mcpField
B
browser-use

browser-use

github.com/sundial-orgAgent workflows67246 installsUpdated 34w ago
Repository

About browser-use

browser-use provides cloud browsers and autonomous browser automation through an API. It is for users who want Clawdbot to operate web pages or run browsing tasks, with persistent profiles and task execution as a subagent.

Key features

  1. 01Create and manage cloud browser sessions
  2. 02Keep cookies and login state in profiles
  3. 03Connect Clawdbot to a browser session
  4. 04Submit autonomous browser tasks
  5. 05Set a start page, step limit, and vision

Use cases

  1. 01Operate logged-in websites in a cloud browser
  2. 02Reuse login state stored in a profile
  3. 03Delegate a web browsing task to an agent
  4. 04Set a start page and options for browser tasks

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sundial-org/awesome-openclaw-skills --skill browser-use

After installing, type/browser-usein Claude Code to confirm it loaded.

Details

From the project README

Browser Use

Browser Use provides cloud browsers and autonomous browser automation via API.

Docs:

Setup

API Key is read from clawdbot config at skills.entries.browser-use.apiKey.

If not configured, tell the user:

To use Browser Use, you need an API key. Get one at https://cloud.browser-use.com (new signups get $10 free credit). Then configure it:

clawdbot config set skills.entries.browser-use.apiKey "bu_your_key_here"

Base URL: https://api.browser-use.com/api/v2

All requests need header: X-Browser-Use-API-Key: <apiKey>


1. Browser Sessions (Primary)

Spin up cloud browsers for Clawdbot to control directly. Use profiles to persist logins and cookies.

Create browser session
# With profile (recommended - keeps you logged in)
curl -X POST "https://api.browser-use.com/api/v2/browsers" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"profileId": "<profile-uuid>", "timeout": 60}'

# Without profile (fresh browser)
curl -X POST "https://api.browser-use.com/api/v2/browsers" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"timeout": 60}'

Response:

{
  "id": "session-uuid",
  "cdpUrl": "https://<id>.cdp2.browser-use.com",
  "liveUrl": "https://...",
  "status": "active"
}
Connect Clawdbot to the browser
gateway config.patch '{"browser":{"profiles":{"browseruse":{"cdpUrl":"<cdpUrl-from-response>"}}}}'

Now use the browser tool with profile=browseruse to control it.

List/stop browser sessions
# List active sessions
curl "https://api.browser-use.com/api/v2/browsers" -H "X-Browser-Use-API-Key: $API_KEY"

# Get session status
curl "https://api.browser-use.com/api/v2/browsers/<session-id>" -H "X-Browser-Use-API-Key: $API_KEY"

# Stop session (unused time is refunded)
curl -X PATCH "https://api.browser-use.com/api/v2/browsers/<session-id>" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"status": "stopped"}'

Pricing: $0.06/hour (Pay As You Go) or $0.03/hour (Business). Max 4 hours per session. Billed per minute, refunded for unused time.


2. Profiles

Profiles persist cookies and login state across browser sessions. Create one, log into your accounts in the browser, and reuse it.

# List profiles
curl "https://api.browser-use.com/api/v2/profiles" -H "X-Browser-Use-API-Key: $API_KEY"

# Create profile
curl -X POST "https://api.browser-use.com/api/v2/profiles" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "My Profile"}'

# Delete profile
curl -X DELETE "https://api.browser-use.com/api/v2/profiles/<profile-id>" \
  -H "X-Browser-Use-API-Key: $API_KEY"

Tip: You can also sync cookies from your local Chrome using the Browser Use Chrome extension.


3. Tasks (Subagent)

Run autonomous browser tasks - like a subagent that handles browser interactions for you. Give it a prompt and it completes the task.

Always use browser-use-llm - optimized for browser tasks, 3-5x faster than other models.

curl -X POST "https://api.browser-use.com/api/v2/tasks" \
  -H "X-Browser-Use-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "task": "Go to amazon.com and find the price of the MacBook Air M3",
    "llm": "browser-use-llm"
  }'
Poll for completion
curl "https://api.browser-use.com/api/v2/tasks/<task-id>" -H "X-Browser-Use-API-Key: $API_KEY"

Response:

{
  "status": "finished",
  "output": "The MacBook Air M3 is priced at $1,099",
  "isSuccess": true,
  "cost": "0.02"
}

Status values: pending, running, finished, failed, stopped

Task options
OptionDescription
taskYour prompt (required)
llmAlways use browser-use-llm
startUrlStarting page
maxStepsMax actions (default 100)
sessionIdReuse existing session
profileIdUse a profile for auth
flashModeEven faster execution
visionVisual understanding

Full API Reference

See references/api.md for all endpoints including Sessions, Files, Skills, and Skills Marketplace.

Comments

Markdown supported