Claude Skill

MemTensor/MemOS

MemOS is a self-evolving memory OS for LLMs and AI agents, featuring ultra-persistent memory, hybrid retrieval, and cross-task skill reuse. Achieve 35.24% token savings with Claude Skill integration.

Overview

Stars10,086
Forks915
LanguageTypeScript
Last pushed2026-07-03
Last synced2026-07-03
View on GitHub

Repository

OwnerMemTensor
RepositoryMemOS
Full nameMemTensor/MemOS
Repo ID1,014,729,376

Install this Skill

git clone https://github.com/MemTensor/MemOS.git

Registry

Typemcp_server
Quality score85/100
Verificationreadme_parsed
Last verified2026-05-28
Platforms
ClaudeMCPOpenClaw
Capabilities
code-reviewpdfmemorysearchimageterminalworkflowagentagentic-aiai
Detected files
README.mddocsexamplespyproject.tomltests
Config keys
URLOPENAI_API_KEYMOS_EMBEDDER_API_KEYMEMRADER_API_KEY
Install methods
  • git clone https://github.com/MemTensor/MemOS.git
  • pip install -r ./docker/requirements.txt

Summary

MemOS is a self-evolving memory operating system designed for LLMs and AI agents, offering ultra-persistent memory, hybrid retrieval, and cross-task skill reuse. It achieves 35.24% token savings by intelligently managing and reusing Claude Skills across diverse tasks.

Chinese description

AI记忆操作系统,专为LLM与智能体系统设计,实现跨任务技能持久化存储、复用与进化能力的Claude Skill管理平台。

Key features

  • Ultra-persistent memory for long-term context retention
  • Hybrid retrieval combining semantic and structured search
  • Cross-task skill reuse with self-evolving capabilities
  • 35.24% token savings through efficient memory management
  • Seamless integration with Claude Skill and multi-agent systems

Use cases

  • Building AI agents with long-term memory for complex workflows
  • Reducing token costs in LLM-powered applications
  • Enabling multi-agent collaboration with shared skill libraries
  • Creating self-improving AI assistants that learn from past tasks

README excerpt

<div align="center"> <a href="https://memos.openmem.net/"> <img src="https://statics.memtensor.com.cn/memos/memos-banner.gif" alt="MemOS Banner"> </a> <h1 align="center"> <img src="https://statics.memtensor.com.cn/logo/memos_color_m.png" alt="MemOS Logo" width="48"/>&nbsp; MemOS 2.0&ensp;Stardust(星尘) </h1> <p align="center"> <br> <a href="https://memos-docs.openmem.net/home/overview/"><img src="https://img.shields.io/badge/Docs-Get--Start-002FA7?labelColor=gray&style=for-the-badge&logo=googledocs&logoColor=white" alt="Docs"></a> <a href="https://arxiv.org/abs/2507.03724"><img src="https://img.shields.io/badge/ArXiv-2507.03724-B31B1B?labelColor=gray&style=for-the-badge&logo=arxiv&logoColor=white" alt="ArXiv"></a> <a href="https://x.com/MemOS_dev"><img src="https://img.shields.io/badge/Follow-MemOS-000000?labelColor=gray&style=for-the-badge&logo=x&logoColor=white" alt="X"></a> <a href="https://discord.gg/Txbx3gebZR"><img src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Fv10%2Finvites%2FTxbx3gebZR%3Fwith_counts%3Dtrue&query=%24.approximate_presence_count&suffix=%20online&label=Discord&color=404EED&labelColor=gray&style=for-the-badge&logo=discord&logoColor=white" alt="Discord"></a> <a href="https://github.com/IAAR-Shanghai/Awesome-AI-Memory"><img src="https://img.shields.io/badge/Resources-Awesome--AI--Memory-8A2BE2?labelColor=gray&style=for-the-badge&logo=awesomelists&logoColor=white" alt="Resources"></a> </p> <p align="center"> <strong>🎯 +43.70% Accuracy vs. OpenAI Memory</strong><br/> <strong>🏆 Top-tier Long-term Memory + Personalization</strong><br/> <strong>💰 Saves 35.24% Memory Tokens</strong><br/> <sub>LoCoMo 75.80 • LongMemEval +40.43% • PrefEval-10 +2568% • PersonaMem +40.75%</sub> <!-

Topics

Explore more

Data from GitHub. Synced on 2026-07-03