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

TL;DR

This work addresses the fragmentation of memory implementations for LLM-based agents by introducing MemEngine, a unified, modular library organized into three hierarchical levels: memory functions, memory operations, and memory models. It provides a suite of pre-implemented memory models (e.g., FUMemory, LTMemory, GAMemory, MBMemory, MTMemory) with configurable prompts and hyper-parameters, plus a configuration and utilities layer to streamline development and deployment. The framework emphasizes modularity, reusability, and extensibility, enabling researchers to customize functions, operations, and models and to deploy locally or remotely with compatibility to popular agent frameworks. By consolidating diverse memory models under one framework and offering convenient deployment and customization pathways, MemEngine aims to accelerate research and practical development of memory-enhanced LLM-based agents across varied tasks, with future plans for multi-modal memory support.

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.

Figures (1)

• Figure 1: An overview framework of MemEngine Library.