InMemoryStorage provides a flexible, lightweight storage solution that keeps all session data in memory, with the option to hook it up to any custom persistent storage solution.

​
Summary

  • No setup or additional dependencies: No installations or database setup required.
  • Custom storage options: Use the built-in dictionary or provide your own for custom persistence.

​
Use Cases

InMemoryStorage is ideal for:
  • Custom Storage Solutions: When you need to integrate with a persistence layer that doesn’t (yet) have first-party agno support (snowflake, AWS S3, etc).
  • Development and Testing: Quick setup without external dependencies.
  • Temporary Sessions: Short-lived applications where persistence isn’t required.

​
Important Notes

  • Data Persistence: Session data is not persistent across program restarts unless you provide an external dictionary with your own persistence mechanism.
  • Memory Usage: All session data is stored in RAM. For applications with many long sessions, monitor memory usage.
Remember that data is lost when your application restarts unless you implement your own persistence mechanism using a custom dictionary.

​
Usage

​
Basic Agent with In-Memory Storage

Here’s a simple example of using in-memory storage with an agent:
agent.py
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.storage.in_memory import InMemoryStorage

agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    storage=InMemoryStorage(),
    add_history_to_messages=True,
)

# Run some conversations
agent.print_response("What is the capital of France?")
agent.print_response("What is its population?")

​
Bring Your Own Dictionary (Custom Storage Integration)

The real power of InMemoryStorage comes from providing your own dictionary for custom storage mechanisms:
custom_persistence.py
import json

import boto3
from agno.storage.in_memory import InMemoryStorage
from agno.agent import Agent
from agno.models.openai import OpenAIChat

# Example: Save and load sessions to/from S3
def save_sessions_to_s3(sessions_dict, bucket_name, key_name):
    """Save sessions dictionary to S3"""
    s3 = boto3.client('s3')
    s3.put_object(
        Bucket=bucket_name,
        Key=key_name,
        Body=json.dumps(sessions_dict, default=str)
    )

def load_sessions_from_s3(bucket_name, key_name):
    """Load sessions dictionary from S3"""
    s3 = boto3.client('s3')
    try:
        response = s3.get_object(Bucket=bucket_name, Key=key_name)
        return json.loads(response['Body'].read())
    except:
        return {}  # Return empty dict if file doesn't exist

# Step 1: Create agent with external dictionary
my_sessions = {}
storage = InMemoryStorage(storage_dict=my_sessions)

agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    storage=storage,
    add_history_to_messages=True,
)

# Run some conversations
agent.print_response("What is the capital of France?")
agent.print_response("What is its population?")

print(f"Sessions in memory: {len(my_sessions)}")

# Step 2: Save sessions to S3
save_sessions_to_s3(my_sessions, "my-bucket", "agent-sessions.json")
print("Sessions saved to S3!")

# Step 3: Later, load sessions from S3 and use with new agent
loaded_sessions = load_sessions_from_s3("my-bucket", "agent-sessions.json")
new_storage = InMemoryStorage(storage_dict=loaded_sessions)

new_agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    storage=new_storage,
    session_id=agent.session_id,  # Use same session ID
    add_history_to_messages=True,
)

# This agent now has access to the previous conversation
new_agent.print_response("What was my first question?")

​
Developer Resources