Memory
Provides AI clients the ability to remember information about users across conversations using vector search technology.
About
MCP Memory functions as a robust server designed to empower MCP Clients like Cursor, Claude, and Windsurf with persistent memory capabilities. It allows these AI clients to recall user preferences and behaviors across different interactions by leveraging advanced vector search technology to find relevant information based on meaning rather than just keywords. Built entirely on Cloudflare's serverless infrastructure, including Workers, D1, Vectorize, Durable Objects, and Workers AI, it offers a scalable, secure, and cost-effective solution for creating stateful AI applications.
Key Features
- 0 GitHub stars
- Offers scalable deployment with a generous free tier for normal usage.
- Enables cross-conversation memory for AI clients.
- Utilizes semantic search via vector embeddings (Cloudflare Vectorize & Workers AI).
- Built on a serverless architecture using Cloudflare Workers, D1, and Durable Objects.
- Includes a dedicated API for storing and semantically searching email content.
Use Cases
- Tracking and recalling user behaviors and interaction patterns within applications.
- Storing and retrieving project-specific notes, decisions, and updates.
- Building a dynamic knowledge base for technical documentation and procedures.
Sponsored