DorkOS vs Droid

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.

Swapping the model in the middle of a job is genuinely useful, and their list is one of the longest anywhere. It is still a different thing from swapping the agent, and nothing in their documentation runs another company’s coding agent. Droid is unusually polite about what you already wrote, though: it reads a CLAUDE.md as happily as an AGENTS.md, so bringing your instructions across costs nothing.

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.

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.

This is a lead agent running a team, not just parallel lanes, and Factory is refreshingly honest about the limits. Their own writing says doing things in order has beaten running everything at once, and lists whether parallel work helps at all as a question they are still testing. Worth remembering whenever anyone, us included, sells you a picture of ten agents working at once.

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.

One catch if you bring your own model keys: their documentation says custom models work in the command-line tool and the desktop app, and do not appear on the hosted web and phone surfaces. So the widest reach and the most control are, for now, two different setups.

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.

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.