📡 MCP Radar

agentsea/nautilo

AI goes multiplayer. A self-hosted workspace for people and machine people. Create, code, and work together across desktop, mobile, and web. Open source. MIT licensed.

⭐ 51 stars
⑂ 4 forks
TypeScript
momentum ▲ 110.0
created 2026-09-16
on radar since 2026-09-18
star trend 31 → 51 since 2026-09-18
ai-agentscollaborationelectrongenerative-aimodel-context-protocolmulti-agentreact-nativeself-hosted
View on GitHub ↗Homepage ↗

About nautilo

English · 简体中文 · 日本語 · Français · Español · 한국어

Code and documentation are currently in English. Translation PRs are welcome; see translation contributions.

https://github.com/user-attachments/assets/79a6c37f-ea01-4e95-afd5-85d4b9b55e0d

Your own super agent. Your people and their Genies. You own the intelligence.

Meet your Genie: a radically customizable agent with a personality, memory, face, and voice you choose. Put her to work writing, researching, browsing, coordinating coding agents, or making a film. Bring your friends, your team, and their Genies into the same Room. Work together. Grab the controls whenever you want to do it yourself.

That's Nautilo. Natively multi-user. Built for people and machine people. Desktop, mobile, and web. Your server, your models, your rules. Open source. MIT licensed.

Website & demos · Get started · Documentation · Download · Packages · Contribute

Every Nautilo client connects to a Nautilo server. Choose the path that fits where you are:

Trying Nautilo for the first time on a Mac? Start with the Local Deploy Quickstart. It is a single-machine evaluation setup. For mobile access or a server your team can reach, choose a hosted deployment below.

You want to… Start here --- --- Join an existing server Download Nautilo, then install and connect with your server address or invite. Run your first server on your Mac Follow the Local Deploy Quickstart, using Docker Desktop and the signed Nautilo CLI. Give your team a server in the cloud Use the Railway deployment guide. Run on your own Docker infrastructure Follow the Docker Compose gui

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/agentsea--nautilo.html)

Related MCP servers

azimov777/casefile

The task tracker your AI agents keep for each other: every task carries a case file, so the next agent picks up where the last one stopped. MCP server + live board. Self-hosted, one-line install.

⭐ 3TypeScript
Azure-Samples/foundry-hosted-agents-workshop

A hands-on, step-by-step workshop for building a Travel Assistant agent on Microsoft Foundry hosted agents with the Agent Framework - growing from a single agent to a multi-agent planner with function

⭐ 3Python
leluong141996-dev/Agent-Brain-Hub

Shared, brain-inspired memory for AI agents: 13 brain regions with awake/sleep loops, a live visualizer, agents connected via REST/SDK/MCP, governance & audit, and business-value metrics. Works with C

⭐ 3JavaScript
0xsline/OpenChatCut

Local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion-powered rendering.

⭐ 130TypeScript
herry2059/project-os-for-codex

Open-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.

⭐ 104TypeScript
christiangrey922/multi-agent-workflow-lab

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

⭐ 87TypeScript

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.