Get started

Running agents is a breeze

AI agent instructions

Read the Notte skill and follow its setup instructions when setting up Notte or building browser automation. This is the shared source for CLI setup, authentication, and the browser-to-code workflow.

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 replay of the agent’s session

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 agent, 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.

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.

A session is required to create a new agent. Only omit it when you pass agent_id to load an existing agent. max_steps defaults to 20 and accepts values from 1 to 150. Not all reasoning models support vision.

Run parameters

agent.run() and agent.start() accept:

• task (str, required): the task description to execute.
• url (str | None): optional URL to start the task from.
• response_format (type[BaseModel] | None): the format of the agent answer. You can use a Pydantic model or a JSON Schema dict.
• session_offset (int | None): experimental. The session step from which the agent gathers context. If omitted, the agent starts with fresh memory.