AgentHubAgentHub

cognitive-ai-memory

MCP ServerMCP Registry官方收录

io.github.sachitrafa/cognitive-ai-memory · v1.0.2

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

概览

cognitive-ai-memory 是一个MCP Server,收录自 官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。

安装

选择你的平台查看安装方式

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

环境变量

DATABASE_URL必填

PostgreSQL connection string with pgvector. Example: postgresql://localhost:5432/yourmemory

OLLAMA_URL可选

Ollama server URL for local embeddings (nomic-embed-text) and classification (llama3.2:3b). Default: http://localhost:11434

EXTRACT_MODEL可选

Ollama model used for fact/assumption classification. Default: llama3.2:3b

相关资源

统一 Manifest

{
  "id": "io.github.sachitrafa/cognitive-ai-memory",
  "type": "mcp-server",
  "version": "1.0.2",
  "displayName": "cognitive-ai-memory",
  "description": "Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall.",
  "repository": {
    "url": "https://github.com/sachitrafa/cognitive-ai-memory",
    "source": "github"
  },
  "distribution": {
    "packages": [
      {
        "registryType": "oci",
        "identifier": "ghcr.io/your-memory/cognitive-ai-memory:1.0.2",
        "transport": "stdio",
        "environmentVariables": [
          {
            "name": "DATABASE_URL",
            "description": "PostgreSQL connection string with pgvector. Example: postgresql://localhost:5432/yourmemory",
            "isRequired": true
          },
          {
            "name": "OLLAMA_URL",
            "description": "Ollama server URL for local embeddings (nomic-embed-text) and classification (llama3.2:3b). Default: http://localhost:11434"
          },
          {
            "name": "EXTRACT_MODEL",
            "description": "Ollama model used for fact/assumption classification. Default: llama3.2:3b"
          }
        ]
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "vscode"
  ],
  "keywords": [],
  "provenance": {
    "origin": "official-mcp-registry",
    "originalId": "io.github.sachitrafa/cognitive-ai-memory",
    "originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.sachitrafa%2Fcognitive-ai-memory/versions/latest",
    "isOfficial": true,
    "status": "active"
  }
}
cognitive-ai-memory — MCP Server 安装与配置 · AgentHub