deliberate.codes

Practical AI for data & software engineers. What works, no hype.

Why I turned my old MacBook into a server for coding agents

Async coding agents need a host. Mine is called Ferris. This post is about getting coding agents to work for me asynchronously. The article walks through installing Debian on an old Mac, getting Claude Code and Codex signed in over XRDP, and the three use cases I run on Ferris today.

Ferris: a 15“ Retina MacBook Pro running Debian and XFCE, flanked by Tux and the Rust crab.

Building Ferris#

Ferris is my old 15“ Retina MacBook Pro. It was my favorite laptop for over five years until we parted ways for a newer model. Since then it has been sitting in my drawer without a purpose. The specs are (roughly): Intel Core i7 at 2.50 GHz, 16 GB RAM, NVidia graphics with 2 GB NVRAM.

When I read about all the people running OpenClaw or other agents on tiny VMs in the cloud, I thought: “Ferris still has ample power for Claude Code or Codex”. I run LLMs in the cloud via Anthropic or OpenAI, so the heavy thinking happens in the cloud anyway. Ferris only has to handle file operations and, of course, compiling the software it generates.

I started by installing Debian 13 “trixie”. The process was straightforward:

  1. Download a live install image. I went with Live Xfce amd64.
  2. Still on macOS, flash an old USB stick using balenaEtcher.
  3. Reboot the Mac and hold Option (⌥) to select the Debian Live Installer.
  4. Install with defaults.

Once Linux is installed, you want it to stop sleeping even when the display lid is closed. Set the following in /etc/systemd/logind.conf:

[Login]
HandleLidSwitch=ignore
HandleLidSwitchExternalPower=ignore
HandleLidSwitchDocked=ignore

Installing Debian is generic, disabling lid sleep was pretty straightforward. Next step on my journey: how to sign in to my Claude and OpenAI subscriptions via a browser on a remote machine?

Logging in remotely via XFCE and RDP#

Logging into Claude Code on Firefox in XFCE.

I wanted to control Ferris remotely and work in a desktop environment, using Claude Code and Codex with my Claude 5x and ChatGPT Plus subscriptions. For that I use XFCE, a lightweight window manager for Linux. The Debian Live XFCE image ships with Firefox already installed, which covers everything I need.

The next question was: how to connect to XFCE remotely? After discussing this with Claude, my goal was to connect to XFCE on Ferris via RDP. The server for RDP on Linux is called xrdp and I summarized a tutorial on how to configure it in the TIL Configure XRDP and XFCE on Debian 13.

On my main Mac I use Windows App by Microsoft to connect to Ferris’ XFCE. Windows App is Microsoft’s RDP client; on macOS it replaced the older Microsoft Remote Desktop app and connects to any RDP server.

What Ferris actually does for me#

Three use cases keep Ferris busy: building software, remote control from anywhere, and conversations with my second brain from a phone.

Building software#

My primary use case for Ferris is building software with Claude. Claude Code runs on Ferris instead of my work laptop, so I am decoupled from it. I prompt Ferris with a set of instructions and the tasks are usually done by the time I check back.

My routine workflow is spec-driven development; I have written about it here on the blog.

Remote-controlling sessions#

Anthropic’s Remote Control feature lets you continue any Claude Code session from the web interface, the Claude app on your phone, or the desktop app. The docs are at Continue local sessions from any device.

I run /remote-control some-name inside Claude Code to enable remote access. The next puzzle piece was keeping the terminal session alive that Claude Code was invoked in. tmux solves that (see also my TIL tmux: terminal multiplexer):

# SSH into Ferris
> ssh marco@ferris.local

# Start a new tmux session
marco@ferris> tmux new

# Start Claude
tmux[0]> claude

# Trigger Remote Control within the session
claude> /remote-control my-session

Chatting with my second brain on the phone#

For coding I prefer an actual keyboard and a bigger screen. But there is one use case where the phone wins: chatting with my second brain from anywhere.

I took Karpathy’s LLM Wiki gist and built myself an LLM wiki I call second brain. It is a collection of Markdown files about my content and posts, both for this blog and for LinkedIn. Every time I have a question, a thought, or an idea for an article or a post, I use my phone and Claude to iterate on it via a remote session running on Ferris.

Learnings and outlook#

My biggest learning from this experiment is the freedom and productivity I gain once the agent runs on a remote machine and I no longer depend on my laptop. For me this is a big step towards a setup in which agents work autonomously on my behalf. It helps a lot to have the agent constrained to a designated host.