/amc-setup-calibration-stack

name: "amc-setup-calibration-stack"
description: "Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key."
metadata:
  author: "NVIDIA CORPORATION"
  tags: [amc, deepstream, docker, calibration, setup, ngc]
owner: "NVIDIA CORPORATION"
service: "auto-magic-calib"
version: "1.0.0"
reviewed: "2026-04-28"
license: "Apache-2.0"

Skill: Launch AutoMagicCalib Release Containers

Set up the AutoMagicCalib microservice and UI from release containers: resolve an AMC checkout, authenticate to NGC, optionally download VGGT, configure Docker Compose, launch services, and verify readiness.

Prerequisites

• Docker and Docker Compose installed
• NVIDIA Docker Runtime configured (for GPU support)
• `auto-magic-calib` repo on disk. Step 0b resolves the current repo, DeepStream `tools/auto-magic-calib`, `DEEPSTREAM_REPO_ROOT`, or `~/auto-magic-calib`; otherwise it asks before cloning `https://github.com/NVIDIA-AI-IOT/auto-magic-calib`.
• NGC account with access to NVIDIA container registry
• Docker runnable without `sudo`; verify with `docker ps` before continuing.

Instructions

Step 0: Verify Docker Runs Without sudo

docker ps

• If it succeeds → continue.
• If it fails with "permission denied" → the user is not in the `docker` group. Ask the user to run:

  sudo usermod -aG docker $USER && newgrp docker

Then ask the user to confirm `docker ps` works before continuing.

> **Agent note**: If `docker ps` cannot be run from within the agent sandbox, ask the user to confirm it works (e.g. "Can you confirm `docker ps` runs without sudo?") before proceeding.

Step 0b: Resolve Repo Checkout

The skill needs AMC repo assets (`compose/`, sample data, and `models/`). Resolve an existing checkout first; ask before cloning into `~/auto-magic-calib`.

REPO_URL="https://github.com/NVIDIA-AI-IOT/auto-magic-calib.git"
DEFAULT_CLONE_DIR="$HOME/auto-magic-calib"
CURRENT_GIT_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || true)"

is_amc_checkout() {
  [ -n "$1" ] \
    && [ -f "$1/README.md" ] \
    && grep -q "AutoMagicCalib" "$1/README.md" 2>/dev/null \
    && [ -f "$1/compose/compose.yml" ] \
    && grep -q "auto-magic-calib-ms" "$1/compose/ms/compose.yml" 2>/dev/null \
    && grep -q "auto-magic-calib-ui" "$1/compose/ui/compose.yml" 2>/dev/null
}

REPO_ROOT=""
for candidate in \
  "$CURRENT_GIT_ROOT" \
  "${CURRENT_GIT_ROOT:+$CURRENT_GIT_ROOT/tools/auto-magic-calib}" \
  "${DEEPSTREAM_REPO_ROOT:+$DEEPSTREAM_REPO_ROOT/tools/auto-magic-calib}" \
  "$PWD/tools/auto-magic-calib" \
  "$DEFAULT_CLONE_DIR"; do
  if is_amc_checkout "$candidate"; then
    REPO_ROOT="$candidate"
    echo "✓ Using auto-magic-calib checkout: $REPO_ROOT"
    break
  fi
done

if [ -z "$REPO_ROOT" ]; then
  if [ -n "$CURRENT_GIT_ROOT" ] && [ -d "$CURRENT_GIT_ROOT/tools/auto-magic-calib" ]; then
    echo "Found $CURRENT_GIT_ROOT/tools/auto-magic-calib, but it is not an initialized AMC checkout."
    echo "If running from the DeepStream repository root:"
    echo "  git submodule update --init tools/auto-magic-calib"
  fi

  # Nothing usable on disk — STOP and ask the user for confirmation using the
  # host's question mechanism; if none is available, ask in chat and wait.
  # Do NOT clone silently from this block or clone over a tracked submodule path.
  echo "No usable auto-magic-calib checkout found. Ask the user for confirmation:"
  echo "  Clone $REPO_URL into $DEFAULT_CLONE_DIR? [y/N]"
  echo "On 'y' — run: git clone \"$REPO_URL\" \"$DEFAULT_CLONE_DIR\""
  exit 1
fi

cd "$REPO_ROOT"
export REPO_ROOT
echo "REPO_ROOT=$REPO_ROOT"

> **Agent note**: never clone silently. Prefer initialized DeepStream `tools/auto-magic-calib`; do not clone over that submodule path. If it exists but is empty, ask the user to run `git submodule update --init tools/auto-magic-calib`. Honour an alternate AMC path if provided.

Step 0c: Install Python venv (New Systems Only)

On a fresh system, `pip` and `python3-venv` may not be available. Install them first:

# Create a venv for HuggingFace CLI (project-local preferred)
REPO_DIR="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
HF_VENV="${REPO_DIR}/venv"
python3 -m venv "$HF_VENV" 2>/dev/null || {
  echo "ERROR: python3-venv not available." >&2
  echo "Install it manually: sudo apt install -y python3-venv python3-pip" >&2
  exit 1
}

# Install HuggingFace hub (needed for VGGT download)
"$HF_VENV/bin/pip" install --upgrade pip huggingface_hub

> **Note**: Skip this step if a venv with `hf` already exists (check `venv/bin/hf` in the repo root or `~/venv/amc/bin/hf`).

Step 1: Login to NGC

Ask the user for their NGC API key using the host's question mechanism; if none is available, ask in chat and wait. Then run:

echo "<NGC_API_KEY>" | docker login nvcr.io --username '$oauthtoken' --password-stdin
echo "✓ NGC authentication complete"

Step 2: Download VGGT Model (If Not Already Present)

export REPO_ROOT=$(git rev-parse --show-toplevel)
cd "$REPO_ROOT"

if [ -f "models/vggt/vggt_1B_commercial.pt" ]; then
  echo "✓ VGGT model already present"
else
  echo "✗ VGGT model not found"
  echo "Options:"
  echo "  1. Continue without VGGT (AMC only - sufficient for most use cases)"
  echo "  2. Download VGGT model (~4.7GB, requires HuggingFace account)"
fi

**To download VGGT**: ask the user to accept the license at https://huggingface.co/facebook/VGGT-1B-Commercial and provide a read token from https://huggingface.co/settings/tokens using the host's question mechanism. Pass it through `HF_TOKEN` so it is not exposed in `ps` output:

REPO_DIR="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
cd "$REPO_DIR"

# Find the HuggingFace CLI binary (named 'hf', not 'huggingface-cli')
HF_BIN="$(find "$REPO_DIR/venv" ~/venv/