MCP Catalogs
Home

beever-atlas vs memory

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

beever-atlas
by Beever-AI
memory
by modelcontextprotocol
Stars★ 328★ 85,748
30d uses
Score5077
Official
Categories
CommunicationKnowledge GraphAI / LLM Tools
Knowledge GraphAI / LLM ToolsProductivity
LanguagePythonTypeScript
Last committhis monththis month

beever-atlas · Summary

Beever Atlas is an MCP server that transforms team chats into a self-maintaining wiki with integrated search and QA capabilities.

memory · Summary

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

beever-atlas · Use cases

  • Automatically team documentation from chat conversations
  • AI-powered search across team communications with source citations
  • Integrate team knowledge base into Claude Code and Cursor via MCP

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

beever-atlas · Install

Installation

  1. Clone the repository:
git clone https://github.com/beever-ai/beever-atlas.git
cd beever-atlas
  1. Try the demo (optional):
make demo
  1. Get API keys:
  • GOOGLE_API_KEY for Gemini extraction and answers
  • JINA_API_KEY for embeddings (Jina v4)
  1. Install with one line:
./atlas

This will walk you through setup including embedding model, LLM provider, graph backend, and MCP server configuration.

Claude Desktop Integration

Add to Claude Desktop config:

{
  "mcpServers": {
    "beever-atlas": {
      "command": "npx",
      "args": ["beever-atlas-mcp"]
    }
  }
}

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