Basics

​

Quick Start

import asyncio
from openbrowser import CodeAgent, ChatGoogle
from dotenv import load_dotenv

load_dotenv()

async def main():
    task = "Extract all products from example.com and save to products.csv"

    agent = CodeAgent(task=task, llm=ChatGoogle())
    await agent.run()

asyncio.run(main())

GOOGLE_API_KEY=your-api-key

​

When to Use

• Data extraction at scale (100s-1000s of items)
• Repetitive interactions where functions can be reused
• Tasks requiring data processing and file operations
• Deterministic workflows you want to rerun

• Best performance for data collection tasks
• Slightly slower for one-off interactions vs standard Agent

• Generates Python code that can be rerun deterministically
• Perfect for refining extraction logic

(function(){
  return Array.from(document.querySelectorAll('.product')).map(p => ({
    name: p.querySelector('.name').textContent,
    price: p.querySelector('.price').textContent
  }))
})()

import pandas as pd

products = await evaluate(extract_products) # reuse other code blocks
df = pd.DataFrame(products)
df.to_csv('products.csv', index=False)

​

Available Libraries

• Data processing: pandas, numpy
• Web: requests, BeautifulSoup
• File formats: csv, json, openpyxl (Excel)
• Visualization: matplotlib
• Utilities: tabulate, datetime, re
• and all which you install …

​

Available Tools

• navigate(url) - Navigate to a URL
• click(index) - Click an element by index
• click_xy(x, y, button='left', click_count=1) - Click a no-index canvas, PDF, embed, or native-rendered target
• hover_xy(x, y) - Move over a no-index canvas, PDF, embed, or native-rendered target
• input(index, text) - Type text into an input
• scroll(down, pages) - Scroll the page
• scroll_xy(x, y, delta_x=0, delta_y=0) - Wheel-scroll a no-index surface
• upload_file(path) - Upload a file
• evaluate(code, variables={}) - Execute JavaScript and return results
• done(text, success, files_to_display=[]) - Mark task complete

​

Exporting Sessions

​

Quick Export

from openbrowser.code_use.notebook_export import export_to_ipynb, session_to_python_script

# After running your agent
await agent.run()

# Export to Jupyter notebook
notebook_path = export_to_ipynb(agent, "my_automation.ipynb")

# Export to Python script
script = session_to_python_script(agent)
with open("my_automation.py", "w") as f:
    f.write(script)

​

Export Formats

• Jupyter Notebook (.ipynb): Interactive development, sharing, documentation
• Python Script (.py): Production deployment, version control, automation

• Setup code with browser initialization
• JavaScript code blocks as Python variables
• All executed Python cells with outputs
• Ready-to-run automation workflows