# Browser Use Cloud > Browser Use Cloud is a managed API for AI browser automation. You run **agents** that use a real browser. Send a task in plain language, get the result back. Two agents: `browser-use` (browser tasks — fast, OSS) and `browsercode` (code + browser — data processing, multi-step work). One base URL: `https://api.browser-use.com/api/v1`. Auth via `X-Browser-Use-API-Key` header (keys start with `bu_`). - Dashboard: https://cloud.browser-use.com - Create API key: https://cloud.browser-use.com/settings?tab=api-keys&new=1 - Docs: https://docs.browser-use.com - Agent registry (which agent to use, machine-readable): GET https://api.browser-use.com/api/v1/agents - Open-source repo: https://github.com/browser-use/browser-use — The open-source Python library. Note: the open-source API is different from the Cloud API. For the easiest path to production with managed infrastructure, use the Cloud API below. **Use `/api/v1`.** The older `/api/v2`, `/api/v3`, `/api/v4` surfaces are legacy — they keep working for existing integrations but should not be used for new projects. See the "Legacy" section. **The model:** you only ever create **runs** (`POST /api/v1/agents/{agent}/runs`). A run provisions its own browser and returns a `session_id` (pass it back to continue) and a `workspace_id` (for files). You do not create sessions or workspaces yourself on the normal path. Before writing code, check if `browser-use-sdk` is already installed. If so, upgrade to the latest version. If not, install it: - Python: `pip install --upgrade browser-use-sdk` - TypeScript: `npm install browser-use-sdk@latest` Set API key (starts with `bu_`). If the user doesn't have one yet, they can create one in one click at https://cloud.browser-use.com/settings?tab=api-keys&new=1: ``` export BROWSER_USE_API_KEY=bu_your_key_here ``` ## Get started - [Overview](https://docs.browser-use.com/cloud/model): The whole API in one page: you run tasks. A run gives you back ids. Reuse the ids. That's it. - [Quickstart](https://docs.browser-use.com/cloud/quickstart): Run your first browser task in under a minute. Send a task, get the result back. - [Prompt for Vibecoders](https://docs.browser-use.com/cloud/vibecoding): Complete Cloud SDK reference for AI coding agents. ## Agents - [Choose an agent](https://docs.browser-use.com/cloud/choose-an-agent): Two agents: browser-use for browser tasks, browsercode for code + browser. Pick by capability, or let the registry route for you. - [Run a task](https://docs.browser-use.com/cloud/run-a-task): POST a task to an agent. One call starts a run; the run provisions whatever it needs and returns ids you can reuse. - [Continue a task](https://docs.browser-use.com/cloud/continue-a-task): Follow up on a previous run by passing its session_id. No separate session to create — the first run made one for you. - [Files](https://docs.browser-use.com/cloud/files): Give an agent files and get its output files back. Files live on the conversation, not a workspace you manage. - [Watch a run](https://docs.browser-use.com/cloud/watch-a-run): Poll a run's status until it finishes. browser-use exposes steps; browsercode exposes events. - [Stop a run](https://docs.browser-use.com/cloud/stop-a-run): End a run with POST /stop. One verb for ending things — runs and browsers both use /stop. - [Open-source agent on the cloud](https://docs.browser-use.com/cloud/open-source-agent): The cloud browser-use agent is the open-source agent, hosted — same agent, same models, running on stealth browsers. ## Browsers - [Browsers](https://docs.browser-use.com/cloud/browsers): Stealth cloud browsers you can drive over CDP — or let an agent drive for you. - [Create a browser](https://docs.browser-use.com/cloud/create-browser): Provision a browser you drive yourself over CDP — no agent required. Agents provision their own; this is for direct control. - [Manage a browser](https://docs.browser-use.com/cloud/manage-browser): List browsers, stop them, and fetch recordings and downloads. Works for standalone browsers and the browsers an agent used. - [Live preview & recording](https://docs.browser-use.com/cloud/browser/live-preview): Watch the agent's browser live, embed it in your app, and get an MP4 recording after the run. - [Screenshots](https://docs.browser-use.com/cloud/browser/screenshots): Take viewport and full-page screenshots from a cloud browser, and control where they're saved. ## Profiles - [Create a profile](https://docs.browser-use.com/cloud/create-profile): Saved login and cookie state. Create a profile once, reference it by id forever. - [Use a profile](https://docs.browser-use.com/cloud/use-a-profile): Pass a profile id into a run or browser to start logged-in, and stop cleanly so new state persists. - [Authentication](https://docs.browser-use.com/cloud/browser/authentication): Log into websites and stay logged in. Save login state once in a profile, reuse it on every run. - [Sync cookies](https://docs.browser-use.com/cloud/browser/sync-cookies): Copy your existing local browser logins into a cloud profile. No passwords, no