🔐 Mem0 is now SOC 2 and HIPAA compliant! We're committed to the highest standards of data security and privacy, enabling secure memory for enterprises, healthcare, and beyond.

This example demonstrates how to configure and use the mem0ai SDK with AWS Bedrock and OpenSearch Service (AOSS) for persistent memory capabilities in Python.

​
Installation

Install the required dependencies:

pip install mem0ai boto3 opensearch-py

​
Environment Setup

Set your AWS environment variables:

import os

# Set these in your environment or notebook
os.environ['AWS_REGION'] = 'us-west-2'
os.environ['AWS_ACCESS_KEY_ID'] = 'AK00000000000000000'
os.environ['AWS_SECRET_ACCESS_KEY'] = 'AS00000000000000000'

# Confirm they are set
print(os.environ['AWS_REGION'])
print(os.environ['AWS_ACCESS_KEY_ID'])
print(os.environ['AWS_SECRET_ACCESS_KEY'])

​
Configuration and Usage

This sets up Mem0 with AWS Bedrock for embeddings and LLM, and OpenSearch as the vector store.

import boto3
from opensearchpy import OpenSearch, RequestsHttpConnection, AWSV4SignerAuth
from mem0.memory.main import Memory

region = 'us-west-2'
service = 'aoss'
credentials = boto3.Session().get_credentials()
auth = AWSV4SignerAuth(credentials, region, service)

config = {
    "embedder": {
        "provider": "aws_bedrock",
        "config": {
            "model": "amazon.titan-embed-text-v2:0"
        }
    },
    "llm": {
        "provider": "aws_bedrock",
        "config": {
            "model": "anthropic.claude-3-5-haiku-20241022-v1:0",
            "temperature": 0.1,
            "max_tokens": 2000
        }
    },
    "vector_store": {
        "provider": "opensearch",
        "config": {
            "collection_name": "mem0",
            "host": "your-opensearch-domain.us-west-2.es.amazonaws.com",
            "port": 443,
            "http_auth": auth,
            "embedding_model_dims": 1024,
            "connection_class": RequestsHttpConnection,
            "pool_maxsize": 20,
            "use_ssl": True,
            "verify_certs": True
        }
    }
}

# Initialize memory system
m = Memory.from_config(config)

​
Usage

​
Add a memory:

messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]

# Store inferred memories (default behavior)
result = m.add(messages, user_id="alice", metadata={"category": "movie_recommendations"})

​
Search a memory:

relevant_memories = m.search(query, user_id="alice")

​
Get all memories:

all_memories = m.get_all(user_id="alice")

​
Get a specific memory:

memory = m.get(memory_id)

​
Conclusion

With Mem0 and AWS services like Bedrock and OpenSearch, you can build intelligent AI companions that remember, adapt, and personalize their responses over time. This makes them ideal for long-term assistants, tutors, or support bots with persistent memory and natural conversation abilities.