Agent with Storage
Persist a Cerebras agent's chat history to Postgres.
Code
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.cerebras import Cerebras
from agno.tools.websearch import WebSearchTools
# Setup the database
db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
db = PostgresDb(db_url=db_url)
agent = Agent(
model=Cerebras(id="gpt-oss-120b"),
db=db,
tools=[WebSearchTools()],
add_history_to_context=True,
)
agent.print_response("How many people live in Canada?")
agent.print_response("What is their national anthem called?")Usage
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateSet your API key
export CEREBRAS_API_KEY=xxxInstall dependencies
uv pip install -U ddgs sqlalchemy psycopg cerebras-cloud-sdk agnoStart your Postgres server
Ensure your Postgres server is running and accessible at the connection string used in db_url.
Run Agent
Save the code above as db.py, then run:
python db.py