MCP Memory Domain Knowledge

🚀 Knowledge Graph Memory Server

A basic implementation that uses a local knowledge graph to achieve persistent memory, enabling Claude to remember user information across different chats.

🚀 Quick Start

The Knowledge Graph Memory Server provides a way to implement persistent memory using a local knowledge graph, allowing Claude to retain user information from various chats.

✨ Features

Core Concepts

Entities

Entities are the primary nodes in the knowledge graph. Each entity has:

• A name (identifier)
• An entity type (e.g., "person", "job", "school", etc.)
• Specific facts about the entity, stored as observations

Relationships

Relationships describe the connections between different entities and have:

• A subject
• A predicate (a verb or adjective describing the relationship)
• An object
• A time range (optional)

Observations

Observations are factual information about an entity, including:

• A name (matching the entity name)
• Descriptive facts
• A time of occurrence (optional)

Core Operations

Entity Management

1. Create a new entity
2. Query all entities
3. Query a specific entity by name
4. Update the attributes of an existing entity
5. Delete an entity

Relationship Management

1. Create a new relationship
2. Query all relationships
3. Query relationships by predicate and object
4. Update the attributes of an existing relationship
5. Delete a relationship

Observation Management

1. Create a new observation
2. Query all observations
3. Query relevant observations by entity name
4. Update an existing observation
5. Delete an observation

📚 Documentation

System Prompt

It is recommended to use the following prompt to guide the model on how to use memory:

Follow these steps for each interaction:

1. User Identification:
   - Assume you are interacting with the default_user by default.
   - If the default_user has not been identified, actively attempt to identify them.

2. Memory Retrieval:
   - Always start the chat with "Start remembering..." and retrieve all relevant information from your knowledge graph.
   - Always refer to your knowledge graph as your "memory".
   - When searching, you can use multiple keywords to find relevant information.
   - Example searches:
     * Single concept: "programming"
     * Related concepts: "programming python"
     * Specific domain and role: "job engineer"

3. Memory Creation:
   - When communicating with the user, pay attention to any new information in the following categories:
     a) Basic identity (age, gender, location, position, education level, etc.)
     b) Behaviors (interests, habits, etc.)
     c) Preferences (communication style, preferred language, etc.)
     d) Goals (targets, objectives, aspirations, etc.)
     e) Relationships (personal and professional relationships, up to 3 degrees of separation)

4. Memory Update:
   - If any new information is obtained during the interaction, update the memory as follows:
     a) Create entities for recurring organizations, people, and important events.
     b) Connect them to current entities using relationships.
     c) Store facts as observations.
     d) Name entities and observations using clear and searchable terms to facilitate future retrieval.

System Setup

Docker Build

docker build -t mcp/memory -f src/memory/Dockerfile .

📄 License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please refer to the LICENSE file in the project repository.