DorkOS vs Cursor

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.

Cursor picks the model for its own agents, and that is the whole choice on offer: the agent is part of the editor. If you already run Claude Code in one terminal and Codex in another, Cursor does not gather them up. They stay separate tools you switch between by hand.

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.

Cursor’s cloud agents keep working after you hand them a job, which is not the same as starting one on their own. Nothing in Cursor says "run this every night at two".

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.

Cursor runs up to eight agents at once, each on its own copy of your project so they do not tread on each other. That is parallel work, not teamwork: each hands its result back to your conversation, and none can ask another a question or pass it the next step.

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.

You can start an agent from your phone, watch it work, and review and merge its pull request without opening a laptop. The iPhone and iPad app was still a public beta when we checked, and Android is named as planned rather than shipped. It is deliberately not an editor: it directs and reviews agents rather than writing code.

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.

Years of editor extensions carry over, with one catch: Cursor installs them from the Open VSX registry rather than the VS Code Marketplace, so a few will be missing. Its agent also reaches outside tools through MCP, so what your team already runs is reachable from inside the editor.