by Puliczek
🔥🖥️ MCP Memory is a MCP Server that gives MCP Clients (Cursor, Claude, Windsurf and more) the ability to remember information about users (preferences, behaviors) across conversations.
# Add to your Claude Code skills
git clone https://github.com/Puliczek/mcp-memoryMCP Memory is a MCP Server that gives MCP Clients (Cursor, Claude, Windsurf and more) the ability to remember information about users (preferences, behaviors) across conversations. It uses vector search technology to find relevant memories based on meaning, not just keywords. It's built with Cloudflare Workers, D1, Vectorize (RAG), Durable Objects, Workers AI and Agents.
In Create Vectorize section choose:
Click button "Create and Deploy"
In Cloudflare dashboard, go to "Workers & Pages" and click on Visit

npm create cloudflare@latest --git https://github.com/puliczek/mcp-memory
npm install
npx wrangler vectorize create mcp-memory-vectorize --dimensions 1024 --metric cosine
npm run dev
npm run deploy

Storing Memories:
@cf/baai/bge-m3 model to generate embeddingsRetrieving Memories:
@cf/baai/bge-m3 modelThis architecture enables: