Browser (croc-managed)

crocbot can run a dedicated Chrome/Brave/Edge/Chromium profile that the agent controls. It is isolated from your personal browser and is managed through a small local control service inside the Gateway (loopback only). Beginner view:

Think of it as a separate, agent-only browser.
The croc profile does not touch your personal browser profile.
The agent can open tabs, read pages, click, and type in a safe lane.
The default chrome profile uses the system default Chromium browser via the extension relay; switch to croc for the isolated managed browser.

What you get

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

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

Quick start

crocbot browser --browser-profile croc status
crocbot browser --browser-profile croc start
crocbot browser --browser-profile croc open https://example.com
crocbot browser --browser-profile croc snapshot

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

Profiles: `croc` vs `chrome`

croc: managed, isolated browser (no extension required).
chrome: extension relay to your system browser (requires the crocbot extension to be attached to a tab).

Set browser.defaultProfile: "croc" if you want managed mode by default.

Configuration

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

{
  browser: {
    enabled: true,                    // default: true
    // cdpUrl: "http://127.0.0.1:18792", // legacy single-profile override
    remoteCdpTimeoutMs: 1500,         // remote CDP HTTP timeout (ms)
    remoteCdpHandshakeTimeoutMs: 3000, // remote CDP WebSocket handshake timeout (ms)
    defaultProfile: "chrome",
    color: "#FF4500",
    headless: false,
    noSandbox: false,
    attachOnly: false,
    executablePath: "/Applications/Brave Browser.app/Contents/MacOS/Brave Browser",
    profiles: {
      croc: { cdpPort: 18800, color: "#FF4500" },
      work: { cdpPort: 18801, color: "#0066CC" },
      remote: { cdpUrl: "http://10.0.0.42:9222", color: "#00AA00" }
    }
  }
}

Notes:

The browser control service binds to loopback on a port derived from gateway.port (default: 18791, which is gateway + 2). The relay uses the next port (18792).
If you override the Gateway port (gateway.port or CROCBOT_GATEWAY_PORT), the derived browser ports shift to stay in the same “family”.
cdpUrl defaults to the relay port when unset.
remoteCdpTimeoutMs applies to remote (non-loopback) CDP reachability checks.
remoteCdpHandshakeTimeoutMs applies to remote CDP WebSocket reachability checks.
attachOnly: true means “never launch a local browser; only attach if it is already running.”
color + per-profile color tint the browser UI so you can see which profile is active.
Default profile is chrome (extension relay). Use defaultProfile: "croc" for the managed browser.
Auto-detect order: system default browser if Chromium-based; otherwise Chrome → Brave → Edge → Chromium → Chrome Canary.
Local croc profiles auto-assign cdpPort/cdpUrl — set those only for remote CDP.

Use Brave (or another Chromium-based browser)

If your system default browser is Chromium-based (Chrome/Brave/Edge/etc), crocbot uses it automatically. Set browser.executablePath to override auto-detection: CLI example:

crocbot config set browser.executablePath "/usr/bin/google-chrome"

// macOS
{
  browser: {
    executablePath: "/Applications/Brave Browser.app/Contents/MacOS/Brave Browser"
  }
}

// Windows
{
  browser: {
    executablePath: "C:\\Program Files\\BraveSoftware\\Brave-Browser\\Application\\brave.exe"
  }
}

// Linux
{
  browser: {
    executablePath: "/usr/bin/brave-browser"
  }
}

Local vs remote control

Local control (default): the Gateway starts the loopback control service and can launch a local browser.
Remote control (node host): run a node host on the machine that has the browser; the Gateway proxies browser actions to it.
Remote CDP: set browser.profiles.<name>.cdpUrl (or browser.cdpUrl) to attach to a remote Chromium-based browser. In this case, crocbot will not launch a local browser.

Remote CDP URLs can include auth:

Query tokens (e.g., https://provider.example?token=<token>)
HTTP Basic auth (e.g., https://user:pass@provider.example)

crocbot preserves the auth when calling /json/* endpoints and when connecting to the CDP WebSocket. Prefer environment variables or secrets managers for tokens instead of committing them to config files.

Node browser proxy (zero-config default)

If you run a node host on the machine that has your browser, crocbot can auto-route browser tool calls to that node without any extra browser config. This is the default path for remote gateways. Notes:

The node host exposes its local browser control server via a proxy command.
Profiles come from the node’s own browser.profiles config (same as local).
Disable if you don’t want it:
- On the node: nodeHost.browserProxy.enabled=false
- On the gateway: gateway.nodes.browser.mode="off"

Browserless (hosted remote CDP)

Browserless is a hosted Chromium service that exposes CDP endpoints over HTTPS. You can point a crocbot browser profile at a Browserless region endpoint and authenticate with your API key. Example:

{
  browser: {
    enabled: true,
    defaultProfile: "browserless",
    remoteCdpTimeoutMs: 2000,
    remoteCdpHandshakeTimeoutMs: 4000,
    profiles: {
      browserless: {
        cdpUrl: "https://production-sfo.browserless.io?token=<BROWSERLESS_API_KEY>",
        color: "#00AA00"
      }
    }
  }
}

Notes:

Replace <BROWSERLESS_API_KEY> with your real Browserless token.
Choose the region endpoint that matches your Browserless account (see their docs).

