Memory
Enables MCP Clients to retain and retrieve user information across conversations using vector search for contextual recall.
About
Memory is a powerful MCP Server designed to imbue MCP Clients (like Cursor, Claude, and Windsurf) with the capability to remember user-specific information, such as preferences and behaviors, across various conversations. Leveraging advanced vector search technology, it intelligently retrieves relevant memories based on semantic meaning rather than mere keyword matches. Built entirely on Cloudflare's robust serverless stack, including Workers, D1, Vectorize, Durable Objects, and Workers AI, it provides a scalable, efficient, and cost-effective solution for persistent conversational context, ensuring that interactions are always personalized and informed.
Key Features
- Semantic search with vector embeddings
- Leverages Cloudflare's serverless ecosystem (Workers, D1, Vectorize, Workers AI, Durable Objects)
- Built-in rate limiting
- Cross-conversation memory for MCP Clients
- Isolated namespaces for user data security
- 0 GitHub stars
Use Cases
- Storing and retrieving user preferences and behaviors for personalized conversational experiences
- Building knowledge bases with advanced semantic search capabilities
- Tracking and organizing project notes, decisions, and updates
