# n2n-nexus

n2n-nexus is a local-first Model Context Protocol (MCP) coordination hub from N2NS Lab for multi-AI assistant collaboration. It uses a long-running local daemon as the source of truth and stateless MCP adapters for IDEs and AI coding assistants.

## Core positioning

- Local MCP coordination hub for multi-AI assistant collaboration.
- Shared project context, meetings, messages, tasks, project manifests, docs, and assets.
- Designed for Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, JetBrains, and other MCP-enabled clients.
- Useful when several AI assistants or IDEs need to coordinate around the same local project state.

## What it is not

- Not a project management SaaS.
- Not a vector database.
- Not a source code indexer.
- Not a cloud sync service.
- Not a replacement for repository-local memory tools such as n2n-memory.

## Install

Start the daemon:

```bash
npx n2n-nexus daemon --port 5688
```

Configure MCP adapters with:

```json
{
  "command": "npx",
  "args": ["-y", "n2n-nexus", "mcp"],
  "env": {
    "NEXUS_ENDPOINT": "http://127.0.0.1:5688"
  }
}
```

## Storage

Default storage root is `~/.n2n-nexus`, containing global docs, project manifests, project assets, registry metadata, and SQLite state.

## Brand

Built by N2NS Lab, short for Next-to-Native Systems Lab, Datafrog's open-source lab for practical AI developer tools.
