24kchengYe/MemoMind

715 stars · Last commit 2026-05-01

Give your AI agent a brain that remembers. Local memory system for Claude Code — 100% private, GPU-accelerated, zero cloud dependency.

README preview

<div align="center">



![Visitors](https://visitor-badge.laobi.icu/badge?page_id=24kchengYe.MemoMind)

# 🧠 MemoMind

**Give your AI agent a brain that remembers.**

*A fully local, GPU-accelerated memory system for AI coding agents. Start building your digital twin's memory today — portable, evolving, and ready to migrate when a better system comes along.*

[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
[![MseeP Verified](https://img.shields.io/badge/MseeP-Verified-brightgreen)](https://mseep.ai/app/24kchengye-memomind)
[![Platform](https://img.shields.io/badge/Platform-Windows%20%7C%20Linux%20%7C%20WSL2-orange)](https://github.com/24kchengYe/MemoMind#quick-start)
[![PostgreSQL](https://img.shields.io/badge/Storage-PostgreSQL%20%2B%20pgvector-336791)](https://github.com/pgvector/pgvector)
[![MCP](https://img.shields.io/badge/Protocol-MCP%20(stdio)-blue)](https://modelcontextprotocol.io/)
[![CUDA](https://img.shields.io/badge/GPU-CUDA%20Accelerated-76b900)](https://developer.nvidia.com/cuda-toolkit)

View full repository on GitHub →