Guide

What an AI agent can and cannot do on a hosted Mac

A hosted Mac gives a coding agent a real development machine: Xcode, the iOS Simulator, a real browser, persistent logins, and a machine that never sleeps. It also has limits that come from being a Mac in a data center rather than one on your desk. Knowing both before you rent saves a refund later. This is the complete list, including the awkward parts.

What works, and works well

Any developer tool, as an admin. Claude Code, Codex, Xcode, Playwright, Homebrew, Docker, Node, Python, and whatever else your project needs. It is your machine.
A real browser for development. Sign in to GitHub, your package registry, App Store Connect, or your staging site once. The agent uses those sessions to test what it builds and read the docs it needs.
Always on. Wired ethernet, never sleeps, restarts itself, session kept alive.
Control from your phone. Claude Code's Remote Control attaches the Claude app to the session running on the Mac.
The desktop when you need it. Screen Sharing from a browser tab for logins, two-factor prompts and anything that stalls.
Small local models. Roughly 8B-parameter models run acceptably on a 16 GB machine, for code tasks where the data has to stay on the box.
Xcode and the iOS Simulator. The agent can build your app, run it on the simulator, and screenshot the result. That is the thing a Linux box cannot do.

What is unreliable

iMessage and FaceTime. Apple ties activation to hardware and often blocks Macs it identifies as hosted. Sometimes it works; do not build on it.
Sites that dislike data-center addresses. Some services, LinkedIn and Instagram among them, challenge or block automation from a hosting IP.

What is off the table

Anything physically nearby. Bluetooth, HomeKit, AirDrop, a printer in your office, a USB device. The Mac is not in your building.
Large local models. A base 16 GB M6 will not run 30B or 70B models. Agents on it call cloud models, which is what Claude Code and Codex do anyway.
Bulk messaging. A personal assistant on your own accounts, such as your email, calendar and chats, is fine. Bulk or unsolicited messages on any app are not. Every Mac shares one internet address, so one spammer would get it blocked for everyone.
Abuse. No spam, no scraping at scale, no credential stuffing, no crypto mining, no automating other people's accounts against their terms. That is the acceptable use policy and it is enforced.
Instant reboots. A restart takes a few minutes, not seconds, and there is no power button to hold.

How to decide

A hosted Mac is a strong fit for a coding agent that works on your software with cloud models. It should need to run all day. And it should only sometimes need a person to click something. It is the wrong tool for three kinds of agent. One that needs iMessage as a core feature. One that needs a device on your local network. One that needs a big model on the machine. Better to know that now.

Frequently asked questions

Does iMessage work on a hosted Mac?

Unreliably. Apple ties iMessage activation to hardware and often refuses it on hosted Macs. It sometimes works, but nothing important should depend on it.

Can the agent use accounts I sign in to?

Yes, for development. Sign in to GitHub, npm, App Store Connect, or your staging environment once through the browser desktop, and the agent uses those sessions afterward. The logins stay on the machine, not with us. Accounts that have nothing to do with your software are outside what the Mac is licensed for.

Can I run local LLMs on a hosted Mac mini?

Small ones. A 16 GB machine handles roughly 8B-parameter models for code tasks where the data has to stay on the box. Large models need far more memory than a base mini has; agents on it use cloud models instead.

What happens if my agent gets stuck?

You open the Mac's screen in your browser, deal with the prompt, login or captcha, and close the tab. The session keeps running throughout.