Install HyperAI

Get HyperAI running on your server in under 5 minutes. You need Docker and a Proxmox server with API access.

Prerequisites

HyperAI does NOT need to run on the same machine as Proxmox. It connects via the Proxmox REST API over the network.

Quick Start (recommended)

One command does everything — downloads config, prompts for your license key, generates secrets, and starts HyperAI:

curl -fsSL https://hyperai.dev/install.sh | bash

The installer will:

Want to inspect the script first? View install.sh — it's ~150 lines with no surprises.

Manual install

If you prefer to do it yourself:

1

Get your license key 1 min

Register on our website to get a free license key (HYPR-xxx).

2

Download and configure 1 min

mkdir hyperai && cd hyperai
curl -o docker-compose.yml https://hyperai.dev/install/docker-compose.yml

cat > .env <<EOF
HYPERAI_LICENSE_KEY=HYPR-your-key-here
SESSION_SECRET=$(openssl rand -hex 32)
ANTHROPIC_API_KEY=
EOF
3

Start 30 sec

docker compose up -d
4

Open the dashboard 1 min

Open http://your-server-ip:3000 in your browser.

  1. Register — create your admin account
  2. An organization is created for you automatically
  3. Go to Settings → Hosts → Add Host
6

Connect your Proxmox 2 min

You need a Proxmox API token. On your Proxmox server:

# SSH into your Proxmox host, then:
pvesh create /access/users/root@pam/token/hyperai --privsep 0

# Output:
# ┌──────────────┬──────────────────────────────────────┐
# │ full-tokenid │ root@pam!hyperai                     │
# │ value        │ xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx │
# └──────────────┴──────────────────────────────────────┘

Back in HyperAI, fill in:

  • Name: anything (e.g. "Production")
  • Hostname: your Proxmox IP or domain (e.g. 192.168.1.100)
  • Port: 8006 (default)
  • API Token ID: root@pam!hyperai
  • API Token Secret: the value from the command above
  • Node Name: your Proxmox node name (shown in the Proxmox UI top-left, e.g. pve)

Click Test Connection — if it shows a green checkmark, click Save.

7

Done! 🎉

Your VMs should now appear in the dashboard. You can:

  • Start, stop, and reboot VMs
  • View real-time metrics and historical charts
  • Set up alert rules for CPU, memory, etc.
  • Press ⌘K to search VMs
  • Press ⌘J to open AI chat (requires Pro + Anthropic key)
  • Invite team members under Settings → Members

Setting up AI features (Pro plan)

AI features require a Pro license and an Anthropic API key (BYOK — Bring Your Own Key).

  1. Go to console.anthropic.com and create an account
  2. Generate an API key under API Keys
  3. Add credits to your Anthropic account ($5 is plenty to start)
  4. Add the key to your .env file: 
    ANTHROPIC_API_KEY=sk-ant-api03-your-key-here
  5. Restart HyperAI: docker compose restart hyperai
  6. Press ⌘J in the dashboard — try "List all running VMs"
AI requests cost ~$0.03 each with Claude Haiku. 100 requests/day ≈ $3/day. You control your spend via your Anthropic account.

Updating HyperAI

docker compose pull
docker compose up -d

Database migrations run automatically on startup. Your data is preserved.

Optional: HTTPS with reverse proxy

For production, put HyperAI behind a reverse proxy with SSL. Example with Caddy (auto-HTTPS):

# Install Caddy, then create /etc/caddy/Caddyfile:
hyperai.yourdomain.com {
    reverse_proxy localhost:3000
}
sudo systemctl restart caddy

Caddy automatically obtains and renews Let's Encrypt certificates.

Update your .env to allow the new origin:

ALLOWED_ORIGINS=https://hyperai.yourdomain.com

Troubleshooting

Container won't start

Check logs: docker compose logs hyperai

Common issues:

Can't connect to Proxmox

AI not working

Need help?

Email us at support@ll-creative.de — we typically respond within 48 hours (24h for Pro Managed customers).