Run This Ai
EN DE

MemOS

Self-evolving Memory OS for LLMs & AI Agents — ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse with 35% token savings

★ 10,383 GitHub Apache-2.0 ai-agentsmemoryllmknowledge-basemulti-agentvector-databaserag AI Agents

Overview

MemOS is a Memory Operating System for LLMs and AI agents that unifies store, retrieve, and manage for long-term memory. It enables context-aware and personalized interactions with knowledge base support, multi-modal memory, tool memory, and enterprise-grade optimizations. Key features include a unified Memory API, multi-modal memory support for text, images, tool traces, and personas, multi-cube knowledge base management, asynchronous ingestion via MemScheduler, and memory feedback with natural-language correction. MemOS leads multiple benchmarks with scores of 88.83 on LoCoMo and 89.20 on LongMemEval, and improves OpenClaw task completion from 36.63% to 50.87%.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  memos:
    image: ghcr.io/memtensor/memos:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/memos:/data

Best VPS for MemOS →

Related tools

Guides & articles