Hand the job to AI agents.
Once, or every day.

No — Octomind Cloud is a no-code AI agent platform. The panel opens on one line to type into: you say what you want in plain language and an octo does it on its computer — browsing, writing files, running whatever it needs to. You never see a terminal unless you go looking for one. Everything it makes shows up on its page, downloadable in a click.

An AI that does work for you on its own: you say the job in plain words, and it does it — browsing, writing, building — once or on a schedule, then sends you the result. Here each one is an octo: named by you, with its own instructions, files and schedule, running on a cloud computer so your laptop can stay closed.

Not yet. Today it works from the web, your files and whatever you send it in chat — paste a message, forward a screenshot, or attach the file.

Pro is $50 a month — $20 your first month — and includes $50 of usage across up to 10 octos. Past that it only spends credits you bought in advance, then stops. An octo with nothing to do sleeps and costs only storage.

The cloud starts with Pro: $20 your first month, then $50, and you can cancel anytime — your first octo is working in under a minute. Free is the model hub on its own: every model at the same prices, pay as you go from credits, from the CLI or your own tools, with no cloud computer and no octos.

It works on its own — that is the point, so there is no approval queue to babysit. When it needs a decision only you can make, it asks in the chat and you answer like any other message; scheduled runs make the reasonable call and report it instead of waiting. Want a hard line? A guardrail rule in the octo’s workspace blocks a tool before it ever runs.

An octo is an agent for one thing you work on — the blog, a client, your money. Each keeps its own folder, instructions, conversations and routines. Octos run on machines of your own: containers with octomind, sudo and Docker, placed and woken for you. Several octos share one machine — five fit on a Small — so a whole crew costs one computer, and an idle machine suspends itself so it costs almost nothing while you sleep. Open Advanced to size machines or bring your own image.

Idle machines bill memory only — $0.012 per GB-hour, about 2.4 cents an hour on Small — and after a few minutes of inactivity (15 by default, configurable) they suspend automatically; from then on you pay storage only. There is never a surprise: one live usage allowance is always visible in the panel.

Everything the agent uses, from one balance in dollars: the AI model’s work (what the provider charges us plus 5%), the machine’s time while it runs, storage, and any images, video or voice it produces. Your plan includes usage worth its price — Pro’s $50 a month is $50 of usage — and prepaid credits pick up after that, at the same prices.

Both. Drag, paste or attach an image in the composer and the agent looks at it — on every paid plan, as long as the model you picked has vision (the attach button tells you before you send if it does not). Voice is on paid plans: hold the mic and your words arrive as text you can edit, and from Telegram or WhatsApp you can send a voice note and get the answer back as one. Listening costs $0.010 a minute, speaking $0.025, on top of the model — and spoken replies stay off until you switch them on in Settings.

No. Models come through the built-in gateway: log in once and every machine can use them — the whole catalog, Claude, GPT, GLM, Qwen. Everything is billed the same way: what the provider charges us plus 5%, from your plan and then from credits.

Sessions and your shared directory are durable — suspend never touches them, and every session replays in full when you come back. If you cancel Pro, nothing is deleted for 30 days — resubscribe within the grace period and everything is exactly as you left it. Your files are downloadable from the Files tab whenever you want them.

Yes: build any image FROM our base (that guarantees octomind and the mount contract), push it to a public registry, and point the panel at it. We pull and verify — you get your exact toolchain.

Yes, on every paid plan. Everything the panel does is a REST API: create an octo, POST a prompt at one of its conversations, poll or stream the result, delete the octo when the job is over. It uses its own developer keys (om_…), separate from model gateway keys — create one on the Keys page; the full reference lives on the panel Docs page.

Both, always. The panel is a plain conversation first; open Advanced at the foot of the sidebar for a full web terminal into the same container, machines, workflows and the config editor. Nothing is locked behind it — shells are per-connection, but your files and sessions always persist.