Computer control from the CLI
Turn any machine into a Nebula local device with one command — set the working folder, choose whether agents can run commands, and manage the daemon.
nebula-ai local-device enable turns the machine you're on into a local device your agents can use. It's the headless counterpart to the desktop app's Computer Control — same result, no window required, which is what makes it the right tool for a server or a dev box you reach over SSH.
What enabling does
One command does four things, in this order.
Signs you in, if you aren't already.
Uses the folder you ran it from as the working folder. Pass --primary-folder <path> to point somewhere else.
Registers this machine as a device in your active workspace.
Starts the daemon that lets agents reach it.
Run it from the directory you actually want agents working in. It takes the current directory silently, so cd first.
A local device is private to whoever registered it. Nobody else in the workspace can see it or send work to it — not even the workspace owner.
Whether agents can run commands
Registering a device and letting agents execute commands on it are two separate decisions.
| host | none | |
|---|---|---|
| Agents can run commands | Yes | — |
| Files in the working folder | Yes | Yes |
| Set with | local-device exec-mode set host | local-device exec-mode set none |
| Best when | It's your own dev machine | You want file access without a shell |
nebula-ai local-device exec-mode get prints the current mode. A running daemon picks a change up on its own — you don't need to restart it.
Managing the daemon
nebula-ai local-device status reports whether computer control is on, which workspace the device belongs to, and whether the daemon is running.
start, stop, and restart do what they say. nebula-ai local-device logs shows what the daemon has been doing.
nebula-ai local-device disable turns computer control off and stops the daemon, leaving the device registered. uninstall goes further and removes the device too.
The daemon runs only while computer control is on. It does not reinstall itself as a system service and does not survive a reboot — start it again after one, or re-run enable.
Changing the working folder
The working folder is where agents read and write by default.
Nebula calls this the same thing in different places — the desktop app's settings window says Primary folder where the CLI says working folder. They're one setting.
Agents can also move themselves within a thread using their own working-directory tool, which is separate from this machine-level default.
Related
Nebula CLI
Run Nebula from your terminal. Install the nebula-ai CLI, sign in once, and use the full-screen app to chat, join calls, and drive your workspace.
Command reference
Every nebula-ai command in one table, plus the global flags, JSON output for scripting, shell completion, and where to find the logs.