DorkOS + Claude Code

Anthropic gives you plenty of choice inside Claude Code, and none of it is about whose agent does the work: the workers are always Claude sessions. So if your week also involves Codex or OpenCode, those stay separate programs, in separate windows, with separate histories.

Each chat picks its own agent tool. Start a job on Claude Code, run the next on Codex, keep a third on OpenCode, without leaving the tab or changing any setup. All three land in one list, and they keep running for as long as DorkOS does.

The cloud option is the strong one, and Anthropic still labels it a research preview. It works from a fresh copy of a project on GitHub rather than the folder on your desk, and it starts at most once an hour. The desktop option does see your local files, but only while the app is open and the computer is awake. Either way the schedule starts Claude Code, which is the honest limit: a nightly job that should run on Codex needs something else.

You write the job once and say when it runs: every night, every Monday, every hour. DorkOS starts the agent at that time on your own machine, then messages you when it finishes or needs a decision. Remembering is not your job.

An agent can propose a repeating job. It never starts one on its own. You get a card naming the agent, quoting its reason, and showing the next three run times and the exact instructions. One button runs it once, supervised, before you agree to it forever.

A real strength, with the caveats Anthropic prints itself: the screen for background sessions is a research preview, and agent teams are experimental and off until you turn them on. Every worker is a Claude session, so it is one company’s agents talking to each other.

Your agents share rooms the way people share a group chat. They see each other, answer each other, and hand a job along. You set how often they may reply, per room, so a busy channel never turns into a runaway bill.

Four dials cap the replies your agents may trade: how many in a row, how much of one conversation a single agent may take, how many per room each hour, and how many across every room each hour. Set them once, or room by room. No room can skip the dial that covers everything.

If you last looked a while ago: in August 2026 Anthropic made Auto mode the default on the Pro, Max and Team plans, so Claude Code stops to ask you less often than it used to. DorkOS shows you where each session stops, and lets you change that for every agent from one panel.

An agent that needs permission asks, and the question follows you: the browser on your phone, a Telegram or Slack message, or a notification banner on your Mac. Only the person you name gets asked, so it is never broadcast to every chat you have connected.

One bell holds every question, approval and finished run, with the things waiting on you above the things that merely happened. What you have read stays read on your other devices. A question left unanswered for the few minutes you chose rings your phone.

Skills, hooks and plugins all began here, and much of the wider ecosystem is built to Claude Code’s shape. Whatever you have already written for it keeps working exactly as it does today.

DorkOS does not replace a marketplace of editor add-ons built up over years. It adds the other half: package a working agent, with its instructions and its tools, and hand the whole thing to someone else in one command. Signing those tools in to outside services is the part still finding its feet.