Skip to main content
This example demonstrates how to create an agent with basic session state management, maintaining a shopping list across interactions using SQLite storage.
1

Create a Python file

session_state_basic.py
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses


def add_item(session_state, item: str) -> str:
    """Add an item to the shopping list."""
    session_state["shopping_list"].append(item)
    return f"The shopping list is now {session_state['shopping_list']}"


agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    session_state={"shopping_list": []},
    db=SqliteDb(db_file="tmp/agents.db"),
    tools=[add_item],
    instructions="Current state (shopping list) is: {shopping_list}",
    markdown=True,
)

agent.print_response("Add milk, eggs, and bread to the shopping list", stream=True)
print(f"Final session state: {agent.get_session_state()}")
2

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
3

Install dependencies

uv pip install -U agno openai
4

Export your OpenAI API key

​
Set OpenAI Key

Set your OPENAI_API_KEY as an environment variable. You can get one from OpenAI.
export OPENAI_API_KEY=sk-***
5

Run Agent

python session_state_basic.py