Quickstart

Enable Learning

The simplest way: set learning=True.

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses

db = SqliteDb(db_file="tmp/agents.db")

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=True,
)

This enables user profile and user memory extraction in Always mode. The agent automatically captures information and recalls it in future sessions.

Test It

# Session 1: Share information
agent.print_response(
    "Hi! I'm Sarah, I work at Acme Corp as a data scientist.",
    user_id="sarah@acme.com",
    session_id="session_1",
)

# Session 2: Agent remembers
agent.print_response(
    "What do you know about me?",
    user_id="sarah@acme.com",
    session_id="session_2",
)

Session 2 is a new conversation, but the agent remembers Sarah.

Choose What Gets Learned

For more control, configure stores individually:

from agno.learn import LearningMachine

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=LearningMachine(
        user_profile=True,      # Structured facts (name, role, preferences)
        user_memory=True,       # Unstructured observations
        session_context=True,   # Session summary and goals
        entity_memory=False,    # Facts about external entities
        learned_knowledge=False # Insights across users (requires Knowledge)
    ),
)

See Learning Stores for details on each store.

Choose How Learning Happens

Each store can use a different learning mode:

from agno.learn import (
    LearningMachine,
    LearningMode,
    UserProfileConfig,
    UserMemoryConfig,
)

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=LearningMachine(
        user_profile=UserProfileConfig(mode=LearningMode.ALWAYS),
        user_memory=UserMemoryConfig(mode=LearningMode.AGENTIC),
    ),
)

Mode	How it works
Always	Extraction runs automatically from the messages prepared for the current model call
Agentic	Agent receives tools and decides what to save
Propose	Agent proposes learnings, you approve before saving

In Agno v2.7.4, Always-mode extraction starts before the model call. It sees the current input and any history included in that call. The generated response becomes available to extraction when it appears in a later run’s history.

See Learning Modes for details.

Production Database

For production, use PostgreSQL:

from agno.db.postgres import PostgresDb

db = PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai")

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    learning=True,
)

Get Started

Basics

Advanced

Production

Providers

Other

Additional Resources

Enable Learning

Test It

Choose What Gets Learned

Choose How Learning Happens

Production Database

Next Steps

Learning Stores

Learning Modes

​Enable Learning

​Test It

​Choose What Gets Learned

​Choose How Learning Happens

​Production Database

​Next Steps

Learning Stores

Learning Modes

Enable Learning

Test It

Choose What Gets Learned

Choose How Learning Happens

Production Database

Next Steps