Session Storage

Store and retrieve agent sessions from your database.

When you add a database to your agent, sessions are stored automatically. A session groups related runs into a conversation thread - every message, response, and piece of metadata is persisted under a session_id. This page covers how to access and configure that storage.

Configure the Session Table

By default, sessions are stored in the agno_sessions table. The table is created automatically if it doesn't exist.

Use session_table to store sessions in a custom table:

1from kern.db.postgres import PostgresDb
2
3db = PostgresDb(
4    db_url="postgresql://user:password@localhost:5432/mydb",
5    session_table="my_agent_sessions",
6)
7
8agent = Agent(db=db)

Tip

Use separate tables for different agents or environments.

What Gets Stored

Each session record contains:

Field	Type	Description
`session_id`	`str`	Unique session identifier
`session_type`	`str`	Type of session (agent, team, or workflow)
`agent_id`	`str`	The agent ID (if agent session)
`team_id`	`str`	The team ID (if team session)
`workflow_id`	`str`	The workflow ID (if workflow session)
`user_id`	`str`	The user this session belongs to
`session_data`	`dict`	Session-specific data and state
`agent_data`	`dict`	Agent configuration and metadata
`team_data`	`dict`	Team configuration and metadata
`workflow_data`	`dict`	Workflow configuration and metadata
`metadata`	`dict`	Additional custom metadata
`runs`	`list`	All the runs (interactions) in this session
`summary`	`dict`	The session summary (if enabled)
`created_at`	`int`	Unix timestamp when session was created
`updated_at`	`int`	Unix timestamp of last update

Retrieve Sessions

Use get_session() to retrieve a stored session:

1from kern.agent import Agent
2from kern.db.sqlite import SqliteDb
3
4agent = Agent(db=SqliteDb(db_file="agent.db"))
5
6agent.print_response("What is the capital of France?", session_id="session_123")
7
8# Retrieve the session
9session = agent.get_session(session_id="session_123")
10
11# Access session data
12print(session.session_id)
13print(session.runs)  # List of runs with messages and responses

Works With Teams and Workflows

Session storage works identically for Teams and Workflows:

1from kern.team import Team
2from kern.workflow import Workflow
3from kern.db.sqlite import SqliteDb
4
5db = SqliteDb(db_file="kern.db")
6
7team = Team(db=db, ...)
8workflow = Workflow(db=db, ...)
9
10# Retrieve sessions the same way
11team_session = team.get_session(session_id="team_session_123")
12workflow_session = workflow.get_session(session_id="workflow_session_456")

Note

Workflow sessions store complete pipeline runs rather than conversation messages. See Workflow Sessions for details.

Next Steps

compress

Session Summaries

Condense long conversations to save tokens.

sliders

Storage Control

Choose what gets persisted to your database.