Share Memory between Agents

This example demonstrates how to share memory between Agents.

This means that memories created by one Agent, will be available to the other Agents.

Code

agents_share_memory.py

from agno.agent.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools
from rich.pretty import pprint

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

db = PostgresDb(db_url=db_url)

john_doe_id = "[e-mail]"

chat_agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    description="You are a helpful assistant that can chat with users",
    db=db,
    enable_user_memories=True,
)

chat_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,
)

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


research_agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    description="You are a research assistant that can help users with their research questions",
    tools=[DuckDuckGoTools(cache_results=True)],
    db=db,
    enable_user_memories=True,
)

research_agent.print_response(
    "I love asking questions about quantum computing. What is the latest news on quantum computing?",
    stream=True,
    user_id=john_doe_id,
)

memories = research_agent.get_user_memories(user_id=john_doe_id)
print("Memories about John Doe:")
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. Install libraries

   pip install -U agno rich
   
3. Run Example

   Mac

   python cookbook/memory/03_agents_share_memory.py