github doobidoo/mcp-memory-service v6.2.0
v6.2.0: Native Cloudflare Backend Integration

latest releases: v10.31.1, v10.31.0, v10.30.0...
7 months ago

🌍 Native Cloudflare Backend Integration (v6.2.0)

This major release introduces native Cloudflare integration as a third storage backend option alongside SQLite-vec and ChromaDB, providing global distribution, automatic scaling, and enterprise-grade infrastructure.

🚀 Key Features

Native Cloudflare Platform Integration

  • 🌐 Vectorize: 768-dimensional vector storage with cosine similarity for semantic search
  • 🗄️ D1 Database: SQLite-compatible database for metadata storage
  • 🤖 Workers AI: Embedding generation using @cf/baai/bge-base-en-v1.5 model
  • 📦 R2 Storage (optional): Object storage for large content exceeding 1MB threshold

Performance & Reliability

  • 🌍 Global Distribution: <100ms latency from most worldwide locations
  • 📈 Automatic Scaling: Serverless infrastructure with pay-per-use pricing
  • 🏢 Enterprise Features: Automatic retry logic, connection pooling, batch operations
  • ⚡ LRU Caching: 1000-entry cache for embedding deduplication

Memory Awareness Compatibility

  • 🧠 Full Phase 1 & 2 Support: Works seamlessly with existing Memory Awareness hooks
  • 🔗 Cross-Session Intelligence: Session tracking and conversation threading supported
  • 🎯 Dynamic Context Updates: Real-time memory loading during conversations
  • ⚡ Global Performance: Enhances Memory Awareness with sub-100ms response times

📁 Implementation Files

  • src/mcp_memory_service/storage/cloudflare.py - Complete CloudflareStorage implementation (740 lines)
  • scripts/migrate_to_cloudflare.py - Migration tool for existing SQLite-vec and ChromaDB users
  • scripts/test_cloudflare_backend.py - Comprehensive test suite with automated validation
  • scripts/setup_cloudflare_resources.py - Automated Cloudflare resource provisioning
  • docs/cloudflare-setup.md - Complete setup, configuration, and troubleshooting guide
  • tests/unit/test_cloudflare_storage.py - 15 unit tests for CloudflareStorage class

🔧 Quick Setup

# Install Cloudflare dependencies
pip install -r requirements-cloudflare.txt

# Configure environment variables
export MCP_MEMORY_STORAGE_BACKEND=cloudflare
export CLOUDFLARE_API_TOKEN="your-api-token"
export CLOUDFLARE_ACCOUNT_ID="your-account-id"
export CLOUDFLARE_VECTORIZE_INDEX="mcp-memory-index"
export CLOUDFLARE_D1_DATABASE_ID="your-database-id"

# Start the service
python -m src.mcp_memory_service.server

📖 Complete Setup Guide

🔄 Migration Path

Seamless migration from existing backends:

# From SQLite-vec
python scripts/migrate_to_cloudflare.py --source sqlite

# From ChromaDB
python scripts/migrate_to_cloudflare.py --source chroma

🎯 Benefits

  • 🌍 Global Reach: Deploy memory services worldwide with Cloudflare's edge network
  • 🔧 Zero Maintenance: Serverless architecture eliminates server management
  • 💰 Cost Effective: Pay-per-use pricing with generous free tier
  • 🏢 Enterprise Ready: Built-in reliability, retry logic, and error handling
  • 🧠 Memory Aware: Full compatibility with Phase 1 and Phase 2 Memory Awareness features

Compatibility

  • Fully backward compatible with existing SQLite-vec and ChromaDB backends
  • No breaking changes to existing APIs or configurations
  • Complete Memory Awareness integration with all existing hooks and functionality
  • Cross-platform support on Windows, macOS, and Linux

This release provides users with a third powerful storage option while maintaining full compatibility with existing workflows and the advanced Memory Awareness system. The Cloudflare backend represents a significant step toward globally distributed AI memory infrastructure.

🤖 Generated with Claude Code

Co-Authored-By: Claude noreply@anthropic.com

Don't miss a new mcp-memory-service release

NewReleases is sending notifications on new releases.