memory vs orionbelt-analytics

Side-by-side comparison to help you pick between these two MCP servers.

	memory by modelcontextprotocol	orionbelt-analytics by ralfbecher
Stars	★ 85,748	★ 29
30d uses	—	—
Score	77	45
Official	✓	—
Categories	Knowledge GraphAI / LLM ToolsProductivity	DatabaseDeveloper ToolsKnowledge Graph
Language	TypeScript	Python
Last commit	this month	this month

memory · Summary

An MCP server implementing persistent memory using a local knowledge graph for AI models to remember user information across chats.

orionbelt-analytics · Summary

Ontology-based MCP server analyzing database schemas and generating RDF/OWL ontologies with SQL mappings for Text-to-SQL.

memory · Use cases

Personalizing AI assistant interactions by remembering user preferences, history, and relationships
Building context-aware chat applications that maintain conversation history
Creating knowledge bases that persist across AI model sessions

orionbelt-analytics · Use cases

Enterprise data analysis with natural language queries across multiple database systems
Schema analysis and ontology generation for knowledge graph applications
Automated SQL validation with fan-trap prevention to ensure query correctness

memory · Install

Installation

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

VS Code

Use one-click installation buttons or manually configure in .vscode/mcp.json:

{
  "servers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

Docker

{
  "mcpServers": {
    "memory": {
      "command": "docker",
      "args": ["run", "-i", "-v", "claude-memory:/app/dist", "--rm", "mcp/memory"]
    }
  }
}

orionbelt-analytics · Install

Installation

git clone https://github.com/ralfbecher/orionbelt-analytics
cd orionbelt-analytics
uv sync

Configure environment variables:

cp .env.template .env

Run the server:

uv run server.py

For Claude Desktop, add to your claude_desktop_config.json:

{
  "mcpServers": {
    "OrionBelt-Analytics": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:9000/mcp",
        "--transport",
        "http-only"
      ]
    }
  }
}

Comparison generated from public README + GitHub signals. Last updated automatically.