# memory_plugin MCP server

> Provides local-first long-term memory and hybrid RAG to help AI coding agents retain context, preferences, and project knowledge across sessions.

- Repository: https://github.com/Lotargo/memory_plugin
- Page: https://hostedmcp.org/servers/lotargo/memory-plugin
- Transport: stdio
- Stars: 2
- License: MIT

## Install

### Claude Code

```sh
claude mcp add memory-plugin -- npx -y @lotargo/memory_plugin
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "memory-plugin": {
      "command": "npx",
      "args": [
        "-y",
        "@lotargo/memory_plugin"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "memory-plugin": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@lotargo/memory_plugin"
      ]
    }
  }
}
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "memory-plugin": {
      "command": "npx",
      "args": [
        "-y",
        "@lotargo/memory_plugin"
      ]
    }
  }
}
```

### Codex (`~/.codex/config.toml`)

```toml
[mcp_servers.memory-plugin]
command = "npx"
args = ["-y", "@lotargo/memory_plugin"]
```

### Gemini CLI (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "memory-plugin": {
      "command": "npx",
      "args": [
        "-y",
        "@lotargo/memory_plugin"
      ]
    }
  }
}
```

## FAQ

### Does this plugin require an external vector database?

No, it runs entirely locally without the need for Docker, an external vector database, or a hosted embedding API.

### How can I manage and view my saved memory records?

You can use a local web panel to browse and edit Notebook records, instructions, history, and knowledge sources.

### Is my data sent to a cloud provider?

Working memory stays local; however, you can optionally use cloud snapshots via Turso for manual or scheduled backups.

### Which AI coding clients are supported?

It supports OpenCode, Codex, Claude Code, Gemini CLI, and Antigravity.