The control plane stays one process (houdry serve). Each extra GPU box is another worker.

On the new workstation:

curl -fsSL https://github.com/houdry-genomex/houdry/releases/latest/download/install.sh | sh
export PATH="$HOME/.houdry/bin:$PATH"
houdry gpu detect
houdry gpu register

Windows: install.ps1, then houdry.exe gpu detect and gpu register.

If discovery fails:

houdry gpu register --server http://HOST:8080

Leave register running. Ctrl+C drains, waits for the current job, then leaves.

Agent does not need a reinstall. model=auto will start using the new READY node when it scores better for a task.

Check:

houdry node list --server http://127.0.0.1:8080