How to beginner · 4 min read

How to use Browser Use with LangChain

Q: How to use Browser Use with LangChain

Use the browser-use package with LangChain by creating a Agent instance and passing a LangChain ChatOpenAI model as the LLM. Then call agent.run() asynchronously to automate browser tasks with AI-driven instructions.

Quick answer

Use the browser-use package with LangChain by creating a Agent instance and passing a LangChain ChatOpenAI model as the LLM. Then call agent.run() asynchronously to automate browser tasks with AI-driven instructions.

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 browser-use and langchain_openai via pip. Ensure you have your OpenAI API key set in the environment variable OPENAI_API_KEY. Also, install Playwright and the Chromium browser for browser automation.

bash

pip install browser-use langchain_openai openai
playwright install chromium

output

Collecting browser-use
Collecting langchain_openai
Collecting openai
Installing collected packages: ...
Successfully installed browser-use langchain_openai openai
[Playwright] Chromium browser installed successfully

Step by step

This example shows how to create a Agent with a LangChain ChatOpenAI model, then run a simple browsing task asynchronously.

python

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

async def main():
    # Initialize LangChain ChatOpenAI with OpenAI API key and model
    llm = ChatOpenAI(model="gpt-4o", temperature=0, openai_api_key=os.environ["OPENAI_API_KEY"])

    # Create Browser Use agent with the LangChain LLM
    agent = Agent(task="Go to google.com and search for 'AI news'", llm=llm)

    # Run the agent asynchronously
    result = await agent.run()

    print("Agent output:", result)

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

output

Agent output: Here is a summary of the latest AI news from Google search results: ...

Common variations

Use different LangChain models like gpt-4o-mini or adjust temperature for creativity.
Run the agent synchronously by wrapping asyncio.run(agent.run()) in a sync function.
Stream output by integrating LangChain streaming features if supported.

python

import os
from browser_use import Agent
from langchain_openai import ChatOpenAI

# Synchronous wrapper example
def run_agent_sync():
    import asyncio
    llm = ChatOpenAI(model="gpt-4o-mini", temperature=0.7, openai_api_key=os.environ["OPENAI_API_KEY"])
    agent = Agent(task="Search Bing for 'latest AI breakthroughs'", llm=llm)
    result = asyncio.run(agent.run())
    print("Sync agent output:", result)

if __name__ == "__main__":
    run_agent_sync()

output

Sync agent output: The latest AI breakthroughs include advancements in large language models, multimodal AI, and reinforcement learning techniques...

Troubleshooting

If you see playwright not installed errors, run playwright install chromium to install the browser.
Ensure your OPENAI_API_KEY environment variable is set correctly to avoid authentication errors.
For network issues, verify your internet connection and proxy settings if applicable.

✅

Key Takeaways

Use browser-use with LangChain by passing a ChatOpenAI instance as the LLM.
Run browser automation tasks asynchronously with agent.run() for best results.
Install Playwright and Chromium to enable browser control.
Adjust LangChain model parameters to customize AI behavior in browsing tasks.

Verified 2026-04 · gpt-4o, gpt-4o-mini

Verify ↗