MemOS: A Memory OS for AI System Article Swipe

MAKE IMPACT

Zhiyu Li , Shichao Song , Chunyan Xi , Hanyu Wang , Chen Tang , Simin Niu , Chen Ding , Jia‐Wei Yang , Chunyu Li , Qingchen Yu , J. Zhao , Yezhaohui Wang , Peng Liu , Zhaohui Lin , Pengyuan Wang , Jiahao Huo , Tianyi Chen , Kai Chen , Kehang Li , Tao Zhen , Huan Sheng Lai , Hao Wu , Bo Tang , Zhenren Wang , Zheng Fan , Ningyu Zhang , Linfeng Zhang , Junchi Yan , Mingchuan Yang , Tong Xu , Wei Xu , Huajun Chen , Hucheng Wang , Hongkang Yang , Wentao Zhang , Zhi‐Qin John Xu , Siheng Chen , Feiyu Xiong · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.03724

Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI), yet their lack of well-defined memory management systems hinders the development of long-context reasoning, continual personalization, and knowledge consistency.Existing models mainly rely on static parameters and short-lived contextual states, limiting their ability to track user preferences or update knowledge over extended periods.While Retrieval-Augmented Generation (RAG) introduces external knowledge in plain text, it remains a stateless workaround without lifecycle control or integration with persistent representations.Recent work has modeled the training and inference cost of LLMs from a memory hierarchy perspective, showing that introducing an explicit memory layer between parameter memory and external retrieval can substantially reduce these costs by externalizing specific knowledge. Beyond computational efficiency, LLMs face broader challenges arising from how information is distributed over time and context, requiring systems capable of managing heterogeneous knowledge spanning different temporal scales and sources. To address this challenge, we propose MemOS, a memory operating system that treats memory as a manageable system resource. It unifies the representation, scheduling, and evolution of plaintext, activation-based, and parameter-level memories, enabling cost-efficient storage and retrieval. As the basic unit, a MemCube encapsulates both memory content and metadata such as provenance and versioning. MemCubes can be composed, migrated, and fused over time, enabling flexible transitions between memory types and bridging retrieval with parameter-based learning. MemOS establishes a memory-centric system framework that brings controllability, plasticity, and evolvability to LLMs, laying the foundation for continual learning and personalized modeling.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2507.03724

PDF

https://arxiv.org/pdf/2507.03724

OA Status

green

OpenAlex ID

https://openalex.org/W4415163064

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415163064

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2507.03724

Digital Object Identifier

Title

MemOS: A Memory OS for AI System

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-07-04

Full publication date if available

Authors

Zhiyu Li, Shichao Song, Chunyan Xi, Hanyu Wang, Chen Tang, Simin Niu, Chen Ding, Jia‐Wei Yang, Chunyu Li, Qingchen Yu, J. Zhao, Yezhaohui Wang, Peng Liu, Zhaohui Lin, Pengyuan Wang, Jiahao Huo, Tianyi Chen, Kai Chen, Kehang Li, Tao Zhen, Huan Sheng Lai, Hao Wu, Bo Tang, Zhenren Wang, Zheng Fan, Ningyu Zhang, Linfeng Zhang, Junchi Yan, Mingchuan Yang, Tong Xu, Wei Xu, Huajun Chen, Hucheng Wang, Hongkang Yang, Wentao Zhang, Zhi‐Qin John Xu, Siheng Chen, Feiyu Xiong

List of authors in order

Landing page

https://arxiv.org/abs/2507.03724

Publisher landing page

PDF URL

https://arxiv.org/pdf/2507.03724

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2507.03724

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload