vrr/spawn
2
0
Fork 0
mirror of https://github.com/OpenRouterTeam/spawn.git synced 2026-05-06 08:10:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8
spawn/hyperstack/README.md
A 79562bbfcf
fix: Fix broken gptme script and update READMEs for Railway, Northflank, Hyperstack (#226) 
- Fix railway/gptme.sh calling nonexistent inject_env_vars_railway (should be inject_env_vars)
- Railway README: add missing NanoClaw and gptme agent entries
- Northflank README: add missing NanoClaw, Goose, Codex CLI, Open Interpreter, Gemini CLI agent entries and Environment Variables table
- Hyperstack README: restructure to match standard format with Agents section, use openrouter.ai/lab/spawn URLs instead of raw GitHub URLs, add 6 missing agents (Amazon Q, Cline, gptme, OpenCode, Plandex, Kilo Code), add Environment Variables table and Non-Interactive Mode section

Agent: ux-engineer

Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-02-10 12:35:56 -08:00

4.8 KiB
Raw Blame History

Hyperstack

Hyperstack GPU cloud via REST API. Hyperstack

Hyperstack (formerly NexGen Cloud) offers NVIDIA GPUs with pay-per-minute billing.

Agents

Claude Code

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/claude.sh)

OpenClaw

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/openclaw.sh)

NanoClaw

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/nanoclaw.sh)

Aider

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/aider.sh)

Goose

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/goose.sh)

Codex CLI

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/codex.sh)

Open Interpreter

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/interpreter.sh)

Gemini CLI

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/gemini.sh)

Amazon Q CLI

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/amazonq.sh)

Cline

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/cline.sh)

gptme

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/gptme.sh)

OpenCode

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/opencode.sh)

Plandex

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/plandex.sh)

Kilo Code

bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/kilocode.sh)

Setup

1. Get Hyperstack API Key

  1. Sign up at Hyperstack Infrahub
  2. Navigate to Settings -> API Keys
  3. Create a new API key
  4. Copy the API key

2. Set Environment Variable

export HYPERSTACK_API_KEY="your-api-key-here"

Or the script will prompt you and save it to ~/.config/spawn/hyperstack.json.

3. Choose an Environment

Hyperstack organizes resources by "environments" (e.g., default-CANADA-1, default-EU-1). The script will:

  • Use HYPERSTACK_ENVIRONMENT if set
  • Otherwise, fetch available environments and prompt you to choose

List available environments:

curl -H "api_key: YOUR_API_KEY" \
  https://infrahub-api.nexgencloud.com/v1/core/environments | jq '.environments[] | {name, region}'

Non-Interactive Mode

HYPERSTACK_API_KEY=your-key \
HYPERSTACK_ENVIRONMENT=default-CANADA-1 \
HYPERSTACK_VM_NAME=my-vm \
OPENROUTER_API_KEY=sk-or-v1-xxxxx \
  bash <(curl -fsSL https://openrouter.ai/lab/spawn/hyperstack/claude.sh)

Environment Variables

Variable Description Default
HYPERSTACK_API_KEY API key from Hyperstack Infrahub (required)
HYPERSTACK_ENVIRONMENT Environment name (prompted)
HYPERSTACK_FLAVOR VM flavor/size n1-cpu-small
HYPERSTACK_IMAGE OS image Ubuntu Server 24.04 LTS R5504 UEFI
HYPERSTACK_VM_NAME Custom VM name (prompted)
HYPERSTACK_SSH_KEY_NAME SSH key name spawn-key-$(whoami)
OPENROUTER_API_KEY OpenRouter API key (OAuth or prompted)

Available Flavors

To list available VM flavors:

curl -H "api_key: YOUR_API_KEY" \
  https://infrahub-api.nexgencloud.com/v1/core/flavors | jq '.flavors[] | {name, cpu, ram, gpu}'

Common flavors:

  • n1-cpu-small - 1 vCPU, 2GB RAM
  • n1-cpu-medium - 2 vCPU, 4GB RAM
  • n1-cpu-large - 4 vCPU, 8GB RAM
  • GPU flavors with RTX A6000, A100, H100, etc.

Available Images

To list available OS images:

curl -H "api_key: YOUR_API_KEY" \
  https://infrahub-api.nexgencloud.com/v1/core/images | jq '.images[] | {name, version}'

Pricing

Hyperstack uses pay-per-minute billing for on-demand instances. Pricing is calculated per GPU per hour.

Example pricing (subject to change):

  • RTX A6000 (48GB): $0.50/hour on-demand, $0.35/hour reserved
  • Reserved instances offer ~30% savings over on-demand

Check current pricing at Hyperstack Pricing or via the API pricebook endpoints.

Troubleshooting

API Key Invalid

If you see authentication errors:

  1. Verify your API key at https://infrahub.hyperstack.cloud
  2. Ensure the key has proper permissions (not read-only)
  3. Check that the key hasn't been revoked

Environment Not Found

If the environment name is invalid:

  1. List available environments: curl -H "api_key: KEY" https://infrahub-api.nexgencloud.com/v1/core/environments
  2. Use the exact name from the API response (case-sensitive)
  3. Set HYPERSTACK_ENVIRONMENT to the correct name

VM Creation Fails

Common issues:

  • Insufficient quota in the selected environment
  • Flavor not available in the selected region
  • SSH key name conflicts with existing key
  • Invalid security rules