notte

Rapidly build reliable and fast web agents

We outperform all other web agents in speed, costs, and reliability
→ 🔥 Read more on open-operator-evals • X • LinkedIn • Landing • Console

What is Notte?

Notte provides the full-stack web AI agents framework that allows you to develop, deploy, and scale your own agents, all with a single API. Transform the internet into an agent-friendly environment and websites into structured, navigable maps described in natural language. Read more on our documentation here 🔥

Key features:

• Browser Sessions → on-demand headless browser instances, built in & custom proxy config, CDP, cookie integration, session replay
• Run automated LLM-powered agents → solve complex tasks on the web
• Page interactions → observe website states and execute actions using intuitive natural language commands — granular control while maintaining the simplicity of natural language interaction
• Secrets Vault → enterprise-grade credential management for your Sessions & Agents

Quickstart me

We provide an easy to use API with our hosted version.

To run the above you'll need to sign up on the notte console and create a free notte API key 🔑

uv venv --python 3.11
source .venv/bin/activate
uv pip install notte-sdk

And spin up your crazy cool and dead simple agent on our remote machine:

import os
from notte_sdk import NotteClient

client = NotteClient(api_key=os.getenv("NOTTE_API_KEY"))

with client.Session(headless=False) as session:
    agent = client.Agent(reasoning_model="gemini/gemini-2.0-flash", max_steps=5, session=session)
    response = agent.run(task="doom scroll cat memes on google images")

🔥 Build Powerful Web Agents

Notte is composed of 3 main components that can be combined to build your own agentic system: notte.Session, notte.Vault and notte.Agent.

You can use the notte.Session to create a browser session with different stealth configurations (i.e browser types, proxies, captcha, etc), the notte.Vault to store your credentials and the notte.Agent to run your agent.

Here is an example of how to use these components together along with structured output:

from notte_sdk import NotteClient
from pydantic import BaseModel

class TwitterPost(BaseModel):
    url: str

notte = NotteClient()
with notte.Vault() as vault, notte.Session(headless=False, proxies=False, browser_type="chrome") as session:
    vault.add_credentials(
        url="https://x.com",
        username="your-email",
        password="your-password",
    )
    agent = notte.Agent(session=session, vault=vault, max_steps=10)
    response = agent.run(
      task="go to twitter and post: new era this is @nottecore taking over my acc. Return the post url.",
      response_format=TwitterPost,
    )
print(response.answer)

Demos

Highlights ✨

We introduce a perception layer that transforms websites into structured, natural-language maps. This reduces parsing complexity, making it easier for LLMs to understand and act on web content.

The result: lower cognitive load, better accuracy, and support for smaller, faster models—cutting both inference time and production costs.

Benchmarks

Rank	Provider	Agent Self-Report	LLM Evaluation	Time per Task	Task Reliability
🏆	Notte	86.2%	79.0%	47s	96.6%
2️⃣	Browser-Use	77.3%	60.2%	113s	83.3%
3️⃣	Convergence	38.4%	31.4%	83s	50%

Read the full story here: https://github.com/nottelabs/open-operator-evals

A full stack framework

Notte's full stack agentic internet framework combines core browser infrastructure (sessions, live replay, cdp) with intelligent browsing agents, bridged and enhanced with our perception layer. Our entire codebase is made to be highly customizable, ready to integrate other devtools from the ecosystem and packaged to be push to prod. We also provide web scripting capabilities and sota scraping endpoints out of the box, because why not.

Unstable and upcoming features

⏭️ We have either already partially shipped or are working on the following features: captcha resolution, residential proxies, web security, vpn-style browsing, authentication and payments with secure safe, improved speed and memory, human-in-the-loop integration, channeled notifications, and cookies management.

Run in local mode

You will need to install the dependencies and bring your own keys:

uv venv --python 3.11
source .venv/bin/activate
uv pip install notte
uv run patchright install --with-deps chromium

Then add your LLM provider API keys in a .env

import notte

with notte.Session(headless=False) as session:
    agent = notte.Agent(reasoning_model="gemini/gemini-2.0-flash", max_steps=5, session=session)
    response = agent.run(task="doom scroll cat memes on google images")

Contribute

Setup your local working environment;

uv sync --all-extras --dev
uv run patchright install --with-deps chromium
uv run pre-commit install

Find an issue, fork, open a PR, and merge :)

License

This project is licensed under the Server Side Public License v1. See the LICENSE file for details.

Citation

If you use notte in your research or project, please cite:

@software{notte2025,
  author = {Pinto, Andrea and Giordano, Lucas and {nottelabs-team}},
  title = {Notte: Software suite for internet-native agentic systems},
  url = {https://github.com/nottelabs/notte},
  year = {2025},
  publisher = {GitHub},
  license = {SSPL-1.0}
  version = {1.4.4},
}

Copyright © 2025 Notte Labs, Inc.