サーバー
Memxus
@gpitrella
Multi-platform AI memory. One save, recall everywhere—Claude, ChatGPT, Cursor, VS Code, and more. Persistent memory across AI conversations and clients.
概要
What is Memxus?
Memxus gives AI assistants persistent memory across conversations and clients. It is a hosted remote MCP server that allows users to save preferences, project context, and facts once and recall them from any MCP-compatible app via OAuth or API key.
How to use Memxus?
Sign in at https://dashboard.memxus.com/login, then connect via OAuth at https://www.memxus.com/install or add a Bearer token (aimem_*) in your MCP client configuration. The endpoint is https://mcp.memxus.com/mcp using Streamable HTTP transport.
Key features of Memxus
- Cross-client memory (Claude, ChatGPT, Cursor, VS Code)
- Project-context scoped collections (e.g.,
project:my-app) - Semantic recall via
recallandget_contexttools - Eight tools: remember, recall, get_context, list_memories, get_memory, list_collections, forget
- No local install, fully hosted
Use cases of Memxus
- Continue conversations where you left off when switching between AI clients
- Save project-level context (e.g., API base URLs) and recall automatically