What is Memory?

Customer support agents, product copilots, and personal assistants often serve the same user across many conversations. Memory keeps facts such as preferences, responsibilities, and recurring goals available across those conversations.

memory_agent.py

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

agent = Agent(
    model=OpenAIResponses(id="gpt-5.4-mini"),
    db=SqliteDb(db_file="tmp/memory.db"),
    update_memory_on_run=True,
)

agent.print_response(
    "I prefer email updates and morning meetings.",
    user_id="sarah",
    session_id="onboarding",
)

agent.print_response(
    "How should you schedule and send my project updates?",
    user_id="sarah",
    session_id="project-planning",
)

The first run stores useful facts for sarah. The second run uses the same user_id, so the agent can recall those facts in a different session.

How Memory Works

user_id identifies whose memories should be loaded.
The configured database stores each user’s memory records.
Stored memories for that user are added to the model context for later runs.
The selected memory mode controls when records are created, updated, or deleted.

Use a stable application user ID for every run that should share the same memories.

Choose a Memory Mode

Mode	Configuration	Use it when
Automatic	`update_memory_on_run=True`	Each user input should be processed into memories automatically
Agentic	`enable_agentic_memory=True`	The model should decide when to inspect, create, update, or delete memories during a run

Automatic memory applies one consistent extraction step during each run. Agentic memory adds memory tools to the agent’s toolset and lets the model choose when to call them.

When both settings are enabled, agentic memory takes precedence and the automatic extraction step is skipped. Choose one mode for each agent.

Memory, History, and State

Feature	Stores	Scope	Use it for
Memory	Extracted facts about a user	`user_id` across sessions	Preferences, profile details, recurring goals
Chat history	Messages and tool calls from previous runs	`session_id`	Conversational continuity within one thread
Session state	Application data managed by code or tools	`session_id`	Carts, task lists, workflow progress, counters

These features can work together. A support agent can use memory for the customer’s communication preference, history for the current ticket, and state for the ticket status.

Store and Inspect Memories

Memories use the database configured on the agent. The default table or collection name is agno_memories. Set memory_table on the database when your application needs a custom name.

memories = agent.get_user_memories(user_id="sarah")

for memory in memories or []:
    print(memory.memory_id, memory.memory)

Manual retrieval is useful for customer profile screens, debugging, review, and deletion workflows. You can also manage memories in the AgentOS UI.

Next Steps

Agent Memory

Configure memory for a single agent.

Team Memory

Share user memories with a team and its members.

Working with Memories

Customize memory creation, retrieval, and storage.

Production Best Practices

Plan user isolation, retention, and memory quality checks.

Get Started

Basics

Advanced

Production

Providers

Other

Additional Resources

What is Memory?

How Memory Works

Choose a Memory Mode

Memory, History, and State

Store and Inspect Memories

Next Steps

Agent Memory

Team Memory

Working with Memories

Production Best Practices

​How Memory Works

​Choose a Memory Mode

​Memory, History, and State

​Store and Inspect Memories

​Next Steps

Agent Memory

Team Memory

Working with Memories

Production Best Practices

How Memory Works

Choose a Memory Mode

Memory, History, and State

Store and Inspect Memories

Next Steps