Agent With Memory

This example shows you how to use persistent memory with an Agent.

After each run, user memories are created/updated.

To enable this, set enable_user_memories=True in the Agent config.

Code

cookbook/agent_concepts/memory/06_agent_with_memory.py

from agno.agent.agent import Agent
from agno.memory.v2.db.sqlite import SqliteMemoryDb
from agno.memory.v2.memory import Memory
from agno.models.openai import OpenAIChat
from agno.storage.sqlite import SqliteStorage
from rich.pretty import pprint
from utils import print_chat_history

memory_db = SqliteMemoryDb(table_name="memory", db_file="tmp/memory.db")

# No need to set the model, it gets set by the agent to the agent's model
memory = Memory(db=memory_db)

# Reset the memory for this example
memory.clear()

session_id = "session_1"
john_doe_id = "[e-mail]"

agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    memory=memory,
    storage=SqliteStorage(
        table_name="agent_sessions", db_file="tmp/persistent_memory.db"
    ),
    enable_user_memories=True,
)

agent.print_response(
    "My name is John Doe and I like to hike in the mountains on weekends.",
    stream=True,
    user_id=john_doe_id,
    session_id=session_id,
)

agent.print_response(
    "What are my hobbies?", stream=True, user_id=john_doe_id, session_id=session_id
)

# -*- Print the chat history
session_run = memory.runs[session_id][-1]
print_chat_history(session_run)

memories = memory.get_user_memories(user_id=john_doe_id)
print("John Doe's memories:")
pprint(memories)

agent.print_response(
    "Ok i dont like hiking anymore, i like to play soccer instead.",
    stream=True,
    user_id=john_doe_id,
    session_id=session_id,
)

# -*- Print the chat history
session_run = memory.runs[session_id][-1]
print_chat_history(session_run)

# You can also get the user memories from the agent
memories = agent.get_user_memories(user_id=john_doe_id)
print("John Doe's memories:")
pprint(memories)

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   

2. Set your API key

   export GOOGLE_API_KEY=xxx
   

3. Install libraries

   pip install -U agno google-generativeai
   

4. Run Example

   Mac

   python cookbook/agent_concepts/memory/06_agent_with_memory.py