README.md

MCP Memory Service Documentation

Welcome to the comprehensive documentation for MCP Memory Service - a Model Context Protocol server that provides semantic memory and persistent storage capabilities for Claude Desktop and other MCP clients.

Quick Start

• New Users: Start with the Setup Guide
• Multi-Client Setup: See Multi-Client Integration
• Docker Users: Check out Docker Deployment
• Troubleshooting: Visit General Troubleshooting

Documentation Structure

📦 Installation & Setup

• Setup Guide - Comprehensive installation instructions for all platforms

🔗 Integration & Connectivity

• Multi-Client Setup - Share memory across multiple applications
• Homebrew Integration - Use system-installed PyTorch via Homebrew
• IDE Compatibility - VS Code, Continue, and other IDE integrations
• Gemini Integration - Use MCP Memory Service with Google Gemini
• Groq Bridge · Groq Integration Summary · Groq Model Comparison - Groq LLM integration for quality scoring

🚀 Deployment

• Docker Deployment - Containerized deployment with various configurations
• Cloud Deployment - Cloud platform deployment guides
• Production Guide - Single-process production deployment
• Dual-Service Deployment - FastMCP + HTTP two-service architecture
• External Embeddings - Use vLLM, Ollama, TEI or OpenAI-compatible embedding APIs
• systemd Service - Linux systemd service unit setup

📚 User Guides

• MCP Protocol Enhancements - Resources, Prompts, and Progress Tracking (v4.1.0)
• Storage Backends - SQLite-vec / Cloudflare / Hybrid comparison and configuration
• Migration Guide - Migrate between storage backends and versions
• Scripts Reference - Available utility scripts

🎯 Natural Memory Triggers

• Installation Guide - Set up automatic memory triggers in Claude Code
• CLI Reference - Trigger CLI command reference
• Performance Optimization - Tune trigger sensitivity and latency

🏛️ Architecture & Design

• Graph Database Design - Memory graph schema and relationships
• Search Enhancement Spec - Hybrid search architecture
• Search Examples - Worked examples of search modes

🎯 Tutorials & Examples

• Data Analysis Examples - Advanced data analysis with memory service
• Advanced Techniques - Power user techniques and patterns
• Demo Session Walkthrough - Step-by-step usage examples

🔧 Maintenance & Administration

• Memory Maintenance - Database cleanup, optimization, and backup
• Health Checks - Monitoring and diagnostics
• Performance Tuning - Optimization techniques

📖 API Reference

• Memory Metadata API - Advanced metadata operations
• Tag Standardization - Tag schema and conventions

🛠️ Development & Technical

• Development Guide - Contributing and development setup
• Technical Implementation - Deep dive into technical details
  • Memory Migration
  • Tag Storage

🔍 Troubleshooting

• General Troubleshooting - Common issues and solutions
• Docker Issues - Docker-specific troubleshooting

Project Information

About MCP Memory Service

MCP Memory Service enables persistent, semantic memory for AI applications through the Model Context Protocol. It provides:

• Semantic Search: Vector-based memory retrieval using sentence transformers
• Multiple Storage Backends: SQLite-vec (local), Cloudflare (cloud/edge), and Hybrid (recommended for production)
• Multi-Client Support: Shared memory across multiple applications
• Cross-Platform: Support for macOS, Windows, and Linux
• Flexible Deployment: Local installation, Docker containers, or cloud deployment

Key Features

• ✅ Semantic Memory Storage: Store and retrieve memories using natural language
• ✅ Multi-Client Access: Share memories across Claude Desktop, VS Code, and other MCP clients
• ✅ Flexible Storage: Choose SQLite-vec (local/dev), Cloudflare (cloud/edge), or Hybrid (production)
• ✅ Cross-Platform: Native support for macOS (Intel & Apple Silicon), Windows, and Linux
• ✅ Docker Ready: Complete containerization support with multiple deployment options
• ✅ Hardware Optimized: Automatic detection and optimization for available hardware (CUDA, MPS, DirectML)
• ✅ Production Ready: HTTP/SSE API, authentication, monitoring, and scaling features

Recent Updates

• v0.2.2+: Enhanced multi-client support with automatic MCP application detection
• SQLite-vec Backend: Lightweight local backend with ~5 ms reads — default for development and single-user setups
• Homebrew Integration: Native support for Homebrew-installed PyTorch on macOS
• Docker Improvements: Fixed boot loops, added multiple deployment configurations
• HTTP/SSE API: Real-time multi-client communication with Server-Sent Events

Getting Help

Quick Links

• Installation Issues: Check the Setup Guide and platform-specific guides
• Configuration Problems: See Troubleshooting
• Multi-Client Setup: Follow the Multi-Client Guide
• Performance Issues: Review Performance Tuning

Support Resources

• GitHub Issues: Report bugs and request features
• Documentation: Comprehensive guides for all use cases
• Community: Share experiences and get help from other users

Contributing

We welcome contributions! See the Development Guide for information on:

• Setting up a development environment
• Running tests
• Submitting pull requests
• Code style and conventions

Version History

• Latest: Enhanced documentation organization, consolidated guides, improved navigation
• v0.2.2: Multi-client improvements, SQLite-vec backend, Homebrew integration
• v0.2.1: Docker deployment fixes, HTTP/SSE API enhancements
• v0.2.0: Multi-client support, cross-platform compatibility improvements

---

Navigation Tips

• 📁 Folders: Click on folder names to explore sections
• 🔗 Links: All internal links are relative and work offline
• 📱 Mobile: Documentation is mobile-friendly for on-the-go reference
• 🔍 Search: Use your browser's search (Ctrl/Cmd+F) to find specific topics

Happy memory-ing! 🧠✨