MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents

TL;DR

MemEngine is a comprehensive, modular library that enables easy development and integration of advanced memory models for LLM-based agents, promoting research and application in this field.

Contribution

We introduce MemEngine, a unified framework that consolidates various memory models for LLM agents, facilitating extensible and user-friendly memory development.

Findings

Implemented numerous recent memory models within MemEngine

Enhanced ease of development and customization for memory in LLM agents

Publicly released the library to support community research

Abstract

Recently, large language model based (LLM-based) agents have been widely applied across various fields. As a critical part, their memory capabilities have captured significant interest from both industrial and academic communities. Despite the proposal of many advanced memory models in recent research, however, there remains a lack of unified implementations under a general framework. To address this issue, we develop a unified and modular library for developing advanced memory models of LLM-based agents, called MemEngine. Based on our framework, we implement abundant memory models from recent research works. Additionally, our library facilitates convenient and extensible memory development, and offers user-friendly and pluggable memory usage. For benefiting our community, we have made our project publicly available at https://github.com/nuster1128/MemEngine.