Skip to content

Source paper

MemOS: A Memory OS for AI System

Zhiyu Li, Shichao Song, Chenyang Xi and 36 more

Zhiyu Li, Shichao Song, Chenyang Xi, Hanyu Wang, Chen Tang, Simin Niu, Ding Chen, Jiawei Yang, Chunyu Li, Qingchen Yu, Jihao Zhao, Yezhaohui Wang, Peng Liu, Zehao Lin, Pengyuan Wang, Jiahao Huo, Tianyi Chen, Kai Chen, Kehang Li, Zhen Tao, Junpeng Ren, Huayi Lai, Hao Wu, Bo Tang, Zhenren Wang, Zhaoxin Fan, Ningyu Zhang, Linfeng Zhang, Junchi Yan, Mingchuan Yang, Tong Xu, Wei Xu, Huajun Chen, Haofeng Wang, Hongkang Yang, Wentao Zhang, Zhi-Qin John Xu, Siheng Chen, Feiyu Xiong

arXiv 2507.03724 · 2025159 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

This paper proposes MemOS, a novel operating system framework designed to manage the memory of Large Language Models (LLMs) as a schedulable, hierarchical resource rather than a static dependency. By unifying plaintext retrieval, activation states (KV-cache), and parameter adapters into a standardized 'MemCube' unit, the system enables dynamic memory scheduling, lifecycle management, and consistent long-term context across different agents and sessions.

How it works (AI summary)

The authors introduce a layered OS architecture consisting of an Interface Layer (MemReader), Operation Layer (MemScheduler, MemOperator), and Infrastructure Layer (MemVault). The core innovation is the 'MemCube,' a container that encapsulates memory content (plaintext, tensors, or weights) with metadata, allowing the system to dynamically transition memory between active GPU cache, long-term storage, and parametric weights based on usage frequency and task context.