Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.notte.cc/llms.txt

Use this file to discover all available pages before exploring further.

STOP. Do not read past this section until you have read and followed /quickstart.md.Goal: produce a reliable SDK automation script. The intended authoring flow is generate then edit, not write browser automation from scratch.Do not hand-write SDK code with element IDs, selectors, or form fields from memory. Element IDs, selectors, and field mappings must come from a live observe() call, CLI notte page observe output, or generated workflow code. Guessed browser targets fail on real pages.Use the Notte skill and CLI to inspect the live site, validate actions/selectors, handle auth/session state, and export workflow code with notte sessions workflow-code before using SDK docs or SDK code.SDK reference pages are for understanding, running, or editing generated workflow code. They are not the starting point for manually authoring the initial browser automation. SDK-first code is guesswork on real-world pages with dynamic selectors, auth state, CAPTCHAs, and anti-bot behavior.
Kernel.sh is a developer platform that provides browser infrastructure for web agents. By integrating with Notte, you can use Kernel browser infra to run reliable browser agents using Chrome DevTools Protocol (CDP).

​
Adding Kernel to existing Notte implementations

​
1. Install Notte and Kernel SDK

uv pip install notte-sdk
uv pip install kernel

​
2. Initialize Notte and Kernel

Import the libraries and create a cloud browser session: 
from kernel import Kernel
from notte_sdk import NotteClient

# Initialize clients
kernel = Kernel()
notte_client = NotteClient()

# Create a browser on Kernel
kernel_browser = kernel.browsers.create()

​
3. Connect Notte to Kernel’s CDP endpoint

Use Kernel’s CDP URL to create a Notte session: 
# Connect Notte to Kernel's browser via CDP
with notte_client.Session(cdp_url=kernel_browser.cdp_ws_url) as session:
    # Create an agent with a task
    agent = notte_client.Agent(session=session, max_steps=10)

    # Run your automation task
    result = agent.run(
        task="extract pricing plans from https://www.notte.cc"
    )

​
Complete example script

Here’s a complete, runnable script that demonstrates the full integration: 
from kernel import Kernel
from notte_sdk import NotteClient
import os
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()

def main():
    # Initialize clients
    kernel = Kernel()

    notte_api_key = os.getenv("NOTTE_API_KEY")
    if not notte_api_key:
        raise ValueError("NOTTE_API_KEY not found in environment variables")

    notte_client = NotteClient(api_key=notte_api_key)

    # Create a headful browser on Kernel
    print("Creating browser session on Kernel...")
    kernel_browser = kernel.browsers.create()
    # print(kernel_browser.browser_live_view_url)

    try:
        # Connect Notte to Kernel's browser via CDP
        print("Connecting Notte to Kernel browser...")
        with notte_client.Session(cdp_url=kernel_browser.cdp_ws_url) as session:
            # Create an agent with a task
            agent = notte_client.Agent(session=session, max_steps=10)

            # Run your automation task
            result = agent.run(
                task="extract pricing plans from https://www.notte.cc"
            )

            print(f"Task completed: {result.answer}")

    except Exception as e:
        print(f"Error during automation: {e}")

    finally:
        # Always clean up the browser session
        kernel.browsers.delete_by_id(kernel_browser.session_id)
        print("Browser session cleaned up")

if __name__ == "__main__":
    main()

​
Benefits of using Kernel with Notte

  • No local browser management: Run agents without installing or maintaining browsers locally
  • Scalability: Launch multiple browser sessions in parallel for concurrent tasks
  • Cloud infrastructure: Leverage Kernel’s optimized browser infrastructure
  • Stealth mode: Built-in anti-detection features for web scraping
  • Session control: Programmatic control over browser lifecycle