Skip to main content
This example demonstrates how to use session state variables directly in agent instructions. It shows how to initialize session state and reference those variables in the instruction templates.
1

Create a Python file

Create a file called session_state_in_instructions.py
2

Add code to file

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

agent = Agent(
    model=OpenAIChat(id="gpt-5-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}",
    markdown=True,
)

agent.print_response("What is my name?", stream=True)
3

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
4

Install libraries

pip install -U agno openai
5
Set OpenAI Key
6
Set your OPENAI_API_KEY as an environment variable. You can get one from OpenAI.
7
Mac
export OPENAI_API_KEY=sk-***
Windows
setx OPENAI_API_KEY sk-***
8

Run the agent

python session_state_in_instructions.py
9

Find All Cookbooks

Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:Agno Cookbooks on GitHub