MemOS

MemTensor/MemOS

Self-evolving memory OS for LLM & AI Agents with ultra-persistent memory, hybrid-retrieval, cross-task skill reuse

GitHub Website

10k

Stars

920

Forks

180

Open issues

Watchers

TypeScript Apache-2.0Last pushed Jul 7, 2026

Overview

MemOS is a self-evolving system designed to optimize long-term memory management for large language models (LLM) and AI agents. It offers features such as token savings, persistent memory storage, enhanced retrieval mechanisms, and support for multi-agent systems.

Similar tools

ECC

affaan-m/ECC

The agent harness performance optimization system

227k 35kJavaScript

hermes-agent

NousResearch/hermes-agent

The self-improving AI agent built by Nous Research

211k 39kPython

AutoGPT

Significant-Gravitas/AutoGPT

AutoGPT: Build, Deploy, and Run AI Agents

185k 46kPython

ollama

ollama/ollama

Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

176k 17kGo

transformers

huggingface/transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models

162k 34kPython

langflow

langflow-ai/langflow

Langflow is a powerful platform for building and deploying AI-powered agents and workflows.

151k 9.5kPython

Install

npm install MemOS

npm Docs / website

README

MemOS 2.0 Stardust（星尘）

🏆 Leading Performance Across Agent and User Memory Benchmarks
🤖 OpenClaw Task Completion Improves from 36.63% to 50.87%
🎯 92.34 on LoCoMo and 93.40 on LongMemEval
📊 Unified Evaluation Across 14 Commercial Memory Products

🧠 MemOS Plugin: Persistent Memory for Your AI Agents ✨

Your lobsters and Hermes Agents now have the best memory system — choose Cloud Service or Self-hosted to get started 🏃🏻

🔌 Plugin	💡 Core Features	🧩 Resources
🧠 memos-local-plugin 2.0	One local-first memory core for Hermes Agent and OpenClaw. Self-evolving memory: L1 trace, L2 policy, L3 world model, and crystallized Skills driven by feedback.	🌐 Website · 📖 Docs · 🐙 GitHub · 📦 NPM
☁️ OpenClaw Cloud Plugin	Reduces token usage by 72%. Multi-agent memory sharing by `user_id`.	🖥️ MemOS Dashboard · 📖 Full Tutorial

🐳 Docker Deployment Note: When running memos-local-plugin in Docker containers, you must specify the config location using MEMOS_HOME environment variable or --home CLI flag. See Docker Configuration Guide for details.

👾 MemOS: Memory Operating System for LLM & AI Agents

MemOS is a Memory Operating System for LLMs and AI agents that unifies store / retrieve / manage for long-term memory, enabling context-aware and personalized interactions with KB, multi-modal, tool memory, and enterprise-grade optimizations built in.