First-run setup

First-run setup is a terminal TUI: hal0 setup. It detects your hardware, picks a coherent set of slots, models, and extensions, and provisions them — no browser required. hal0 ships with no default model stack by design; setup is where you choose one (or skip and configure manually later).

hal0 setup

Note

The installer runs hal0 setup --auto --no-pull --no-extensions to seed the hardware-recommended slot and write the first-run sentinel (/var/lib/hal0/.first_run_done) non-destructively — only slots whose config is absent. Re-running hal0 setup interactively afterwards lets you pull models and enable extensions. The web dashboard no longer hosts a first-run picker; it shows a banner pointing you at the terminal.

The flow

hal0 setup is a two-column terminal app: an interactive picker on the left over an always-on context pane (detected RAM, GPU, NPU) on the right. It walks:

1. Model storage — the directory every slot container reads and writes model files to. Defaults to /var/lib/hal0/models; override with --storage-dir.

2. Extensions — opt-in apps and agents, auto-wired on apply:

   Extension	Kind	Default
   Open WebUI	app	on
   ComfyUI	app (image/video, iGPU)	on
   Hermes	agent (conversational, with memory)	on
   Pi	agent (coding)	off

3. Main model — the chat model for the chat slot, anchored to a hardware-fit tier (see below).

4. Agent model — the model backing the bundled agent slot.

5. NPU — when an AMD XDNA NPU + FastFlowLM are present, enable the NPU trio (chat + STT + embed passengers on one flm serve).

Setup then applies your selection — in-process when run at install time, or via the running API (POST /api/install/apply-selections) when the daemon is up — creating the slot containers in OFFLINE and seeding background model pulls. It writes the first-run sentinel on completion.

Hardware-anchored tiers

The main-model step is anchored to four tiers; the highest that fits your detected memory is recommended, and tiers that exceed your pool are flagged.

Tier	Fits
hal0-Lite	smaller hosts — a tiny chat model only
hal0-Default	mid-range — chat + embed/rerank + voice
hal0-Pro	larger unified memory — adds a coder model + image generation
hal0-Max	high-memory Strix Halo — adds the NPU trio

Flags

Flag	Effect
--auto	Non-interactive; apply the recommended defaults.
--storage-dir <path>	Model storage directory (default /var/lib/hal0/models).
--no-pull	Create slots + write the sentinel, but download nothing.
--no-extensions	Skip extensions (under --auto).

Configure manually instead

Prefer to wire things up yourself? Skip setup and add slots and models directly — see Load your first model.

Next

Load your first model Pull a model from Hugging Face and assign it to a slot, via setup or the CLI.