What is the key difference between Memkin and Cognee?

Memkin belongs to the Knowledge & Memory category with local stdio execution, while Cognee belongs to the Knowledge & Memory category with local stdio execution.

How do I install Memkin or Cognee in Claude Desktop or Cursor?

Copy the mcpServers JSON configuration snippet provided on this page into your claude_desktop_config.json or ~/.cursor/mcp.json file and restart your AI client.

Are Memkin and Cognee free or paid?

Memkin operates under a BYOK (Pay Provider Direct) model (API Key required). Cognee operates under a BYOK (Pay Provider Direct) model (API Key required).

Which MCP server has more tools and community activity?

Memkin lists 6 tools with 3 views and 5 GitHub stars. Cognee lists 6 tools with 2 views and 29,870 GitHub stars.

Can I use both Memkin and Cognee together in the same MCP host?

Yes! MCP hosts like Claude Desktop, Cursor, Windsurf, Cline, and VS Code support configuring multiple servers under the mcpServers object simultaneously.

How do I install Memkin or Cognee in Claude Desktop, Cursor, or Windsurf?

Both servers follow the standard Model Context Protocol configuration format. Simply copy the JSON block from the configuration section above and paste it into your AI client's mcpServers configuration object (for instance in claude_desktop_config.json or ~/.cursor/mcp.json ), then completely restart or refresh the application.

Are Memkin and Cognee free to use, or do they require API keys?

Memkin is listed under a BYOK (Pay Provider Direct) model with API Key required . Cognee operates under a BYOK (Pay Provider Direct) model with API Key required . If environment variables are required (such as API keys), be sure to define them under the env key in your MCP client's configuration file.

Can I run both Memkin and Cognee at the same time in my AI client?

Yes! MCP clients support multi-server orchestration. You can include both andrelyl-memkin and topoteretes-cognee as distinct keys inside the single mcpServers object in your configuration file. Your AI assistant will automatically select and call the appropriate tool from either server during chat sessions.

Which MCP server has higher directory engagement and quality ratings?

On AllMCPs, Memkin has a Quality Score of 48 /100 ( Fair ) with 3 views, 0 installs, and 5 GitHub stars. Cognee holds a Quality Score of 48 /100 ( Fair ) with 2 views, 0 installs, and 29,870 GitHub stars.

Side-by-Side Model Context Protocol Comparison

Memkin vs Cognee

In-depth architectural comparison of the Memkin and Cognee 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.

At a Glance & Executive Verdict

Memkin

Knowledge & Memory · Local stdio

Quality: 48/100 (Fair) | Auth: API Key required

Cognee

Knowledge & Memory · Local stdio

Quality: 48/100 (Fair) | Auth: API Key required

Verdict Summary: Choose Memkin if you need specialized Knowledge & Memory tools running via a local process. Choose Cognee if your workspace requires Knowledge & Memory integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.

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)).
You have access to required keys: OPENAI_API_KEY, OLLAMA_API_KEY.
Primary tools included: Incremental and historical data collection from 7 Feishu sources, AI session data ingestion from Claude Code, Codex, Hermes/OpenClaw, Private local knowledge graph with entity linking and identity merging.

Explore Memkin Details

Choose Cognee 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)).
You have access to required keys: LLM_API_KEY.
Primary tools included: Supports ingestion from 30+ data sources, Combines vector embeddings with graph-based reasoning, Self-hosted knowledge graph with ontology generation.

Explore Cognee Details

Feature & Specification Comparison

Specification	Memkin AndreLYL Knowledge & Memory	Cognee topoteretes 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	Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources
Category & Scope	Knowledge & Memory	Knowledge & Memory
Quality signal	48/100 (Fair)	48/100 (Fair)
Transport Protocol	Local Subprocess (stdio)	Local Subprocess (stdio)
Auth Requirement	API Key required	API Key required
Pricing Model	BYOK (Pay Provider Direct)	BYOK (Pay Provider Direct)
Required Env Vars	`OPENAI_API_KEYOLLAMA_API_KEY`	`LLM_API_KEY`
Compatible Clients	Claude DesktopCursorWindsurfClineVS Code	Claude DesktopCursorWindsurfClineVS Code
Install path signal	`npx · high`	`npx · low`
Engagement & Health	3 views 0 copies 0 upvotes 5 stars	2 views 0 copies 0 upvotes 29,870 stars
Verified / Official	Community Listing	Community Listing
Open full listing	View Memkin Listing	View Cognee Listing

Tools & Capabilities Breakdown

Memkin Tools (6)

Incremental and historical data collection from 7 Feishu sources

AI session data ingestion from Claude Code, Codex, Hermes/OpenClaw

Private local knowledge graph with entity linking and identity merging

Hybrid retrieval combining full-text search and vector similarity

Privacy-preserving data handling with reversible and irreversible redaction

MCP server supporting stdio and Streamable HTTP transport

Cognee Tools (6)

Supports ingestion from 30+ data sources

Combines vector embeddings with graph-based reasoning

Self-hosted knowledge graph with ontology generation

Persistent memory for AI agents with cross-session recall

User/tenant isolation and audit traceability

OpenTelemetry (OTEL) collector integration

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).

Memkin Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "andrelyl-memkin": {
      "command": "npx",
      "args": [
        "-y",
        "memkin"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY_HERE",
        "OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
      }
    }
  }
}

Cognee Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "topoteretes-cognee": {
      "command": "npx",
      "args": [
        "-y",
        "topoteretes-cognee"
      ],
      "env": {
        "LLM_API_KEY": "YOUR_LLM_API_KEY_HERE"
      }
    }
  }
}

Frequently Asked Questions

Memkin is categorized under Knowledge & Memory and uses a local stdio subprocess. In contrast, Cognee belongs to Knowledge & Memory using local stdio subprocess. Select Memkin when you need capabilities focused on knowledge & memory and Cognee when you require tools for knowledge & memory.

More alternatives to Memkin More alternatives to Cognee Knowledge & Memory category hub