Memkin vs Recallnest

In-depth architectural comparison of the Memkin and Recallnest MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

Which MCP Server Should You Choose?

Choose Memkin when:

• You need dedicated capabilities in the Knowledge & Memory domain.
• You prefer local stdio subprocess transport architecture.
• Your security boundary fits: API Key required (BYOK (Pay Provider Direct)).
• Primary tools included: Feishu/Lark data collection, AI coding session ingestion, Local entity knowledge graph.

Explore Memkin Details

Choose Recallnest when:

• You need dedicated capabilities in the Knowledge & Memory domain.
• You prefer local stdio subprocess transport architecture.
• Your security boundary fits: API Key required (Free / Open Source).
• You have access to required keys: JINA_API_KEY.
• Primary tools included: Hybrid retrieval: vector, BM25, multi-vector levels, and knowledge graph PPR, Session checkpoint and resume with repo-state guarding, Multi-scope isolation with related scope sidecar search.

Feature & Specification Comparison

Specification	Memkin AndreLYL Knowledge & Memory	Recallnest AliceLJY Knowledge & Memory
Summary	Local-first personal memory for AI agents. Ingests Feishu/Lark chats and Claude Code / Codex sessions, distills them into a private entity knowledge graph (people, projects, decisions, tasks), and serves it to any agent over MCP — read and write. npx memkin	Persistent memory MCP server for AI coding agents (Claude Code, Codex, Gemini CLI). Hybrid retrieval (vector + BM25), cross-encoder reranking, knowledge graph with PPR traversal, session checkpoint/resume, and multi-scope isolation. Local-first with LanceDB + SQLite, zero external dependencies.
Category & Scope

Tools & Capabilities Breakdown

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

{
  "mcpServers": {
    "andrelyl-memkin": {
      "command": "npx",
      "args": [
        "-y",
        "memkin"
      ]
    }
  }
}

{
  "mcpServers": {
    "aliceljy-recallnest": {
      "command": "npx",
      "args": [
        "-y",
        "recallnest"
      ],
      "env": {
        "JINA_API_KEY": "YOUR_JINA_API_KEY_HERE"
      }
    }
  }
}

Related MCP Server Comparisons