Cloud AI, and the three things it means
Cloud AI means three things people keep confusing: a model hosted at a provider, an API called from software you write, and an agent that runs on a remote machine and works there on its own. The third is the only sense in which something keeps going after you close the tab.
Three things under one phrase
The oldest sense is a hosted model. You download nothing, you send a question, an answer comes back. That is what an assistant in a tab does.
The second is the one engineering teams mean: an API. The model becomes a part in software you write, billed per token. The machine stays at the provider, the logic stays with you.
The third is newer, and it is the one that changes the day of somebody writing code. An agent runs on a remote machine with a file system, a terminal and network access. It installs dependencies, runs the tests, reads the errors and tries again. You do not talk to it at every step. You give it a goal.
What actually separates the third one
An AI that answers stops when you close the tab, because it had nothing to do between two questions. An agent on a remote machine carries on: the process lives on the machine, not in the browser. It is the only one of the three where shutting the laptop costs nothing.
The consequence is arithmetic. If one agent fits on one machine, two fit on two, and five on five. Work stops being capped by the number of terminals in front of you.
Where it breaks when there is more than one
Most tools answer by isolating: one agent, one machine, one branch, one merge at the end. That holds until two agents have changed the same file, and nobody knew until both had finished.
The other road is sharing with a rule. Agents live in one directory, and an agent claims a path before it writes to it. One holder per file, enforced by the server rather than politely asked of the model. That is the shape Murmell chose.
What to ask before you pick one
Who owns the machine, and what else is on it. How long it lives, and what survives it. What you pay for: the machine, the model tokens, or both. And whether the agent subscription you already have is reusable or has to be bought again.
On that last one the answer here is short: you connect the accounts you already pay for, and the bill covers the machine and the room. See what the canvas is.
Straight answers
What is the difference between cloud AI and local AI?
Local AI runs on your hardware: the weights are on your disk, the compute is on your card, nothing leaves. Cloud AI runs on somebody else's machine and you reach it over the network. The practical question is not speed, it is who owns the machine that stays switched on when you close your laptop.
Do I need a GPU to use cloud AI?
No. The model runs at the provider, and a cloud coding agent runs on a machine rented by the hour. A browser is enough, which is the whole point of the arrangement for anyone without dedicated hardware.
Where does my code go when a cloud AI agent reads it?
It is copied to the machine the agent runs on, and extracts go to the model while it works. Two places, two policies worth reading. On Murmell the machine that executes code holds no database and no decryption key, and the work is pushed to a private repository you own.