# Meaning Model

> Meaning Model is an open-source MCP server for knowledge and memory. Let an AI build revisable models of stories, game worlds, histories and its own memory. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** macOS, Windows, Linux, CLI
- **Website:** https://meaningmodel.ai
- **Repository:** https://github.com/emergent-wisdom/meaning-model
- **MCP Registry name:** io.github.emergent-wisdom/meaning-model
- **Categories:** knowledge and memory, games and play
- **Listing updated:** 2026-11-14

## About

Rather than keeping notes as free text, the assistant records a world as a model it can inspect, correct and return to. A correction keeps what was believed before, which the site frames as memory held as processes over time. A Rust engine does the simulation work, and the npm package installs it with --install-engine or builds it with Cargo.

Four uses are named: novels and stories built from a world with whole lives behind each character, game worlds and invented places sketched coarsely then detailed on demand, an agent's memory of its work or user, and real systems such as markets where sources, estimates and uncertainty stay separate. Showcases include a viewer replaying how an AI built the world behind a story.

It runs on your machine with a local SQLite database, and your assistant calls life_modeling_context for guidance on the task at hand.

## Features

- **Revisable world models:** Models can be corrected without losing earlier beliefs.
- **Story feedback:** life_story_feedback grounds critique in the world you built.
- **Local storage:** The server and its SQLite database run on your computer.
- **Viewer:** Replay how a world was built step by step.
- **Agent-guided install:** Paste a prompt and the agent installs it from a guide.

## Good for

- Plan a novel's characters and world before drafting
- Build a game setting with detail added where players go
- Keep an agent's memory of a project that can be corrected
- Model a market with sources and uncertainty kept apart

## Install

### Claude Code (Terminal)

```sh
claude mcp add meaning-model --env LIFE_SIM_ENGINE_BIN='<LIFE_SIM_ENGINE_BIN>' -- npx -y @emergent-wisdom/meaning-model-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "meaning-model": {
      "command": "npx",
      "args": [
        "-y",
        "@emergent-wisdom/meaning-model-mcp"
      ],
      "env": {
        "LIFE_SIM_ENGINE_BIN": "<LIFE_SIM_ENGINE_BIN>"
      }
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "meaning-model": {
      "command": "npx",
      "args": [
        "-y",
        "@emergent-wisdom/meaning-model-mcp"
      ],
      "env": {
        "LIFE_SIM_ENGINE_BIN": "<LIFE_SIM_ENGINE_BIN>"
      }
    }
  }
}
```

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

```json
{
  "servers": {
    "meaning-model": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@emergent-wisdom/meaning-model-mcp"
      ],
      "env": {
        "LIFE_SIM_ENGINE_BIN": "<LIFE_SIM_ENGINE_BIN>"
      }
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "meaning-model": {
      "command": "npx",
      "args": [
        "-y",
        "@emergent-wisdom/meaning-model-mcp"
      ],
      "env": {
        "LIFE_SIM_ENGINE_BIN": "<LIFE_SIM_ENGINE_BIN>"
      }
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "meaning-model": {
      "command": "npx",
      "args": [
        "-y",
        "@emergent-wisdom/meaning-model-mcp"
      ],
      "env": {
        "LIFE_SIM_ENGINE_BIN": "<LIFE_SIM_ENGINE_BIN>"
      }
    }
  }
}
```

## Tools

- `life_modeling_context`: Gives the assistant operational guidance for a modeling task.
- `life_story_feedback`: Returns feedback on a story grounded in its world model.

## FAQ

### What do I need installed?

Node.js 22.18 or newer plus the matching Rust engine binary.

### Does my work leave my computer?

The server and database run locally; your assistant sees what it works on.

### Is Meaning Model free?

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

### How do I add Meaning Model to Claude Code?

Run this command in your terminal: claude mcp add meaning-model --env LIFE_SIM_ENGINE_BIN='<LIFE_SIM_ENGINE_BIN>' -- npx -y @emergent-wisdom/meaning-model-mcp

### What are the best alternatives to Meaning Model?

The closest alternatives to Meaning Model 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.
- [AvatarSay — Fictional Character & Talking Video MCP](https://ai-powered.com/mcp/avatarsay-fictional-character-and-talking-video-mcp): AvatarSay — Fictional Character & Talking Video MCP is a freemium MCP server for design and media.
- [VfxSmith](https://ai-powered.com/mcp/vfxsmith): VfxSmith is a freemium MCP server for design and media.
- [Born Then](https://ai-powered.com/mcp/born-then): Born Then is a free MCP server for education and exams.

---
Source: https://ai-powered.com/mcp/meaning-model
