How to beginner · 3 min read

How to use Browser Use with OpenAI

Q: How to use Browser Use with OpenAI

Use the browser-use package with an OpenAI API key to automate browser tasks by combining Agent from browser_use and ChatOpenAI from langchain_openai. Instantiate Agent with a task and an LLM instance, then run it asynchronously to get the result.

Quick answer

Use the browser-use package with an OpenAI API key to automate browser tasks by combining Agent from browser_use and ChatOpenAI from langchain_openai. Instantiate Agent with a task and an LLM instance, then run it asynchronously to get the result.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0
pip install browser-use langchain_openai
Playwright installed with chromium (run: playwright install chromium)

Setup

Install the required packages and set your OpenAI API key as an environment variable. Also, install Playwright's Chromium browser for automation.

bash

pip install openai browser-use langchain_openai
playwright install chromium

output

Collecting openai
Collecting browser-use
Collecting langchain_openai
Installing collected packages...
Playwright browsers installed successfully.

Step by step

This example shows how to create a simple browser automation task that searches Google for 'AI news' using Agent from browser_use and ChatOpenAI from langchain_openai. The code runs asynchronously and prints the result.

python

import asyncio
from browser_use import Agent
from langchain_openai import ChatOpenAI
import os

async def main():
    llm = ChatOpenAI(model="gpt-4o-mini", openai_api_key=os.environ["OPENAI_API_KEY"])
    agent = Agent(task="Go to google.com and search for 'AI news'", llm=llm)
    result = await agent.run()
    print("Result:", result)

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

output

Result: [Agent's summarized output of the search or browser interaction]

Common variations

Use different LLM models by changing model in ChatOpenAI, e.g., gpt-4o-mini.
Run synchronously by wrapping async calls with asyncio.run() or use an async framework.
Customize browser options or tasks by passing additional parameters to Agent.

Troubleshooting

If you get playwright not installed errors, run playwright install chromium.
Ensure OPENAI_API_KEY is set in your environment before running the script.
For permission errors, verify Python environment and package versions are compatible.

✅

Key Takeaways

Use Agent from browser_use with ChatOpenAI for browser automation powered by OpenAI.
Install Playwright and Chromium to enable browser control.
Run the agent asynchronously with asyncio.run() for best results.
Customize the LLM model and task easily via parameters.
Set environment variables securely; never hardcode API keys.

Verified 2026-04 · gpt-4o-mini

Verify ↗