DorkOS vs GitHub Agent HQ

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.

GitHub will run a rival’s agent for you, which almost nobody else does. Two things are worth knowing. The line-up is shorter than the announcement suggested: Google’s and Cognition’s agents were promised for "the coming months" and are still not there. And these are GitHub’s own hosted versions of Claude and Codex, billed through your Copilot seat, not the Claude Code or Codex already installed and signed in on your machine. DorkOS drives that copy, which is why the plan you already pay for does the work.

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.

A saved job repeats hourly, daily or weekly, which covers most of what people want it for. The catch is the one in the table: your repository has to be private or internal, so none of this works on open source. DorkOS takes the time in plain words and runs the job on your own machine, whoever owns the repository, and whether or not there is one.

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.

Racing three agents at one problem is genuinely useful, and a pull request is a sensible place to compare the answers. It is competition, not teamwork: no agent can ask another a question or pick up where another left off.

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.

This is the sharpest difference, and not an oversight: living inside GitHub is the whole idea, and it is what makes the review, the permissions and the audit trail come free. The price is that the work has to be on GitHub first. DorkOS starts from a folder, any folder, on any host or none, and runs the agent beside it on the machine in front of you.

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.