A new workspace is a complete Ubuntu desktop with a working graphics card: the driver, the desktop itself, a terminal, a file manager, and everything the card needs to be used by anything you install.
Nobody has chosen a toolchain for you. The applications are yours to pick.
Installing things
Two ways, and both are ordinary.
The applications list. The workspace has a catalog of the things people usually want — ComfyUI, JupyterLab, PyTorch, Ollama, vLLM, LangChain, the AI Toolkit, Axolotl, Chrome, VS Code — and installs any of them for you. One action, and it handles the parts that usually go wrong: the right build for the card, the environment around it, a way to start it.
Some of them are large. Installing anything that brings PyTorch with it pulls gigabytes and takes a while, so you are asked before it starts rather than left watching a progress bar you did not expect.
Everything else, yourself. It is your machine. apt, pip, conda, a tarball from somewhere, a git checkout you build — all of it works, and none of it is second class. Nothing about Hinode expects you to stay inside a list.
Carrying it to other machines
What you install on the workspace can be captured and used as the starting point for machines you attach later, so a machine you add for a big job already has your tools and your settings. You take that snapshot when you want one; new machines start from the newest.
Anything you install on a machine that was attached from a snapshot stays on that machine, and goes when the machine does. If it is worth keeping, install it on the workspace and take a new snapshot.
Where to put big files
Models, datasets and output belong in the shared folder, which every machine in the workspace sees and which no machine deletion touches. Environments, checkouts and anything made of many small files belong in your home folder, where they are fast.