Get started

Running agents is a breeze

AI agent instructions

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.

Here’s how you create an agent, and run a task:

simple.py

from notte_sdk import NotteClient

client = NotteClient()
with client.Session() as session:
    agent = client.Agent(session=session)
    agent.run(task="go to google, and find cat pictures")

Usage

See more information on the available operations:

Run

Execute a task

Replay

Get the agent replay

Status

Query the agent status

Running with a session

Providing a session to your agent allows you to choose specific options, like changing your browser or using proxies.

firefox.py

from notte_sdk import NotteClient

client = NotteClient()

with client.Session() as session:
    _ = client.Agent(session=session).run(
        task="What's the weather like in SF tonight?",
    )

Providing credentials

Agents can be provided a vault with credentials in order to securely log in to websites without sharing your information to the LLM.

agent_with_vault.py

from notte_sdk import NotteClient

client = NotteClient()
# Get your vault id from the Notte dashboard
vault = client.Vault(vault_id="my_vault_id")
# Add your credentials securely
vault.add_credentials(
    url="https://github.com/",
    email="[e-mail]",
    password="my_cool_password",
)
# Run an agent with secure credential access
with client.Session() as session:
    agent = client.Agent(vault=vault, session=session, max_steps=10)
    response = agent.run(task="Go to the nottelabs/notte repo and star it. If it's already starred don't unstar it.")

Parameters

You can use the default parameters to create your session, or customize them:

session · UnionType[RemoteSession, None] · default: "None"

The session to connect to. The session’s open_viewer parameter controls whether to display a live viewer (browsers are always headless).

vault · UnionType[NotteVault, None] · default: "None"

A notte vault instance, if the agent requires authentication

notifier · UnionType[BaseNotifier, None] · default: "None"

A notifier (for example, email), which will get called upon task completion.

persona · UnionType[NottePersona, None] · default: "None"

agent_id · UnionType[str, None] · default: "None"

reasoning_model · notte_core.common.config.LlmModel | str

The language model to use for agent reasoning.

use_vision · bool

Whether to enable vision capabilities for the agent.

max_steps · int

Maximum number of steps the agent can take.

vault_id · str | None

Optional ID of the vault to use.

persona_id · str | None

notifier_config · dict[str, typing.Any] | None

Config used for the notifier.