Agent State

State is any kind of data the Agent needs to maintain throughout runs.

A simple yet common use case for Agents is to manage lists, items and other “information” for a user. For example, a shopping list, a todo list, a wishlist, etc.This can be easily managed using the session_state. The Agent updates the session_state in tool calls and exposes them to the Model in the description and instructions.

Agno’s provides a powerful and elegant state management system, here’s how it works:

The Agent has a session_state parameter.
We add our state variables to this session_state dictionary.
We update the session_state dictionary in tool calls or other functions.
We share the current session_state with the Model in the description and instructions.
The session_state is stored with Agent sessions and is persisted in a database. Meaning, it is available across execution cycles. This also means when switching sessions between calls to agent.run(), the state is loaded and available.
You can also pass session_state to the agent on agent.run(), effectively overriding any state that was set on Agent initialization.

Here’s an example of an Agent managing a shopping list:

session_state.py

from agno.agent import Agent
from agno.models.openai import OpenAIChat

# Define a tool that adds an item to the shopping list
def add_item(agent: Agent, item: str) -> str:
    """Add an item to the shopping list."""
    agent.session_state["shopping_list"].append(item)
    return f"The shopping list is now {agent.session_state['shopping_list']}"


# Create an Agent that maintains state
agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    # Initialize the session state with a counter starting at 0
    session_state={"shopping_list": []},
    tools=[add_item],
    # You can use variables from the session state in the instructions
    instructions="Current state (shopping list) is: {shopping_list}",
    # Important: Add the state to the messages
    add_state_in_messages=True,
    markdown=True,
)

# Example usage
agent.print_response("Add milk, eggs, and bread to the shopping list", stream=True)
print(f"Final session state: {agent.session_state}")

This is as good and elegant as state management gets.

Maintaining state across multiple runs

A big advantage of sessions is the ability to maintain state across multiple runs. For example, let’s say the agent is helping a user keep track of their shopping list.

By setting add_state_in_messages=True, the keys of the session_state dictionary are available in the description and instructions as variables.Use this pattern to add the shopping_list to the instructions directly.

shopping_list.py

from textwrap import dedent

from agno.agent import Agent
from agno.models.openai import OpenAIChat


# Define tools to manage our shopping list
def add_item(agent: Agent, item: str) -> str:
    """Add an item to the shopping list and return confirmation."""
    # Add the item if it's not already in the list
    if item.lower() not in [i.lower() for i in agent.session_state["shopping_list"]]:
        agent.session_state["shopping_list"].append(item)
        return f"Added '{item}' to the shopping list"
    else:
        return f"'{item}' is already in the shopping list"


def remove_item(agent: Agent, item: str) -> str:
    """Remove an item from the shopping list by name."""
    # Case-insensitive search
    for i, list_item in enumerate(agent.session_state["shopping_list"]):
        if list_item.lower() == item.lower():
            agent.session_state["shopping_list"].pop(i)
            return f"Removed '{list_item}' from the shopping list"

    return f"'{item}' was not found in the shopping list"


def list_items(agent: Agent) -> str:
    """List all items in the shopping list."""
    shopping_list = agent.session_state["shopping_list"]

    if not shopping_list:
        return "The shopping list is empty."

    items_text = "\n".join([f"- {item}" for item in shopping_list])
    return f"Current shopping list:\n{items_text}"


# Create a Shopping List Manager Agent that maintains state
agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    # Initialize the session state with an empty shopping list
    session_state={"shopping_list": []},
    tools=[add_item, remove_item, list_items],
    # You can use variables from the session state in the instructions
    instructions=dedent("""\
        Your job is to manage a shopping list.

        The shopping list starts empty. You can add items, remove items by name, and list all items.

