supermemoryai/supermemory-mcp

Your memories are in ChatGPT... But nowhere else. Universal Memory MCP makes your memories available to every single LLM. No logins or paywall. One command to set it up.

What it solves

It eliminates the fragmented memory across different AI assistants. Instead of having your personal information and memories stored in a single LLM (like ChatGPT), this project provides a universal memory layer that makes your data available to any LLM or MCP client you choose to use.

How it works

It is built as a Model Context Protocol (MCP) server that connects to the Supermemory API. This allows any MCP-compatible client to access a centralized repository of your memories, enabling a consistent context across different AI tools without requiring a separate login for each.

Who it’s for

Users who use multiple different LLMs and want a single, portable memory system that works across all of them.

Highlights

  • Universal Access: Makes memories available to every LLM via the Model Context Protocol.
  • API-Driven: Built on the Supermemory API for speed and scalability.
  • ** SBOM**: Completely free to use with no login required for basic setup.
  • Self-hosting: Supports self-hosting via an API key provided by the Supermemory console.

Related

  • Project
    undreamai/LLMUnity

    A Unity engine integration for Large Language Models that enables the creation of intelligent, local AI characters with RAG support.

  • Project
    Eynzof/Hermes-CN-Desktop

    A native Windows and macOS desktop client for Hermes Agent, providing a streamlined interface and bundled runtime for managing AI agents.

  • Project
    101dotxyz/GPTeam

    GPTeam is a multi-agent simulation where AI agents collaborate, communicate, and move through a simulated world to achieve common goals.

  • Project
    nikilster/clawflows

    A powerful workflow system for OpenClaw that provides over 100 prebuilt, deterministic automation routines to turn an AI agent into a proactive personal assistant.