MCP Server

io.github.sachitrafa/cognitive-ai-memory MCP Server

Name: io.github.sachitrafa/cognitive-ai-memory MCP Server
Author: io.github.sachitrafa

io.github.sachitrafa/cognitive-ai-memory

Repository Registry

What is the io.github.sachitrafa/cognitive-ai-memory MCP server?

Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall.

How to install io.github.sachitrafa/cognitive-ai-memory

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

Environment / auth

DATABASE_URL
required
PostgreSQL connection string with pgvector. Example: postgresql://localhost:5432/yourmemory
OLLAMA_URL
Ollama server URL for local embeddings (nomic-embed-text) and classification (llama3.2:3b). Default: http://localhost:11434
EXTRACT_MODEL
Ollama model used for fact/assumption classification. Default: llama3.2:3b

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "cognitive-ai-memory": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/your-memory/cognitive-ai-memory:1.0.2"
      ],
      "env": {
        "DATABASE_URL": "<YOUR_DATABASE_URL>",
        "OLLAMA_URL": "<YOUR_OLLAMA_URL>",
        "EXTRACT_MODEL": "<YOUR_EXTRACT_MODEL>"
      }
    }
  }
}

Cursor

~/.cursor/mcp.json

{
  "mcpServers": {
    "cognitive-ai-memory": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/your-memory/cognitive-ai-memory:1.0.2"
      ],
      "env": {
        "DATABASE_URL": "<YOUR_DATABASE_URL>",
        "OLLAMA_URL": "<YOUR_OLLAMA_URL>",
        "EXTRACT_MODEL": "<YOUR_EXTRACT_MODEL>"
      }
    }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "cognitive-ai-memory": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/your-memory/cognitive-ai-memory:1.0.2"
      ],
      "env": {
        "DATABASE_URL": "<YOUR_DATABASE_URL>",
        "OLLAMA_URL": "<YOUR_OLLAMA_URL>",
        "EXTRACT_MODEL": "<YOUR_EXTRACT_MODEL>"
      }
    }
  }
}

VS Code

.vscode/mcp.json

{
  "servers": {
    "cognitive-ai-memory": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/your-memory/cognitive-ai-memory:1.0.2"
      ],
      "env": {
        "DATABASE_URL": "<YOUR_DATABASE_URL>",
        "OLLAMA_URL": "<YOUR_OLLAMA_URL>",
        "EXTRACT_MODEL": "<YOUR_EXTRACT_MODEL>"
      }
    }
  }
}

Claude Code

claude mcp add cognitive-ai-memory --env DATABASE_URL=<YOUR_DATABASE_URL> --env OLLAMA_URL=<YOUR_OLLAMA_URL> --env EXTRACT_MODEL=<YOUR_EXTRACT_MODEL> -- docker run -i --rm ghcr.io/your-memory/cognitive-ai-memory:1.0.2

Related MCP servers

YourMemory

Persistent memory for AI agents. Memories decay with time and strengthen on recall.

View repository →