Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

changes to docs

Gregor Žunič744d00282f41
diff --git a/README.md b/README.md
index ac58b245f..4407ed19d 100644
--- a/README.md
+++ b/README.md
@@ -97,26 +97,25 @@ Check out the [library docs](https://docs.browser-use.com) and the [cloud docs](
<br/>
-# 🔥 Production with Sandboxes
+# 🔥 Deploy on Sandboxes
-**The easiest way to run Browser-Use in production.** We handle agents, browsers, persistence, auth, cookies, and LLMs. The agent runs right next to the browser for minimal latency.
+We handle agents, browsers, persistence, auth, cookies, and LLMs. The agent runs right next to the browser for minimal latency.
```python
from browser_use import Browser, sandbox, ChatBrowserUse
from browser_use.agent.service import Agent
+import asyncio
-@sandbox(
- cloud_profile_id='your-profile-id', # Your saved cookies/auth
- cloud_proxy_country_code='us', # Bypass captchas, cloudflare, geo-restrictions
-)
-async def production_task(browser: Browser):
- agent = Agent(task="Your task", browser=browser, llm=ChatBrowserUse())
+@sandbox()
+async def my_task(browser: Browser):
+ agent = Agent(task="Find the top HN post", browser=browser, llm=ChatBrowserUse())
await agent.run()
-await production_task()
+# Just call it like any async function
+asyncio.run(my_task())
```
-See [Going to Production](https://docs.browser-use.com/production) to sync your cookies to the cloud.
+See [Going to Production](https://docs.browser-use.com/production) for more details.
<br/>
diff --git a/docs/production.mdx b/docs/production.mdx
index 3ab035784..61f93de9f 100644
--- a/docs/production.mdx
+++ b/docs/production.mdx
@@ -1,42 +1,66 @@
---
title: "Going to Production"
-description: "Deploy with authentication"
+description: "Deploy your local Browser-Use code to production with `@sandbox` wrapper, and scale to millions of agents"
icon: "rocket-launch"
---
-Deploy with saved authentication: test locally → sync cookies → use cloud profile.
+## 1. Basic Deployment
-## 1. Test Locally
+Wrap your existing local code with `@sandbox()`:
```python
-browser = Browser(
- executable_path='/Applications/Google Chrome.app/Contents/MacOS/Google Chrome',
- user_data_dir='~/Library/Application Support/Google/Chrome',
- profile_directory='Default',
-)
-agent = Agent(task="your task", browser=browser, llm=ChatBrowserUse())
-await agent.run()
+from browser_use import Browser, sandbox, ChatBrowserUse
+from browser_use.agent.service import Agent
+import asyncio
+
+@sandbox()
+async def my_task(browser: Browser):
+ agent = Agent(task="Find the top HN post", browser=browser, llm=ChatBrowserUse())
+ await agent.run()
+
+# Just call it like any async function
+asyncio.run(my_task())
```
-<Warning>Close Chrome completely before running.</Warning>
-## 2. Sync to Cloud
+That's it - your code now runs in production at scale. We handle agents, browsers, persistence, and LLMs.
+
+## 2. Add Proxies for Stealth
-Create profile at [cloud.browser-use.com/dashboard/settings?tab=profiles](https://cloud.browser-use.com/dashboard/settings?tab=profiles)
+Use country-specific proxies to bypass captchas, Cloudflare, and geo-restrictions:
+
+```python
+@sandbox(cloud_proxy_country_code='us') # Route through US proxy
+async def stealth_task(browser: Browser):
+ agent = Agent(task="Your task", browser=browser, llm=ChatBrowserUse())
+ await agent.run()
+```
+
+## 3. Sync Local Cookies to Cloud
+
+To use your local authentication in production:
+
+**First**, create an API key at [cloud.browser-use.com/new-api-key](https://cloud.browser-use.com/new-api-key) or follow the instruction on [Cloud - Profiles](https://cloud.browser-use.com/dashboard/settings?tab=profiles)
+
+**Then**, sync your local cookies:
```bash
export BROWSER_USE_API_KEY=your_key && curl -fsSL https://browser-use.com/profile.sh | sh
```
-Log into your accounts in the browser that opens. You'll get a `profile_id`.
+This opens a browser where you log into your accounts. You'll get a `profile_id`.
-## 3. Use in Production
+**Finally**, use it in production:
```python
@sandbox(cloud_profile_id='your-profile-id')
-async def task(browser: Browser):
- agent = Agent(task="authenticated task", browser=browser, llm=ChatBrowserUse())
+async def authenticated_task(browser: Browser):
+ agent = Agent(task="Your authenticated task", browser=browser, llm=ChatBrowserUse())
await agent.run()
```
-Done - your cloud browser is already logged in.
+Your cloud browser is already logged in!
+
+---
+
+For more sandbox parameters and events, see [Sandbox Quickstart](/customize/sandbox/quickstart).
diff --git a/docs/quickstart.mdx b/docs/quickstart.mdx
index 3e867e567..9d8e59a3b 100644
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -140,10 +140,6 @@ if __name__ == "__main__":
Sandboxes are the **easiest way to run Browser-Use in production**. We handle agents, browsers, persistence, auth, cookies, and LLMs. It's also the **fastest way to deploy** - the agent runs right next to the browser, so latency is minimal.
-<Warning>
-Sandboxes are in **beta**.
-</Warning>
-
To run in production with authentication, just add `@sandbox` to your function:
```python