media dark|light|no-preference|none
Timezone / locale: set timezone ..., set locale ...
Device / viewport:
- set device "iPhone 14" (Playwright device presets)
- set viewport 1280 720

Security & privacy

The clawd browser profile may contain logged-in sessions; treat it as sensitive.
For logins and anti-bot notes (X/Twitter, etc.), see Browser login + X/Twitter posting.
Keep control URLs loopback-only unless you intentionally expose the server.
Remote CDP endpoints are powerful; tunnel and protect them.

Troubleshooting

For Linux-specific issues (especially snap Chromium), see Browser troubleshooting.

Agent tools + how control works

The agent gets one tool for browser automation:

browser — status/start/stop/tabs/open/focus/close/snapshot/screenshot/navigate/act

How it maps:

browser snapshot returns a stable UI tree (AI or ARIA).
browser act uses the snapshot ref IDs to click/type/drag/select.
browser screenshot captures pixels (full page or element).
browser accepts:
- profile to choose a named browser profile (host or remote control server).
- target (sandbox | host | custom) to select where the browser lives.
- controlUrl sets target: "custom" implicitly (remote control server).
- In sandboxed sessions, target: "host" requires agents.defaults.sandbox.browser.allowHostControl=true.
- If target is omitted: sandboxed sessions default to sandbox, non-sandbox sessions default to host.
- Sandbox allowlists can restrict target: "custom" to specific URLs/hosts/ports.
- Defaults: allowlists unset (no restriction), and sandbox host control is disabled.

This keeps the agent deterministic and avoids brittle selectors.

Start Here

Install & Updates

CLI

Core Concepts

Gateway & Ops

Web & Interfaces

Channels

Providers

Automation & Hooks

Tools & Skills

Nodes & Media

Platforms

macOS Companion App

Reference & Templates

​Browser (clawd-managed)

​What you get

​Quick start

​Configuration

​Local vs remote control

​Remote browser (control server)

​Running the control server on the browser machine

​Security

​Tokens (what is shared with what?)

​Binding (don’t expose to your LAN by accident)

​TLS / HTTPS (recommended approach: terminate in front)

​Profiles (multi-browser)

​Chrome extension relay (use your existing Chrome)

​Sandboxed sessions

​Setup

​Isolation guarantees

​Browser selection

​Control API (optional)

​Playwright requirement

​How it works (internal)

​CLI quick reference

​Snapshots and refs

​Wait power-ups

​Debug workflows

​JSON output

​State and environment knobs

​Security & privacy

​Troubleshooting

​Agent tools + how control works

Browser (clawd-managed)

What you get

Quick start

Configuration

Local vs remote control

Remote browser (control server)

Running the control server on the browser machine

Security

Tokens (what is shared with what?)

Binding (don’t expose to your LAN by accident)

TLS / HTTPS (recommended approach: terminate in front)

Profiles (multi-browser)

Chrome extension relay (use your existing Chrome)

Sandboxed sessions

Setup

Isolation guarantees

Browser selection

Control API (optional)

Playwright requirement

How it works (internal)

CLI quick reference

Snapshots and refs

Wait power-ups

Debug workflows

JSON output

State and environment knobs

Security & privacy

Troubleshooting

Agent tools + how control works