Run This Ai
EN DE

MCP Memory Service

Persistent memory for AI agents — knowledge graph, REST API and MCP server for LangGraph, CrewAI, AutoGen and Claude.

★ 1,900 GitHub Apache-2.0 mcpmemoryknowledge-graphagentslanggraphcrewaiautogenclaude MCP Servers

Overview

Open-source persistent memory layer for AI agents and pipelines. MCP Memory Service gives your LLM applications durable, searchable memory backed by a knowledge graph — with a REST API and a Model Context Protocol (MCP) server that plug directly into LangGraph, CrewAI, AutoGen, OpenCode and Claude. It stores entities, relationships and semantic embeddings, supports autonomous consolidation, and lets agents retrieve relevant context across sessions instead of re-inventing context every run.

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:
  mcp-memory-service:
    image: doobidoo/mcp-memory-service:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/mcp-memory-service:/data

Best VPS for MCP Memory Service →

Related tools

Guides & articles