# AI agents on a home server: one environment for Windows, MacBook and phone Note, 2026-10-23 I run my AI agents on a home server with Linux, and from Windows, a MacBook and my phone I only steer them. All of those devices see the same environment, and the server does the work. A Linux server with SSH and Docker is, in my opinion, the best thing you can give your agent. Last updated: 2026-10-23 ## My hardware I work on Windows, a MacBook and a Linux server. The server is an ordinary computer that doubles as my NAS, a network disk available on my home network. It runs all the time because it draws very little power. ## What I get from it From every computer I connect to the server and use the same agents: Codex, Claude Code or Copilot in VS Code. I used VS Code more earlier, when I opened plain code more often than an environment for agents. The projects live on the server, so they take no disk space on the MacBook or the Windows machine and put no load on either. I never end up with something on one computer and not on the other. I could also keep the project files on GitHub, but one permanent environment is more convenient. What I like most is that the server sits at home, and from my phone, even away from home, I give commands to an agent running on a computer on my own network. ## Docker on Linux Docker runs a program in an isolated environment called a container. It works great on Linux, in my opinion worse on Windows, and not very well on macOS either. The reason is simple: a container uses the Linux the computer already runs. On Windows and macOS, Docker has to start a virtual machine with Linux in the background, so there is an extra layer that eats memory and slows down things like file access. In containers I usually run Python with some packages or Node with a website. The downside is that container images take a lot of space. Every layer of an image eats disk. ## A graphics card and local models The server has a graphics card that can handle small models. I run models on it that turn speech into text and text into sound (that may be a topic for a separate post), and I host a few LLMs. Some of my apps use them, so I process data privately, at home. For writing a program or a demanding analysis I prefer a paid model. I use the local ones for simple, highly repetitive things, because I pay nothing per call. There is no API bill and no limit that runs out. The cost is electricity, wear on the hardware, and buying that hardware in the first place. ## A windowed app instead of the terminal I prefer graphical apps to an agent in the terminal. I take a screenshot, mark what I don't like on a page or in an app, and comment on what to fix. Voice mode is handy too. The ChatGPT and Claude desktop apps connect over SSH to my home server without trouble. With a VPS rented in the cloud it should work the same way. Then my computer uses no resources, the agent keeps working even after I switch it off, and I can look at the result (a program, a page, an analysis) later from my phone. ## The biggest downside By default, over SSH I don't get computer use to the extent I would on Windows, a Mac or a desktop Linux. The agent runs shell commands, e.g. curl to download something from the web, or Docker containers. That works without windows and without a preview. Playwright helps a bit: the agent opens my page, renders it and shows me how it looks. There is also a way around the missing screen. You can run a desktop without a monitor on the server, e.g. a virtual display with Xvfb or GNOME reachable over VNC, and the agent controls it by looking at screenshots. It needs no graphics forwarding over SSH. I haven't tested this myself yet. ## Glossary - **Linux**: An operating system popular on servers, an alternative to Windows and macOS. - **SSH**: A secure connection to another computer where you type commands as if you were sitting at it. - **Docker**: A program that runs an app in an isolated environment (a container) together with everything it needs. - **NAS**: A computer with disks that other devices at home save files to and read files from over the network. - **Codex**: An AI assistant from OpenAI that works on files on your computer: it reads and changes them and runs programs. - **Claude Code**: An AI assistant from Anthropic for programming that reads project files and runs commands. - **Copilot**: An AI assistant from GitHub for writing code, built into editors such as VS Code. - **VS Code**: A free code editor from Microsoft. - **GitHub**: A website where projects are stored together with their history of changes. - **Python**: A popular programming language, e.g. for scripts and data analysis. - **Node**: A runtime for programs written in JavaScript, e.g. websites. - **LLM**: A large language model, an AI program that understands and writes text, e.g. ChatGPT or Claude. - **API**: A way for one program to request something from another, here paid access to an AI model from your own app. - **terminal**: A window where you type commands as text instead of clicking. - **VPS**: A server rented in the cloud that you connect to over the internet and run your programs on. - **computer use**: A mode where an AI agent looks at the computer screen and clicks and types by itself. - **curl**: A command that downloads files and pages from the internet straight from the terminal. - **Playwright**: A tool that opens a page in a browser controlled by a program, e.g. to take a screenshot of it. - **GNOME**: The look of the desktop on Linux, meaning windows, menus and icons. - **Xvfb**: A program that creates a virtual screen in memory so graphical apps can run on a server with no monitor. - **virtual machine**: A program that imitates a separate computer in a window, running another system, here Linux.