DorkOS + Codex

The choice Codex offers is which OpenAI model does the work, not whose agent does it. If your week already mixes Codex with Claude Code, those stay two programs with two histories, and remembering which job went where is left to you.

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.

Cloud runs happen on OpenAI’s machines and cannot open a folder on your computer. Desktop runs can, but they need the computer on and the app running. Either way the schedule starts Codex, so it is not where a job belongs if that job should run on Claude Code.

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.

Running jobs in parallel is a genuine advantage when the pieces are independent: each gets its own sandbox, and none of them slows your own machine down. What they cannot do is talk, so a job that needs the answer from another job is still yours to line up by hand.

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.

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.

The setup follows you between surfaces: the same outside-tool connections work from the command line, the desktop app and the editor extension, so you write them once.

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.