MCP Catalogs
Home

mymir vs memory

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

mymir
by FrkAk
memory
by modelcontextprotocol
Stars★ 68★ 85,748
30d uses
Score4677
Official
Categories
Developer ToolsProductivityKnowledge Graph
Knowledge GraphAI / LLM ToolsProductivity
LanguageTypeScriptTypeScript
Last committhis monththis month

mymir · Summary

Mymir is an AI-native project management tool that provides MCP tools for task management and context tracking in agentic engineering workflows.

memory · Summary

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

mymir · Use cases

  • Managing complex software development projects with persistent agent memory
  • Automating task decomposition and dependency planning in agentic workflows
  • Providing context-aware task execution across multiple AI coding assistants

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

mymir · Install

Installation Steps

  1. Install prerequisites: Bun v1.0+ and Docker
  2. Clone the repository: git clone git@github.com:FrkAk/mymir.git
  3. Install dependencies: bun install
  4. Copy environment file: cp .env.local.example .env.local
  5. Configure database and auth credentials in .env.local
  6. Setup database: bun run db:setup
  7. Build and start: bun run build && bun run start

For Claude Code integration:

{
  "mcpServers": {
    "mymir": {
      "command": "npx",
      "args": ["@frkak/mymir", "--stdio"]
    }
  }
}

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.