State in Context

Persist each user’s name and age across runs in separate session state.

Use session state to carry user context across runs in one session. Each session stores its own state, so the two users remain isolated.

1. Create a Python file

   session_state_in_context.py

   from agno.agent import Agent
   from agno.db.sqlite import SqliteDb
   from agno.models.openai import OpenAIResponses
   
   db = SqliteDb(db_file="tmp/agent.db")
   
   agent = Agent(
       model=OpenAIResponses(id="gpt-5.2"),
       instructions="Users name is {user_name} and age is {age}",
       db=db,
   )
   
   # 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},
       stream=True,
   )
   
   # 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", stream=True)
   
   # 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},
       stream=True,
   )
   
   # 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", stream=True)
   
2. Set up your virtual environment

   Mac

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

   uv pip install -U agno openai sqlalchemy
   
4. Export your OpenAI API key

   Set OpenAI Key

   Set your OPENAI_API_KEY as an environment variable. You can get one from OpenAI.

   Mac

   export OPENAI_API_KEY=sk-***
   
5. Run Agent

   python session_state_in_context.py