SingleStore

Use SingleStore for agent session storage and persistence.

Agno supports using SingleStore as a database with the SingleStoreDb class.

You can get started with SingleStore following their documentation.

Usage

Install the sqlalchemy, pymysql and openai packages:

uv pip install sqlalchemy pymysql openai

singlestore_for_agent.py

from os import getenv

from agno.agent import Agent
from agno.db.singlestore import SingleStoreDb

# Configure SingleStore DB connection
USERNAME = getenv("SINGLESTORE_USERNAME")
PASSWORD = getenv("SINGLESTORE_PASSWORD")
HOST = getenv("SINGLESTORE_HOST")
PORT = getenv("SINGLESTORE_PORT")
DATABASE = getenv("SINGLESTORE_DATABASE")
db_url = (
    f"mysql+pymysql://{USERNAME}:{PASSWORD}@{HOST}:{PORT}/{DATABASE}?charset=utf8mb4"
)

# Setup your Database
db = SingleStoreDb(db_url=db_url)

# Create an agent with SingleStore db
agent = Agent(db=db)

Params

Parameter	Type	Default	Description
id	Optional[str]	-	The ID of the database instance. UUID by default.
db_engine	Optional[Engine]	-	The SQLAlchemy database engine to use.
db_schema	Optional[str]	-	The database schema to use.
db_url	Optional[str]	-	The database URL to connect to.
session_table	Optional[str]	-	Name of the table to store Agent, Team and Workflow sessions.
memory_table	Optional[str]	-	Name of the table to store memories.
metrics_table	Optional[str]	-	Name of the table to store metrics.
eval_table	Optional[str]	-	Name of the table to store evaluation runs data.
knowledge_table	Optional[str]	-	Name of the table to store knowledge content.
culture_table	Optional[str]	-	Name of the table to store cultural knowledge.
traces_table	Optional[str]	-	Name of the table to store traces.
spans_table	Optional[str]	-	Name of the table to store spans.
versions_table	Optional[str]	-	Name of the table to store schema versions.
create_schema	bool	True	Whether to create the database schema if it doesn't exist. Set to False when the schema is managed externally.