Team with Agentic Memory
Let a team create and update user memories during a run.
The local database setup below requires Docker.
Set enable_agentic_memory=True to give a team the update_user_memory tool for creating and updating user memories during a run.
Code
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIResponses
from agno.team import Team
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
db = PostgresDb(db_url=db_url)
john_doe_id = "john_doe@example.com"
agent = Agent(
model=OpenAIResponses(id="gpt-5.2"),
)
team = Team(
model=OpenAIResponses(id="gpt-5.2"),
members=[agent],
db=db,
enable_agentic_memory=True,
)
team.print_response(
"My name is John Doe and I like to hike in the mountains on weekends.",
stream=True,
user_id=john_doe_id,
)
team.print_response("What are my hobbies?", stream=True, user_id=john_doe_id)Usage
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateInstall dependencies
uv pip install -U agno openai 'psycopg[binary]' sqlalchemyRun PgVector
docker run -d \
-e POSTGRES_DB=ai \
-e POSTGRES_USER=ai \
-e POSTGRES_PASSWORD=ai \
-e PGDATA=/var/lib/postgresql \
-v pgvolume:/var/lib/postgresql \
-p 5532:5432 \
--name pgvector \
agnohq/pgvector:18Set environment variables
export OPENAI_API_KEY=your_openai_api_key_hereRun the example
python team_with_agentic_memory.py