Sessions and memory

Persistent multi-turn conversations and per-user memory.

An agent needs two kinds of state: what was said in this thread and what the agent knows about this user. Agno stores both in its configured database.

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIResponses

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

agent = Agent(
    model=OpenAIResponses(id="gpt-5.5"),
    db=db,
    add_history_to_context=True,
    num_history_runs=5,
    update_memory_on_run=True,
)

agent.run(
    "My name is Sarah and I prefer email over phone.",
    user_id="[e-mail]",
    session_id="thread-42",
)
reply = agent.run(
    "What's the best way to reach me?",
    user_id="[e-mail]",
    session_id="thread-99",
).content
# The sessions have separate histories. Stored user memory can carry the preference.

Sessions vs memory

Session history and memory solve different problems and can be used together.

	Session history	Memory
Stores	The messages in this conversation thread	Learned facts about the user
Scope	One session_id	One user_id, across all their sessions
Enable with	add_history_to_context=True	enable_agentic_memory=True or update_memory_on_run=True
Answers	”What did we just discuss?"	"What do I know about this person?”

Identifiers

Identifier	Distinguishes	Maps to in your product
user_id	The person	Your auth subject (user ID, email)
session_id	A conversation thread for that person	A chat tab, a Slack thread, a support case

Pass both on every run. session_id scopes conversation threads, while user_id scopes memory.

Memory: automatic or agentic

Mode	Set	Use when
Automatic	update_memory_on_run=True	You want memory computed after every run. Without a user_id, memories land under the default user.
Agentic	enable_agentic_memory=True	The agent decides using tool calls.

Reading memory back

For a profile screen or a debug view, pull a user’s memories directly.

memories = agent.get_user_memories(user_id="[e-mail]")

Long conversations

num_history_runs bounds the history that flows into context. It defaults to 3. Session summaries give the agent recall of the earlier thread on top of that bounded history.

Technique	Effect
num_history_runs=N	Only the last N stored runs flow into context
enable_session_summaries=True	A running summary of the session is added to the system prompt, in addition to the history already in context

Next steps

Task	Guide
Put this behind an HTTP API	Serve as an API
Carry memory across Slack and web	Interfaces
Give the agent external data	Connecting your data

Developer Resources

• Sessions
• Session management
• Memory
• Memory cookbook