# Muxen

> All your machines, one app. For you and your AI agents. Muxen is a native app for macOS, Linux and Windows that puts all of your machines (Macs, Linux boxes, Windows PCs, cloud servers and VMs) in one window, and gives AI agents the same reach through an MCP server and a command line.

Muxen is made by Lumary Labs LLC. It's a paid app in early access: downloads and pricing aren't public yet.
What it does, on any machine you can reach with ssh:

- Agent sessions: run Claude Code, Codex, OpenCode, Gemini CLI, Amp, Pi or a shell there. They keep running on the machine, like tmux, whether or not Muxen is open.
- Desktops: the machine's screen, live, with your mouse and keyboard (Macs, Linux with X11, Windows), beside a session's terminal.
- Servers in your browser: a web server running on the machine opens at localhost on your computer, through Muxen's own connection.
- Logs, services and Docker: live logs, services (systemd, Homebrew, Windows), containers and Compose projects, and processes.
- Files: copy files and folders between any two machines, through Muxen.
- Several machines at once: one command on many machines, and schedules that run a command or start an agent on a machine at set times.
- VMs and cloud machines: make a Windows or Linux VM on a machine you have, or a DigitalOcean droplet, and use it like any other.
- GitHub: review requests, issues and pull requests; hand an issue to an agent in a fresh workspace; self-hosted GitHub Actions runners and their jobs.
- Usage: what Claude Code and Codex used on every machine, at API prices.

For AI agents: everything above is in Muxen's MCP server (`muxen mcp`, 80+ tools) and its CLI, where every command takes `--json`. Add it to Claude Code with `claude mcp add muxen -- muxen mcp`. Agents read freely, and change things on your machines only when you ask.

How it connects: with your own ssh, then a small agent Muxen installs on each machine, over one live connection (ssh, or direct over QUIC), on your local network or through Tailscale. Your settings stay on your computer, in one config.toml. The app has no analytics or telemetry.

## Start

- [Introduction](https://muxin.dev/docs/index.md): Muxen is one app for all your machines: the Macs, Linux boxes, Windows PCs and cloud servers you work on, for you and your AI agents.
- [Getting started](https://muxin.dev/docs/getting-started.md): Install Muxen, add your first machine, and start an agent on it.

## Your machines

- [Machines](https://muxin.dev/docs/machines.md): What the overview and a machine’s page tell you, how the sidebar is organized, and what each state means.
- [Connections](https://muxin.dev/docs/connections.md): How Muxen reaches your machines: one ssh connection, or a direct one over QUIC, on your local network or through Tailscale.
- [VMs on your machines](https://muxin.dev/docs/vms.md): Make a Windows or Linux VM on a machine you already have, use it like any other machine, and destroy it when you’re done.
- [Cloud machines](https://muxin.dev/docs/cloud.md): Make a DigitalOcean droplet from Muxen, set up and added to your machines, and keep an eye on what it costs.
- [Windows](https://muxin.dev/docs/windows.md): Manage Windows PCs from Muxen over OpenSSH, run Muxen itself on Windows, and make Windows VMs.

## On your machines

- [Agent sessions](https://muxin.dev/docs/sessions.md): Run Claude Code, Codex or a shell on any of your machines, and come back to it whenever you like.
- [Desktops](https://muxin.dev/docs/desktops.md): See a machine’s screen live, next to its terminal, and use its mouse and keyboard.
- [Servers and ports](https://muxin.dev/docs/servers.md): See what’s listening on a machine, and open its web servers at localhost on your computer.
- [Logs, services and Docker](https://muxin.dev/docs/logs-services.md): Read a machine’s logs live, and start, stop and restart its services, Docker containers and Compose projects.
- [Files and the clipboard](https://muxin.dev/docs/files.md): Copy files and folders between any two of your machines, and share the clipboard with their desktops.
- [Run a command everywhere](https://muxin.dev/docs/run.md): One command on several machines at once, with each one’s output side by side.
- [Schedules](https://muxin.dev/docs/schedules.md): Run a command or start an agent session on one of your machines at set times, even when Muxen isn’t open.

## Code and CI

- [GitHub and workspaces](https://muxin.dev/docs/github.md): Your review requests, issues and repositories, the checkouts on your machines, and handing an issue to an agent.
- [Runners and jobs](https://muxin.dev/docs/runners.md): Install self-hosted runners on your machines, see which ones are busy, and find out why a job isn’t starting.

## For AI agents

- [MCP for your agents](https://muxin.dev/docs/agents.md): Let Claude Code, Codex or any MCP client see and work with your machines through Muxen.
- [Command line](https://muxin.dev/docs/cli.md): The muxen command: everything the app does, for your terminal, your scripts and agents without MCP.

## More

- [Usage and cost](https://muxin.dev/docs/usage.md): What Claude Code and Codex used across all your machines, in tokens and in what it would cost on the API.
- [Settings and themes](https://muxin.dev/docs/settings.md): What each Settings tab changes, where your settings are kept, and every keyboard shortcut.
- [Troubleshooting](https://muxin.dev/docs/troubleshooting.md): What each “can’t connect” message means and how to fix it, plus where Muxen keeps its files and how to get help.

## Optional

- [All of the docs in one file](https://muxin.dev/llms-full.txt)
- [Privacy policy](https://muxin.dev/privacy)
- [Terms of service](https://muxin.dev/terms)
- [Contact](mailto:contact@lumarylabs.com)