📌Overview

Purpose: MemoryMesh aims to create and manage structured knowledge graphs for AI models, particularly enhancing interactions in text-based RPGs.

Overview: MemoryMesh serves as a local knowledge graph server that enables users to effectively organize and manage information tailored for AI applications. Its flexible design facilitates a wide range of uses, from gaming to social simulations.

Key Features:

Dynamic Schema-Based Tools: Automatically generates tools for data management based on user-defined schemas, streamlining the data manipulation process.
Intuitive Schema Design: Allows users to create schemas that inform the AI on structuring and connecting data, facilitating accurate data creation and relationship definition.
Metadata for AI Guidance: Uses metadata to enhance the AI's understanding of data relationships, improving context and insights into interactions.
Relationship Handling: Supports the definition of relationships between nodes, promoting dynamic connections and interactions within the knowledge graph.
Informative Feedback: Provides error messages to the AI, aiding in recognizing and correcting mistakes, which enhances the learning process.
Event Support: Tracks operations within the graph, offering insights into how modifications occur and affecting data flow management.

MemoryMesh

MemoryMesh is a knowledge graph server designed for AI models, particularly focused on text-based RPGs and interactive storytelling. It enables AIs to maintain consistent and structured memory across conversations, facilitating richer interactions.

Important Changes

Since v0.2.7, the default location of schemas has changed to dist/data/schemas. If updating from a previous version, ensure to move your schema files to this new location.

Quick Links

Overview

MemoryMesh is a versatile local knowledge graph server designed to build and manage structured information for AI models. While it excels in text-based RPGs, it is also useful for various applications such as organizational planning and social network simulations.

Key Features

Dynamic Schema-Based Tools: Automatically generates tools for adding, updating, and deleting data based on defined schemas.
Intuitive Schema Design: Schemas guide AI in generating and connecting nodes with required fields and relationships.
Metadata Usage: Provides context that helps the AI understand relationships within data.
Relationship Handling: Encourages the AI to create connections between related data points.
Informative Feedback: Supplies error feedback to improve AI interactions.
Event Support: Tracks operations for insight into knowledge graph modifications.

Nodes

Nodes represent entities or concepts, characterized by:

name: Unique identifier.
nodeType: Type of the node (e.g., npc, artifact, location).
metadata: Descriptive details.
weight: Optional numerical value between 0 and 1.

Example Node

{
  "name": "Aragorn",
  "nodeType": "player_character",
  "metadata": [
    "Race: Human",
    "Class: Ranger",
    "Skills: Tracking, Swordsmanship",
    "Affiliation: Fellowship of the Ring"
  ]
}

Edges

Edges represent relationships between nodes, defined by:

from: Source node's name.
to: Target node's name.
edgeType: Type of relationship.

{
  "from": "Aragorn",
  "to": "Andúril",
  "edgeType": "owns"
}

Schemas

Schemas define the structure of your data and drive tool generation.

Schema Structure

File name: [name].schema.json.
Properties:
- name: Identifier for the schema; must start with add_.
- description: Context for the AI.
- properties: Defines property types, requirements, and relationships.
- additionalProperties: Allows extra attributes.

Example Schema

{
  "name": "add_npc",
  "description": "Schema for adding an NPC to the memory",
  "properties": {
    "name": {
      "type": "string",
      "description": "A unique identifier for the NPC",
      "required": true
    },
    "race": {
      "type": "string",
      "description": "The species or race of the NPC",
      "required": true,
      "enum": [
        "Human",
        "Elf",
        "Dwarf",
        "Orc",
        "Goblin"
      ]
    },
    "currentLocation": {
      "type": "string",
      "description": "The current location of the NPC",
      "required": true,
      "relationship": {
        "edgeType": "located_in",
        "description": "The current location of the NPC"
      }
    }
  },
  "additionalProperties": true
}

MemoryMesh automatically creates tools based on the schema, such as add_npc, update_npc, and delete_npc.

Dynamic Tools

MemoryMesh auto-generates tools directly from your schema definitions, allowing convenient interaction with the knowledge graph:

add_<entity>: Create new entity instances.
update_<entity>: Modify existing entities.
delete_<entity>: Remove entities.

Memory File

Data is stored in a JSON file located at dist/data/memory.json.

Installation

Installing via Smithery

To install MemoryMesh for Claude Desktop using Smithery, run:

npx -y @smithery/cli install memorymesh --client claude

Prerequisites

Node.js: Version 18 or higher.
npm: Installed with Node.js.
Claude for Desktop: Latest version needed.

Installation Steps

Clone the Repository:

git clone https://github.com/CheMiguel23/memorymesh.git
cd memorymesh

Install Dependencies:
```
npm install
```
Build the Project:
```
npm run build
```
Depending on your setup, configure Claude Desktop by editing the appropriate configuration file for your system.
Restart Claude Desktop for changes to take effect.

Verify Installation

Start Claude Desktop and open a new chat.
Look for the MCP plugin icon.
Ensure "memorymesh" is listed among connected servers and tools are exposed.

Advanced Configuration

MemoryMesh allows customization through variables in /config/config.ts, enabling overrides of default settings like MEMORY_FILE and SCHEMAS_DIR.

Limitations

Node Deletion: The AI may hesitate to delete nodes; encourage it through prompts.

Contribution

Contributions, feedback, and ideas are welcome to further explore integrating structured data with AI.