Mem0

Prerequisites

The Mem0 toolkit requires the mem0ai Python package and either a Mem0 API key for cloud usage or local configuration for self-hosted deployments.

pip install mem0ai

For cloud usage with the Mem0 app:

export MEM0_API_KEY=your_api_key
export MEM0_ORG_ID=your_org_id          # Optional
export MEM0_PROJECT_ID=your_project_id  # Optional

Example

The following example demonstrates how to create an agent with access to Mem0 memory:

cookbook/tools/mem0_tools.py

from textwrap import dedent

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.mem0 import Mem0Tools

USER_ID = "jane_doe"
SESSION_ID = "agno_session"

# Initialize the Agent with Mem0Tools
agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    tools=[Mem0Tools()],
    user_id=USER_ID,
    session_id=SESSION_ID,
    add_state_in_messages=True,
    markdown=True,
    instructions=dedent(
        """
        You have an evolving memory of this user. Proactively capture new 
        personal details, preferences, plans, and relevant context the user 
        shares, and naturally bring them up in later conversation. Before 
        answering questions about past details, recall from your memory 
        to provide precise and personalized responses. Keep your memory concise: store only meaningful 
        information that enhances long-term dialogue. If the user asks to start fresh,
        clear all remembered information and proceed anew.
        """
    ),
    show_tool_calls=True,
)

# Interact with the Agent to store memories
agent.print_response("I live in NYC")
agent.print_response("I lived in San Francisco for 5 years previously")
agent.print_response("I'm going to a Taylor Swift concert tomorrow")

# Query the stored memories
agent.print_response("Summarize all the details of the conversation")

Toolkit Params

Parameter	Type	Default	Description
`config`	`dict`	`None`	Configuration dictionary for self-hosted Mem0 instance.
`api_key`	`str`	`None`	Mem0 API key. If not provided, uses MEM0_API_KEY env var.
`user_id`	`str`	`None`	Default user ID for memory operations.
`org_id`	`str`	`None`	Organization ID. If not provided, uses MEM0_ORG_ID env var.
`project_id`	`str`	`None`	Project ID. If not provided, uses MEM0_PROJECT_ID env var.
`infer`	`bool`	`True`	Whether to enable automatic memory inference and extraction.

Toolkit Functions

Function	Description
`add_memory`	Adds facts to the user’s memory. Supports both text strings and structured dictionaries. Returns success confirmation or error message.
`search_memory`	Performs semantic search across the user’s stored memories. Takes `query` (str) to find relevant facts. Returns list of search results or error message.
`get_all_memories`	Retrieves all memories for the current user. Returns list of all stored memories.
`delete_all_memories`	Deletes all memories associated with the current user. Returns success confirmation or error message.

Configuration Options

from agno.tools.mem0 import Mem0Tools

config = {
    "vector_store": {
        "provider": "chroma",
        "config": {
            "collection_name": "test",
            "path": "db",
        }
    },
    "llm": {
        "provider": "openai",
        "config": {
            "model": "gpt-4o-mini",
            "temperature": 0.1,
            "max_tokens": 1000,
        }
    },
    "embedder": {
        "provider": "openai",
        "config": {
            "model": "text-embedding-ada-002",
        }
    }
}

mem0_tools = Mem0Tools(config=config)

Introduction

Concepts

Other

How to

Prerequisites

Example

Toolkit Params

Toolkit Functions

Configuration Options

Developer Resources

​Prerequisites

​Example

​Toolkit Params

​Toolkit Functions

​Configuration Options

​Developer Resources

Prerequisites

Example

Toolkit Params

Toolkit Functions

Configuration Options

Developer Resources