You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
## Description
<!--
Please include a summary of the changes below;
Fill in the issue number that this PR addresses (if applicable);
Mention the person who will review this PR (if you know who it is);
Replace (summary), (issue), and (reviewer) with the appropriate
information (No parentheses).
请在下方填写更改的摘要；
填写此 PR 解决的问题编号（如果适用）；
提及将审查此 PR 的人（如果您知道是谁）；
替换 (summary)、(issue) 和 (reviewer) 为适当的信息（不带括号）。
-->
Summary: (summary)
Fix: #(issue)
Reviewer: @(reviewer)
## Checklist:
- [ ] I have performed a self-review of my own code | 我已自行检查了自己的代码
- [ ] I have commented my code in hard-to-understand areas |
我已在难以理解的地方对代码进行了注释
- [ ] I have added tests that prove my fix is effective or that my
feature works | 我已添加测试以证明我的修复有效或功能正常
- [ ] I have added necessary documentation (if applicable) |
我已添加必要的文档（如果适用）
- [ ] I have linked the issue to this PR (if applicable) | 我已将 issue
链接到此 PR（如果适用）
- [ ] I have mentioned the person who will review this PR | 我已提及将审查此 PR
的人
**MemOS** is an operating system for Large Language Models (LLMs) that enhances them with long-term memory capabilities. It allows LLMs to store, retrieve, and manage information, enabling more context-aware, consistent, and personalized interactions.
@@ -66,19 +61,12 @@ MemOS demonstrates significant improvements over baseline memory solutions in mu
66
61
67
62
> 💡 **Temporal reasoning accuracy improved by 159% compared to the OpenAI baseline.**
68
63
69
-
70
-
71
64
### Details of End-to-End Evaluation on LOCOMO
72
65
73
66
> [!NOTE]
74
67
> Comparison of LLM Judge Scores across five major tasks in the LOCOMO benchmark. Each bar shows the mean evaluation score judged by LLMs for a given method-task pair, with standard deviation as error bars. MemOS-0630 consistently outperforms baseline methods (LangMem, Zep, OpenAI, Mem0) across all task types, especially in multi-hop and temporal reasoning scenarios.
If you use MemOS in your research, please cite our paper:
191
+
> [!NOTE]
192
+
> We publicly released the Short Version on **May 28, 2025**, making it the earliest work to propose the concept of a Memory Operating System for LLMs.
193
+
194
+
If you use MemOS in your research, we would appreciate citations to our papers.
200
195
201
196
```bibtex
202
-
@misc{li2025memos,
203
-
title={MemOS: A Memory OS for AI System},
204
-
author={Zhiyu Li and Shichao Song and Chenyang Xi and Hanyu Wang and Chen Tang and Simin Niu and Ding Chen and Jiawei Yang and Chunyu Li and Qingchen Yu and Jihao Zhao and Yezhaohui Wang and Peng Liu and Zehao Lin and Pengyuan Wang and Jiahao Huo and Tianyi Chen and Kai Chen and Kehang Li and Zhen Tao and Junpeng Ren and Huayi Lai and Hao Wu and Bo Tang and Zhenren Wang and Zhaoxin Fan and Ningyu Zhang and Linfeng Zhang and Junchi Yan and Mingchuan Yang and Tong Xu and Wei Xu and Huajun Chen and Haofeng Wang and Hongkang Yang and Wentao Zhang and Zhi-Qin John Xu and Siheng Chen and Feiyu Xiong},
205
-
year={2025},
206
-
eprint={2507.03724},
207
-
archivePrefix={arXiv},
208
-
primaryClass={cs.CL}
197
+
198
+
@article{li2025memos_long,
199
+
title={MemOS: A Memory OS for AI System},
200
+
author={Li, Zhiyu and Song, Shichao and Xi, Chenyang and Wang, Hanyu and Tang, Chen and Niu, Simin and Chen, Ding and Yang, Jiawei and Li, Chunyu and Yu, Qingchen and Zhao, Jihao and Wang, Yezhaohui and Liu, Peng and Lin, Zehao and Wang, Pengyuan and Huo, Jiahao and Chen, Tianyi and Chen, Kai and Li, Kehang and Tao, Zhen and Ren, Junpeng and Lai, Huayi and Wu, Hao and Tang, Bo and Wang, Zhenren and Fan, Zhaoxin and Zhang, Ningyu and Zhang, Linfeng and Yan, Junchi and Yang, Mingchuan and Xu, Tong and Xu, Wei and Chen, Huajun and Wang, Haofeng and Yang, Hongkang and Zhang, Wentao and Xu, Zhi-Qin John and Chen, Siheng and Xiong, Feiyu},
201
+
journal={arXiv preprint arXiv:2507.03724},
202
+
year={2025},
203
+
url={https://arxiv.org/abs/2507.03724}
204
+
}
205
+
206
+
@article{li2025memos_short,
207
+
title={MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models},
208
+
author={Li, Zhiyu and Song, Shichao and Wang, Hanyu and Niu, Simin and Chen, Ding and Yang, Jiawei and Xi, Chenyang and Lai, Huayi and Zhao, Jihao and Wang, Yezhaohui and others},
209
+
journal={arXiv preprint arXiv:2505.22101},
210
+
year={2025},
211
+
url={https://arxiv.org/abs/2505.22101}
212
+
}
213
+
214
+
@article{yang2024memory3,
215
+
author = {Yang, Hongkang and Zehao, Lin and Wenjin, Wang and Wu, Hao and Zhiyu, Li and Tang, Bo and Wenqiang, Wei and Wang, Jinbo and Zeyun, Tang and Song, Shichao and Xi, Chenyang and Yu, Yu and Kai, Chen and Xiong, Feiyu and Tang, Linpeng and Weinan, E},
216
+
title = {Memory$^3$: Language Modeling with Explicit Memory},
We welcome contributions from the community! Please read our [contribution guidelines](https://memos.openmem.net/docs/contribution/overview) to get started.
230
+
We welcome contributions from the community! Please read our [contribution guidelines](https://memos-docs.openmem.net/contribution/overview) to get started.
0 commit comments