Postgres Storage - Agno

Agno supports using PostgreSQL as a storage backend for Agents using the PostgresStorage class.

Usage

Run PgVector

Install docker desktop and run PgVector on port 5532 using:

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  agno/pgvector:16

postgres_storage_for_agent.py

from agno.storage.postgres import PostgresStorage

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

# Create a storage backend using the Postgres database
storage = PostgresStorage(
    # store sessions in the ai.sessions table
    table_name="agent_sessions",
    # db_url: Postgres database URL
    db_url=db_url,
)

# Add storage to the Agent
agent = Agent(storage=storage)

Params

Parameter	Type	Default	Description
`table_name`	`str`	-	Name of the table to be used.
`schema`	`Optional[str]`	`"ai"`	Schema name, default is "ai".
`db_url`	`Optional[str]`	`None`	Database URL, if provided.
`db_engine`	`Optional[Engine]`	`None`	Database engine to be used.
`schema_version`	`int`	`1`	Version of the schema, default is 1.
`auto_upgrade_schema`	`bool`	`False`	If true, automatically upgrades the schema when necessary.

Developer Resources

View Cookbook