Overview
In this guide, you’ll:- Configure AWS credentials to enable Bedrock and OpenSearch access
- Set up the Mem0 SDK to use Bedrock for embeddings and LLM
- Store and retrieve memories using OpenSearch as a vector store
- Build memory-aware applications with scalable cloud infrastructure
Prerequisites
- AWS account with access to:
- Bedrock foundation models (e.g., Titan, Claude)
- OpenSearch Service with a configured domain
- Python 3.8+
- Valid AWS credentials (via environment or IAM role)
Setup and Installation
Install required packages:Initialize Mem0 Integration
Import necessary modules and configure Mem0:Memory Operations
Use Mem0 with your Bedrock-powered LLM and OpenSearch storage backend:Key Features
- Serverless Memory Embeddings: Use Titan or other Bedrock models for fast, cloud-native embeddings
- Scalable Vector Search: Store and retrieve vectorized memories via OpenSearch
- Seamless AWS Auth: Uses AWS IAM or environment variables to securely authenticate
- User-specific Memory Spaces: Memories are isolated per user ID
- Persistent Memory Context: Maintain and recall history across sessions
AWS Bedrock Cookbook
Complete guide to using Bedrock with Mem0
Using Mem0? Star us on GitHub to help more developers discover memory for AI apps.