MCP Knowledge Graph is a local memory store that enables AI models to persistently retain information across conversations using a knowledge graph structure of entities, relations, and observations. Key features of MCP Knowledge Graph: - Master database for primary memory storage with optional named databases (work, personal, health, etc.) for topic organization. - Project-local storage through `.aim` directories with automatic project detection. - Global storage option with configurable memory paths for cross-project memory access. - Safety system with `_aim` file markers to prevent accidental overwrites of unrelated JSONL files. - Multi-context support with separate memory files for different conversation contexts. - Compatible with Claude Code, Claude Desktop, and any MCP-compatible AI platform.

MCP Knowledge Graph

Persistent memory for AI models through a local knowledge graph.

Store and retrieve information across conversations using entities, relations, and observations. Works with Claude Code/Desktop and any MCP-compatible AI platform.

Why ".aim" and "aim_" prefixes?

AIM stands for AI Memory - the core concept of this system. The three AIM elements provide clear organization and safety:

This consistent AIM naming makes it obvious which directories, tools, and files belong to the AI memory system.

CRITICAL: Understanding .aim dir vs _aim file marker

Two different things with similar names:

For project-local storage:

For global storage (--memory-path):

Storage Logic

File Location Priority:

1. Project with .aim - Uses .aim/memory.jsonl (project-local) 2. No project/no .aim - Uses configured global directory 3. Contexts - Adds suffix: memory-work.jsonl, memory-personal.jsonl

Safety System:

Master Database Concept

The master database is your primary memory store - used by default when no specific database is requested. It's always named default in listings and stored as memory.jsonl.

Key Features

Quick Start

Global Memory (Recommended)

Add to your claude_desktop_config.json or .claude.json. Two common approaches:

Option 1: Default .aim directory (simple)

{
  "mcpServers": {
    "Aim-Memory-Bank": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-knowledge-graph",
        "--memory-path",
        "/Users/yourusername/.aim"
      ]
    }
  }
}

Option 2: Dropbox/cloud sync (portable)

For accessing memories across multiple machines, use a synced folder. This is how the author of this MCP server keeps his own memories:

{
  "mcpServers": {
    "Aim-Memory-Bank": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-knowledge-graph",
        "--memory-path",
        "/Users/yourusername/Dropbox/ai-memory"
      ]
    }
  }
}

This creates memory files in your specified directory:

Project-Local Memory

In any project, create a .aim directory:

mkdir .aim

Now memory tools automatically use .aim/memory.jsonl (project-local master database) instead of global storage when run from this project.

How AI Uses Databases

Once configured, AI models use the master database by default or can specify named databases with a context parameter. New databases are created automatically - no setup required:

```json // Master Database (default - no context needed) aim_memory_store({ entities: [{ name: "John_Doe", entityType: "person", observations: ["Met at conference"] }] })

// Work database aim_memory_store({ context: "work", entities: [{ name: "Q4_Project", entityType: "project", observations: ["Due December 20