re-login. ## Stealth & proxies - [Stealth & proxies](https://docs.browser-use.com/cloud/browser/stealth-and-proxies): Hardened Chromium, randomized fingerprints, CAPTCHA solving, and residential proxies in 195+ countries — all on by default. - [Stealth](https://docs.browser-use.com/cloud/browser/stealth): Best stealth on the planet. We fork Chromium to give agents access to all websites. - [CAPTCHA Solving](https://docs.browser-use.com/cloud/browser/captcha): Browser Use cloud browsers solve CAPTCHAs automatically, on by default, on every plan. - [Proxies](https://docs.browser-use.com/cloud/browser/proxies): Residential proxies in 195+ countries, on by default. Set a country, disable, or bring your own. - [Geo-scraping](https://docs.browser-use.com/cloud/browser/geo-scraping): Route the browser through a specific country to see region-locked prices, catalogs, and content. - [Custom proxy](https://docs.browser-use.com/cloud/browser/custom-proxy): Bring your own HTTP or SOCKS5 proxy instead of the built-in residential proxies. ## Account - [Account](https://docs.browser-use.com/cloud/account): Your project: one per account. Check identity with GET /project, then billing and limits. - [Billing](https://docs.browser-use.com/cloud/billing): Check your credit balance, plan, and estimated runway. - [Limits](https://docs.browser-use.com/cloud/limits): Check your concurrency and team-member limits, and how many browser slots are in use. ## Integrations - [OpenClaw](https://docs.browser-use.com/cloud/tutorials/integrations/openclaw): Give OpenClaw agents browser automation with Browser Use — via CDP or the CLI skill. - [Hermes Agent](https://docs.browser-use.com/cloud/tutorials/integrations/hermes-agent): Give Hermes Agent cloud browser automation with Browser Use. - [MCP Server](https://docs.browser-use.com/cloud/guides/mcp-server): Run browser automation tasks from your AI coding assistant. Connect to Claude, Cursor, Windsurf, or any MCP client. - [Webhooks](https://docs.browser-use.com/cloud/guides/webhooks): Receive real-time notifications when tasks complete. Configure webhook endpoints for async task monitoring. - [n8n](https://docs.browser-use.com/cloud/tutorials/integrations/n8n): Use Browser Use as an HTTP node in n8n workflows. - [Playwright, Puppeteer, Selenium](https://docs.browser-use.com/cloud/browser/playwright-puppeteer-selenium): Connect your automation framework to Browser Use's stealth infrastructure via CDP. ## Anthropic - [Claude Code](https://docs.browser-use.com/cloud/tutorials/integrations/claude-code): Give Claude Code cloud browser automation with Browser Use. - [Claude Managed Agents](https://docs.browser-use.com/cloud/tutorials/integrations/claude-managed-agents): Give Anthropic's Claude Managed Agents a stealth cloud browser via the Browser Use CLI. ## Tutorials - [Agent Sign Up for Browser Use](https://docs.browser-use.com/cloud/agent-signup): How the Browser Use agent challenge lets an AI agent create a free account and API key. ## API Reference ## Overview - [API reference](https://docs.browser-use.com/cloud/api-v1-reference): The full /api/v1 endpoint reference. Base URL https://api.browser-use.com/api/v1, auth via X-Browser-Use-API-Key. ## browser-use ## browsercode ## Browser profiles ## Agent Workspaces (Files) ## Legacy - [Legacy APIs (v2, v3, v4)](https://docs.browser-use.com/cloud/legacy/overview): Older API versions, kept working for backwards compatibility. New projects should use the unified /api/v1. ## Legacy guides & tutorials - [FAQ](https://docs.browser-use.com/cloud/faq): Common questions and solutions. - [2FA](https://docs.browser-use.com/cloud/guides/2fa): Best practices for handling two-factor authentication in automated browser sessions. - [x402 (pay-per-request)](https://docs.browser-use.com/cloud/guides/x402): Pay for Browser Use Cloud with crypto (USDC on Base). ~30 seconds from wallet to first request. - [Chat UI](https://docs.browser-use.com/cloud/tutorials/chat-ui): Full end-to-end example. Build a chat UI with live browser preview, follow-up tasks, recording, and streaming messages. - [Grow Therapy provider search](https://docs.browser-use.com/cloud/tutorials/grow-therapy-compare): Search Grow Therapy for therapists by location, insurance, and specialty — with cached reruns. ## Guides (v2) - [Agent (v2)](https://docs.browser-use.com/cloud/legacy/agent): V2 agent models and file handling. - [Public share links (v2)](https://docs.browser-use.com/cloud/legacy/public-share): Generate shareable URLs for agent sessions using the v2 API. - [Skills](https://docs.browser-use.com/cloud/legacy/skills): Turn any website into a deterministic API endpoint. Create once, call repeatedly. - [1Password & 2FA](https://docs.browser-use.com/cloud/guides/1password): Auto-fill passwords and TOTP codes from 1Password during agent tasks. - [Secrets](https://docs.browser-use.com/cloud/guides/secrets): Pass domain-scoped credentials to the agent securely. - [Deterministic rerun](https://docs.browser-use.com/cloud/agent/cache-script): Run a task once, then re-execute it for $0 LLM cost.