# SuperLocalMemory

> SuperLocalMemory is an open-source MCP server for knowledge and memory. Local-first memory for agents that cites sources and says when it doesn't know. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** macOS, Windows, Linux, CLI, self-hosted
- **Website:** https://superlocalmemory.com
- **Repository:** https://github.com/qualixar/superlocalmemory
- **MCP Registry name:** io.github.qualixar/superlocalmemory
- **Categories:** knowledge and memory, AI models and LLM tooling
- **Listing updated:** 2026-11-14

## About

Every recall ends in one of three outcomes: a supported answer, the closest memories with a note that there is no exact match, or a plain statement that the thing is not stored. The point is to avoid a confident guess. A saved fact can replace an older one, the old memory is kept, and the change can be undone; each fact records when it happened and when it was learned.

In its local mode the core remember and recall calls make no model-provider call, so no API key or cloud account is needed. An on-device judge, enabled by default on Apple Silicon, checks whether the found memories answer the question, and an online check runs only after you consent. Screenshots, photos and PDFs can be indexed with local OCR and answers cite file and page.

For teams it adds roles, workspaces, a hash-chained audit trail, erasure and GDPR export, plus a mesh for messaging between local agents and web bots. Recall is layered under a hard token cap. It installs from npm or pip, supports Claude Code, Codex, Cursor and others, and the core is AGPL v3.

## Features

- **Three-tier recall:** Supported answer, closest memories, or an explicit not-found.
- **Replaceable facts:** New facts can replace old ones with undo.
- **Local documents and images:** OCR and image search cite file and page.
- **Governance:** Roles, workspaces, audit trail and GDPR export.
- **Agent trust scores:** Records which agent wrote each memory.
- **SLM-Mesh:** Messages, locks and shared state between agents and bots.
- **Capped recall:** Layered output under a hard token limit.

## Good for

- Share one memory across several coding agents
- Ask what was true last month
- Search screenshots and PDFs by description
- Keep an audit trail of agent memory writes
- Stop agents guessing when nothing is stored

## Install

### Claude Code (Terminal)

```sh
claude mcp add superlocalmemory -- npx -y superlocalmemory
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "superlocalmemory": {
      "command": "npx",
      "args": [
        "-y",
        "superlocalmemory"
      ]
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "superlocalmemory": {
      "command": "npx",
      "args": [
        "-y",
        "superlocalmemory"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "superlocalmemory": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "superlocalmemory"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "superlocalmemory": {
      "command": "npx",
      "args": [
        "-y",
        "superlocalmemory"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "superlocalmemory": {
      "command": "npx",
      "args": [
        "-y",
        "superlocalmemory"
      ]
    }
  }
}
```

## FAQ

### Does it need an API key?

In Mode A, core remember and recall make no model-provider call, so no key, cloud account or Docker.

### How do I install it?

npm install -g superlocalmemory, then slm setup; pip is the other route.

### What license?

AGPL v3 for the free local core.

### Which platforms?

Windows, Linux and macOS.

### Is SuperLocalMemory free?

Yes. SuperLocalMemory is open source, so you can use and self-host it for free.

### How do I add SuperLocalMemory to Claude Code?

Run this command in your terminal: claude mcp add superlocalmemory -- npx -y superlocalmemory

### What are the best alternatives to SuperLocalMemory?

The closest alternatives to SuperLocalMemory are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [MedXpert 图书馆连接器（通用版）](https://ai-powered.com/mcp/medxpert): MedXpert 图书馆连接器（通用版） is an open-source MCP server for knowledge and memory.
- [Context Nest](https://ai-powered.com/mcp/context-nest): Context Nest is a freemium MCP server for knowledge and memory.
- [Tulsa Ecosystem Map](https://ai-powered.com/mcp/tulsa-ecosystem-map): Tulsa Ecosystem Map is a free MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/superlocalmemory
