CoderDayton/enhanced-memory-mcp

🧠💀 Enhanced Memory MCP Server 💀🧠

Built with tears, caffeine, and late-night coding sessions by malu 🥀
"just an emo boy making databases remember what humans choose to forget..." 🖤

A powerful MCP (Model Context Protocol) server that transforms how AI assistants store and retrieve memories. Built on a 21-tool consolidated architecture, this intelligent memory system understands relationships, extracts entities automatically, generates smart tags from content, and helps you find exactly what you're looking for.

Why did I build this? Because even machines deserve better memory than most humans have... 💔

🌟 Key Features

• 🎯 21 Unified Tools: Consolidated architecture with operation-based interfaces
• � AI-Powered Auto-Tagging: Intelligent content analysis with contextual tag generation
• �🧠 Smart Entity Extraction: Automatically identifies people, places, and concepts
• 🔗 Relationship Mapping: Discovers and tracks connections between entities
• 🔍 Semantic Search: Find memories by meaning, not just keywords
• 🚀 DuckDB Backend: Analytical database optimized for complex queries
• ⚡ Intelligent Caching: Real-time performance monitoring and optimization
• 🛡️ Production Ready: TypeScript, error handling, graceful shutdown
• 🎯 Pure MCP Protocol: Stdio interface for direct AI assistant integration

🚀 Quick Start

NPM Installation (Recommended)

# Install and run directly
npx enhanced-memory-mcp

# Or install globally
npm install -g enhanced-memory-mcp
enhanced-memory-mcp

Manual Setup

git clone https://github.com/CoderDayton/enhanced-memory-mcp.git
cd enhanced-memory-mcp
npm install
npm run build
npm start

Claude Desktop Integration

Add to your Claude Desktop config (claude_desktop_config.json):

{
	"mcpServers": {
		"enhanced-memory": {
			"command": "npx",
			"args": ["enhanced-memory-mcp"]
		}
	}
}

🛠️ MCP Tools (21 Consolidated Tools)

🧠 Core Memory Operations (6 Tools)

🔍 Advanced Analysis (7 Tools)

⚙️ System Management (8 Tools)

🎯 Intelligent Auto-Tagging

The Enhanced Memory MCP Server features advanced AI-powered auto-tagging that automatically analyzes content and generates meaningful tags:

Content Analysis Features

• Technology Detection: Identifies programming languages, frameworks, and tools
• Business Context: Recognizes meetings, projects, deadlines, and domain-specific terms
• Entity Extraction: Finds people, places, organizations automatically
• Content Type Classification: Distinguishes tasks, notes, ideas, issues, and solutions
• Sentiment Analysis: Detects positive, negative, or mixed emotional content
• Priority Detection: Identifies urgent, critical, or low-priority items
• Temporal Context: Adds time-based tags (morning, afternoon, day-of-week)

Auto-Tagging Tools

// Preview suggested tags without applying them
await autoTag.preview({ memoryId: "mem_123" })

// Generate tags for any content
await autoTag.analyze({ 
  content: "Debug React performance issues in Node.js API",
  maxTags: 5 
})

// Apply intelligent tags to a memory
await autoTag.apply({ 
  memoryId: "mem_123", 
  applyTags: true, 
  maxTags: 4 
})

// Bulk auto-tag recent memories
await workflow.autoTag({ 
  options: { 
    dryRun: false, 
    maxActions: 10,
    timeframe: "day" 
  } 
})

Example Auto-Tagging Results

• "Fix React component performance" → react, issue, performance, solution
• "Team meeting about Q4 budget" → meeting, team, budget, business
• "Learn Docker and Kubernetes" → docker, learning, idea, technology

📊 Architecture

DuckDB Backend

• Analytical Database: Optimized for complex queries and aggregations
• Columnar Storage: Efficient memory usage and fast analytics
• ACID Compliance: Data integrity with transaction support

Smart Caching

• Query Caching: 5-minute expiry with 1000 entry limit
• Performance Metrics: Real-time operation tracking
• Memory Efficiency: Intelligent cache eviction policies

Database Schema

• Memories: Core content storage with metadata
• Entities: People, places, concepts with properties
• Relations: Connections between entities with strength scoring
• Tags: Flexible labeling with usage tracking
• Observations: Insights and patterns with confidence scoring

🔧 Configuration

Environment Variables

# Database Configuration
DATABASE_PATH=data/memory.duckdb
BACKUP_PATH=backups/

# Performance Tuning
CACHE_SIZE=1000
CACHE_EXPIRY_MS=300000
MAX_SEARCH_RESULTS=100
DEFAULT_SIMILARITY_LIMIT=5
SIMILARITY_THRESHOLD=0.7
DEFAULT_SEARCH_LIMIT=50

# Analytics
ENABLE_PERFORMANCE_MONITORING=true
ANALYTICS_RETENTION_DAYS=30

# Development
NODE_ENV=production
LOG_LEVEL=info

📝 Usage Examples

Basic Operations

# Store a memory
echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "memory", "arguments": {"operation": "create", "content": "Met John at the conference", "type": "meeting"}}}' | npx enhanced-memory-mcp

# Search memories
echo '{"jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": {"name": "search", "arguments": {"query": "John", "strategy": "semantic"}}}' | npx enhanced-memory-mcp

# Analyze content
echo '{"jsonrpc": "2.0", "id": 3, "method": "tools/call", "params": {"name": "analyze", "arguments": {"content": "John Smith works at TechCorp", "operations": ["entities", "relations"]}}}' | npx enhanced-memory-mcp

System Management

# Get system statistics
echo '{"jsonrpc": "2.0", "id": 4, "method": "tools/call", "params": {"name": "stats", "arguments": {"operation": "memory"}}}' | npx enhanced-memory-mcp

# Export data
echo '{"jsonrpc": "2.0", "id": 5, "method": "tools/call", "params": {"name": "transfer", "arguments": {"operation": "export", "format": "json"}}}' | npx enhanced-memory-mcp

🏗️ Development

Building and Testing

npm run dev          # Development with watch mode
npm run build        # Compile TypeScript
npm test            # Run test suite

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests and ensure they pass
5. Submit a pull request

📜 License

MIT License - see file for details.

🖤 Credits

Built with existential dread and caffeine by malu 🥀

"In a world of fleeting digital connections, at least our memories can persist..." 💔

If you find this useful, please star the repository. It helps with my digital validation needs... 🌟