# BrowserUse Integration with Novita Agent Sandbox - Documentation

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown is available with `Accept: text/markdown` and `.md` URL variants.

Source: /docs/guides/sandbox-integrations-browser-use

# BrowserUse Integration with Novita Agent Sandbox

[BrowserUse](https://github.com/browser-use/browser-use) is a powerful AI browser agent. Combined with the secure isolated environment provided by Novita Agent Sandbox, you can build high-concurrency, multi-task browser AI agents.
This document provides detailed instructions on how to run BrowserUse projects based on Novita Agent Sandbox service.
The document uses the `browser-chromium` sandbox template released by Novita. If you want to create your own template based on this or view more complete example code, please refer to [here](https://github.com/novitalabs/Novita-CollabHub/tree/main/examples/browser-use).

###

[​](#1-get-novita-api-key)

1. Get Novita API Key

###

[​](#2-install-dependencies)

2. Install Dependencies

Install the required Python packages:

Python

```
pip install browser-use
```

###

[​](#3-example-code)

3. Example Code

Before getting started, you need to configure the necessary environment variables:

Bash

```
export NOVITA_API_KEY=""
export LLM_API_KEY=""
export LLM_BASE_URL=https://api.novita.ai/openai
export LLM_MODEL=""
```

Save the following code:

agent.py

```
import asyncio
import base64
import os
import time
import dotenv
dotenv.load_dotenv(override=True)
from browser_use import Agent, BrowserSession
from browser_use.llm import ChatOpenAI
from novita_sandbox.core import Sandbox

async def screenshot(agent: Agent):
# Screenshot function
print("Taking screenshot...")
page = await agent.browser_session.get_current_page()
screenshot_bytes = await page.screenshot(format='png')
# screenshot method returns the binary data of the image, we should save it as a PNG file
screenshots_dir = os.path.join(".", "screenshots")
os.makedirs(screenshots_dir, exist_ok=True)
screenshot_path = os.path.join(screenshots_dir, f"{time.time()}.png")
if isinstance(screenshot_bytes, str):
screenshot_data = base64.b64decode(screenshot_bytes)
else:
screenshot_data = screenshot_bytes
with open(screenshot_path, "wb") as f:
f.write(screenshot_data)
print(f"Screenshot saved to {screenshot_path}")

async def main():
# Create Novita sandbox instance
sandbox = Sandbox.create(
timeout=600, # Timeout in seconds
template="browser-chromium", # This template contains chromium browser and exposes port 9223 for remote connection
)
try:
# Get Chrome debug port address from sandbox
host = sandbox.get_host(9223) # Get sandbox port 9223 address
cdp_url = f"https://{host}"
print(f"Chrome Debug Protocol URL: {cdp_url}")
# Create BrowserUse session
browser_session = BrowserSession(cdp_url=cdp_url)
await browser_session.start()
print("BrowserUse session created successfully")
# Create AI Agent
agent = Agent(
task="Go to hackernews and find the top 3 stories",
llm=ChatOpenAI(
api_key=os.getenv("LLM_API_KEY"),
base_url=os.getenv("LLM_BASE_URL"),
model=os.getenv("LLM_MODEL"),
temperature=1
),
browser_session=browser_session,
)
# Run Agent task
print("Starting Agent task execution...")
await agent.run(
on_step_end=screenshot, # Take screenshot after each step
)
# Close browser session
await browser_session.kill()
print("Task execution completed")
finally:
# Clean up sandbox resources
sandbox.kill()
print("Sandbox resources cleaned up")
exit

if __name__ == "__main__":
asyncio.run(main())
```

###

[​](#4-run-the-agent)

4. Run the Agent

After Installing the dependencies and setting up the environment variables, you can run the example code. You can see the output in the terminal as below if everything goes well. Browser-use is running tasks in the remote browser inside your sandbox.
![Output](https://mintcdn.com/novitaai/lT4Ftco9V6UT3djo/guides/images/sandbox-browser-use-output.png?fit=max&auto=format&n=lT4Ftco9V6UT3djo&q=85&s=c3f1ed31bce3e07d9b844194b78cfd1f)
It will generate screenshots like below:
![screenshot1](https://mintcdn.com/novitaai/lT4Ftco9V6UT3djo/guides/images/sandbox-browser-use-screenshots/1.png?fit=max&auto=format&n=lT4Ftco9V6UT3djo&q=85&s=b6e77e80047796254a7f110f1a6f83f9)
To run a more complete demo, please refer to [here](https://github.com/novitalabs/Novita-CollabHub/tree/main/examples/browser-use).

Last modified on June 10, 2026