Memento

Created By

gannonh8 months ago

Overview

What is Memento?

Memento is a scalable knowledge graph memory system designed for large language models (LLMs) that provides persistent ontological memory with advanced relation management and semantic search capabilities.

How to use Memento?

To use Memento, set up a Neo4j database and configure it with the required environment variables. You can then interact with the system through the Model Context Protocol (MCP) to manage entities and relations.

Key features of Memento?

Scalable knowledge graph with semantic search capabilities.
Temporal awareness for tracking changes over time.
Advanced relation management with confidence decay.
Support for multiple embedding models for semantic search.

Use cases of Memento?

Enhancing LLMs with persistent memory for improved context retention.
Semantic search for retrieving related entities based on meaning.
Temporal analysis of knowledge evolution over time.

FAQ from Memento?

What is the storage backend for Memento?

Memento uses Neo4j as its storage backend for both graph and vector search capabilities.

How do I set up Memento?

You can set up Memento by installing Neo4j and configuring the necessary environment variables as outlined in the documentation.

Can Memento be integrated with other LLMs?

Yes, Memento is designed to work with any LLM client that supports the model context protocol.

Server Config

{
  "mcpServers": {
    "memento": {
      "command": "npx",
      "args": [
        "-y",
        "@gannonh/memento-mcp"
      ],
      "env": {
        "MEMORY_STORAGE_TYPE": "neo4j",
        "NEO4J_URI": "bolt://127.0.0.1:7687",
        "NEO4J_USERNAME": "neo4j",
        "NEO4J_PASSWORD": "memento_password",
        "NEO4J_DATABASE": "neo4j",
        "NEO4J_VECTOR_INDEX": "entity_embeddings",
        "NEO4J_VECTOR_DIMENSIONS": "1536",
        "NEO4J_SIMILARITY_FUNCTION": "cosine",
        "OPENAI_API_KEY": "your-openai-api-key",
        "OPENAI_EMBEDDING_MODEL": "text-embedding-3-small"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

WindsurfThe new purpose-built IDE to harness magic

Serper MCP ServerA Serper MCP Server

BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs

ChatWiseThe second fastest AI chatbot™

EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

DeepChatYour AI Partner on Desktop