Memory OS of AI Agent

TL;DR

This paper introduces MemoryOS, a hierarchical memory management system inspired by operating systems, designed to enhance long-term memory and personalization in AI agents, demonstrated by significant improvements on the LoCoMo benchmark.

Contribution

MemoryOS is a novel hierarchical memory management framework for AI agents, enabling dynamic memory updates and integration across multiple storage levels.

Findings

49.11% improvement in F1 score on LoCoMo benchmark

46.18% improvement in BLEU-1 score on LoCoMo benchmark

Enhanced contextual coherence and personalized memory retention

Abstract

Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with AI agents. To overcome this challenge, we innovatively propose a Memory Operating System, i.e., MemoryOS, to achieve comprehensive and efficient memory management for AI agents. Inspired by the memory management principles in operating systems, MemoryOS designs a hierarchical storage architecture and consists of four key modules: Memory Storage, Updating, Retrieval, and Generation. Specifically, the architecture comprises three levels of storage units: short-term memory, mid-term memory, and long-term personal memory. Key operations within MemoryOS include dynamic updates between storage units: short-term to mid-term updates follow a dialogue-chain-based FIFO principle, while mid-term to long-term updates use a segmented page organization strategy. Our pioneering MemoryOS enables hierarchical memory integration and dynamic updating. Extensive experiments on the LoCoMo benchmark show an average improvement of 49.11% on F1 and 46.18% on BLEU-1 over the baselines on GPT-4o-mini, showing contextual coherence and personalized memory retention in long conversations. The implementation code is open-sourced at https://github.com/BAI-LAB/MemoryOS.