Security

Key ideas:

Browser control is loopback-only; access flows through the Gateway’s auth.
Keep the Gateway and any node hosts on a private network (Tailscale); avoid public exposure.
Treat remote CDP URLs/tokens as secrets; prefer env vars or a secrets manager.

Remote CDP tips:

Prefer HTTPS endpoints and short-lived tokens where possible.
Avoid embedding long-lived tokens directly in config files.

Profiles (multi-browser)

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

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

Defaults:

The croc 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)

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

The Gateway runs locally (same machine) or a node host runs on the browser machine.
A local relay server listens at a loopback cdpUrl (default: http://127.0.0.1:18792).
You click the crocbot 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 elsewhere, run a node host on the browser machine so the Gateway can proxy browser actions.

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):

crocbot browser extension install

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

Use it:

CLI: crocbot 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:

crocbot 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 browser 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, crocbot picks the first available:

Chrome
Brave
Edge
Chromium
Chrome Canary

You can override with browser.executablePath. Platforms:

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

Control API (optional)

For local integrations only, the Gateway exposes a small loopback 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 croc-managed Chrome. For the Chrome extension relay driver, ARIA snapshots and screenshots require Playwright. If you see Playwright is not available in this gateway build, install the full Playwright package (not playwright-core) and restart the gateway, or reinstall crocbot with browser support.

How it works (internal)

High-level flow:

A small control server accepts HTTP requests.
It connects to Chromium-based browsers (Chrome/Brave/Edge/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:

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

Inspection:

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

Actions:

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

State:

crocbot browser cookies
crocbot browser cookies set session abc123 --url "https://example.com"
crocbot browser cookies clear
crocbot browser storage local get
crocbot browser storage local set theme dark
crocbot browser storage session clear
crocbot browser set offline on
crocbot browser set headers --json '{"X-Debug":"1"}'
crocbot browser set credentials user pass
crocbot browser set credentials --clear
crocbot browser set geo 37.7749 -122.4194 --origin "https://example.com"
crocbot browser set geo --clear
crocbot browser set media dark
crocbot browser set timezone America/New_York
crocbot browser set locale en-US
crocbot 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).
- Config default (tool/CLI only): set browser.snapshotDefaults.mode: "efficient" to use efficient snapshots when the caller does not pass a mode (see Gateway configuration).
- 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

crocbot supports two “snapshot” styles:

AI snapshot (numeric refs): crocbot browser snapshot (default; --format ai)
- Output: a text snapshot that includes numeric refs.
- Actions: crocbot browser click 12, crocbot browser type 23 "hello".
- Internally, the ref is resolved via Playwright’s aria-ref.
Role snapshot (role refs like e12): crocbot browser snapshot --interactive (or --compact, --depth, --selector, --frame)
- Output: a role-based list/tree with [ref=e12] (and optional [nth=1]).
- Actions: crocbot browser click e12, crocbot 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):
- crocbot browser wait --url "**/dash"
Wait for load state:
- crocbot browser wait --load networkidle
Wait for a JS predicate:
- crocbot browser wait --fn "window.ready===true"
Wait for a selector to become visible:
- crocbot browser wait "#main"

These can be combined:

crocbot 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”):

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

JSON output

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

crocbot browser status --json
crocbot browser snapshot --interactive --json
crocbot browser requests --filter api --json
crocbot 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 croc browser profile may contain logged-in sessions; treat it as sensitive.
browser act kind=evaluate / crocbot browser evaluate and wait --fn execute arbitrary JavaScript in the page context. Prompt injection can steer this. Disable it with browser.evaluateEnabled=false if you do not need it.
For logins and anti-bot notes (X/Twitter, etc.), see Browser login + X/Twitter posting.
Keep the Gateway/node host private (loopback or tailnet-only).
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 (croc, chrome, or remote CDP).
- target (sandbox | host | node) to select where the browser lives.
- 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.
- If a browser-capable node is connected, the tool may auto-route to it unless you pin target="host" or target="node".

This keeps the agent deterministic and avoids brittle selectors.

Start Here

Help

Install & Updates

CLI

Core Concepts

Gateway & Ops

Web & Interfaces

Channels

Providers

Automation & Hooks

Tools & Skills

Nodes & Media

Platforms

Reference & Templates

​Browser (croc-managed)

​What you get

​Quick start

​Profiles: croc vs chrome

​Configuration

​Use Brave (or another Chromium-based browser)

​Local vs remote control

​Node browser proxy (zero-config default)

​Browserless (hosted remote CDP)

​Security

​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 (croc-managed)

What you get

Quick start

Profiles: `croc` vs `chrome`

Configuration

Use Brave (or another Chromium-based browser)

Local vs remote control

Node browser proxy (zero-config default)

Browserless (hosted remote CDP)

Security

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