        Current shopping list: {shopping_list}
    """),
    show_tool_calls=True,
    add_state_in_messages=True,
    markdown=True,
)

# Example usage
agent.print_response("Add milk, eggs, and bread to the shopping list", stream=True)
print(f"Session state: {agent.session_state}")

agent.print_response("I got bread", stream=True)
print(f"Session state: {agent.session_state}")

agent.print_response("I need apples and oranges", stream=True)
print(f"Session state: {agent.session_state}")

agent.print_response("whats on my list?", stream=True)
print(f"Session state: {agent.session_state}")

agent.print_response("Clear everything from my list and start over with just bananas and yogurt", stream=True)
print(f"Session state: {agent.session_state}")

State is a great way to control context across multiple runs.

Using state in instructions

You can use variables from the session state in the instructions by setting add_state_in_messages=True.

Don’t use the f-string syntax in the instructions. Directly use the {key} syntax, Agno substitutes the values for you.

state_in_instructions.py

from textwrap import dedent

from agno.agent import Agent
from agno.models.openai import OpenAIChat


agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    # Initialize the session state with a variable
    session_state={"user_name": "John"},
    # You can use variables from the session state in the instructions
    instructions="Users name is {user_name}",
    show_tool_calls=True,
    add_state_in_messages=True,
    markdown=True,
)

agent.print_response("What is my name?", stream=True)

Changing state on run

When you pass session_id to the agent on agent.run(), it will switch to the session with the given session_id and load any state that was set on that session. This is useful when you want to continue a session for a specific user.

changing_state_on_run.py

from agno.agent import Agent
from agno.models.openai import OpenAIChat

agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    add_state_in_messages=True,
    instructions="Users name is {user_name} and age is {age}",
)

# Sets the session state for the session with the id "user_1_session_1"
agent.print_response("What is my name?", session_id="user_1_session_1", user_id="user_1", session_state={"user_name": "John", "age": 30})

# Will load the session state from the session with the id "user_1_session_1"
agent.print_response("How old am I?", session_id="user_1_session_1", user_id="user_1")

# Sets the session state for the session with the id "user_2_session_1"
agent.print_response("What is my name?", session_id="user_2_session_1", user_id="user_2", session_state={"user_name": "Jane", "age": 25})

# Will load the session state from the session with the id "user_2_session_1"
agent.print_response("How old am I?", session_id="user_2_session_1", user_id="user_2")

Persisting state in database

session_state is part of the Agent session and is saved to the database after each run if a storage driver is provided. Here’s an example of an Agent that maintains a shopping list and persists the state in a database. Run this script multiple times to see the state being persisted.

session_state_storage.py

"""Run `pip install agno openai sqlalchemy` to install dependencies."""

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.storage.sqlite import SqliteStorage


# Define a tool that adds an item to the shopping list
def add_item(agent: Agent, item: str) -> str:
    """Add an item to the shopping list."""
    if item not in agent.session_state["shopping_list"]:
        agent.session_state["shopping_list"].append(item)
    return f"The shopping list is now {agent.session_state['shopping_list']}"


agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    # Fix the session id to continue the same session across execution cycles
    session_id="fixed_id_for_demo",
    # Initialize the session state with an empty shopping list
    session_state={"shopping_list": []},
    # Add a tool that adds an item to the shopping list
    tools=[add_item],
    # Store the session state in a SQLite database
    storage=SqliteStorage(table_name="agent_sessions", db_file="tmp/data.db"),
    # Add the current shopping list from the state in the instructions
    instructions="Current shopping list is: {shopping_list}",
    # Important: Set `add_state_in_messages=True`
    # to make `{shopping_list}` available in the instructions
    add_state_in_messages=True,
    markdown=True,
)

# Example usage
agent.print_response("What's on my shopping list?", stream=True)
print(f"Session state: {agent.session_state}")
agent.print_response("Add milk, eggs, and bread", stream=True)
print(f"Session state: {agent.session_state}")

Introduction

Concepts

Other

How to

Agent State

Maintaining state across multiple runs

Using state in instructions

Changing state on run

Persisting state in database

​Maintaining state across multiple runs

​Using state in instructions

​Changing state on run

​Persisting state in database

Maintaining state across multiple runs

Using state in instructions

Changing state on run

Persisting state in database