Browser-use: Connecting AI Agents with the Browser

🌐 Browser-use is the easiest way to connect your AI agents with the browser. With pip (Python>=3.11):

pip install browser-use

Install Playwright:

playwright install chromium

Getting Started

This project demonstrates a simple example of using browser-use to interact with an AI model.

Requirements

Python 3.11 or higher
browser-use
Playwright (Chromium)

Example Usage

The following code demonstrates a basic example:

`browser_agent.py`

from langchain_ollama import ChatOllama
from browser_use import Agent
import asyncio
from dotenv import load_dotenv
load_dotenv()

# Initialize the model
llm=ChatOllama(model="gemma3:4b", num_ctx=32000,base_url="http://localhost:11434")

async def main():
    # Create agent with the model
    agent = Agent(
        task="Compare the price of gpt-4o and DeepSeek-V3",
        llm=llm
    )
    await agent.run()

asyncio.run(main())

This script initializes a ChatOllama model and creates an Agent object. The agent is configured to compare the prices of gpt-4o and DeepSeek-V3. It then runs the agent, which will interact with the model to perform the comparison.

`langchain_ollama_sample.py`

from langchain_ollama import ChatOllama

llm = ChatOllama(
    model="gemma3:4b",
    temperature=1,
    base_url="http://127.0.0.1:11434",
    #Other args
)

messages = [
    (
        "system",
        "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ),
    ("human", "I love programming."),
]
ai_msg = llm.invoke(messages)
print(ai_msg)

This script demonstrates a simple translation task using ChatOllama. It sets up a system message to define the assistant's role, provides a user sentence, and then invokes the model to translate the sentence. The translated message is then printed to the console.

cyysky/README.md