We’re excited to announce a strategic partnership between AWS and Mem0 to enhance the capabilities of agentic AI. This collaboration integrates Mem0’s advanced memory layer into Strands Agents SDK, bringing persistent, contextual, and highly personalized memory to cloud-native autonomous agents. Introducing Strands + Mem0: A New Standard for Agentic

OpenMemory is a local memory infrastructure powered by Mem0 that lets you carry your memory accross any AI app. It provides a unified memory layer that stays with you, enabling agents and assistants to remember what matters across applications. Today, we’re launching the first building block: the OpenMemory MCP

Mem0's Custom Categories feature that is available on the Mem0 platform is a powerful tool for developers and businesses looking to create more intelligent and context-aware applications. This guide will walk you through everything you need to know about Custom Categories in Mem0. What Are Custom Categories in

What is Memory Customization? Memory customization (available on the Mem0 platform) allows developers to fine-tune what information their AI applications store and retrieve. This feature goes beyond traditional RAG (Retrieval-Augmented Generation) systems by providing granular control over memory storage through two main approaches: Memory Inclusion and Memory Exclusion. Why Memory

Effective memory retrieval is key to building AI applications that provide contextually relevant responses. Mem0's search() operation is your gateway to accessing stored memories intelligently. In this guide, we'll explore how to use client.search() effectively, from basic queries to advanced filtering techniques. Basic Search Operations

The add() operation is a basic part of Mem0's memory management system. It's how you store information your application or agent can later recall. Whether you're saving user preferences, maintaining conversation context, or building consistent AI personalities, understanding how to use add() effectively is

For Large Language Model (LLM) powered agents and applications, efficient memory management can make or break your application. Implementing a memory management systems from scratch is complex and doesn’t directly make the core product valuable. But what if you could add and search memory with just a few lines

Personal AI companions are here, and they're not going away. To grasp the scale of this emerging sector, consider this: Character AI, a leading company, reports that their users spend over two hours daily talking to chatbots. The company handles over 20,000 queries per second - 20%

You can find a notebook with all the code mentioned in this guide here. AI Companions are among the most evident and exciting use cases of large language models (LLMs). However, they have a problem. They can’t quite store memories about the user across conversations (not unless the developer

We're excited to announce that Supermemory is now a customer of Mem0, integrating a power memory layer into their digital knowledge hub.  What is Supermemory? Supermemory acts as a “digital brain”— a place for organizing, searching, and utilizing saved information from the internet. It provides easy tools for

We're excited to introduce Mem0—the memory layer to create personalized AI applications. Mem0 gives any LLM or agent application the ability to store user preferences, traits, action histories, life events, and more in a smart and self-improving long-term memory layer. Mem0 is available today, both as open-source