vrr/spawn
2
0
Fork 0
mirror of https://github.com/OpenRouterTeam/spawn.git synced 2026-04-30 12:59:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10
spawn/runpod
History
L 0708ff1700
fix: Use robust OpenCode install method across all clouds (#48) 
The upstream OpenCode installer pipes `curl -# -L | tar xz` which fails
in container exec environments (Sprite, E2B, Modal, Daytona) where the
binary stream gets corrupted through the exec layer, producing
"gzip: stdin: not in gzip format" errors.

Added opencode_install_cmd() to shared/common.sh that downloads the
binary to a file first, then extracts it. Updated all 17 opencode.sh
scripts to use this robust method instead of the upstream installer.

The previous fix (#44) only addressed Sprite with a hardcoded
linux-x86_64 architecture. This fix detects OS/arch dynamically and
applies to all cloud providers.

Fixes #42

Co-authored-by: Sprite <noreply@sprite.dev>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-02-07 23:02:18 -08:00
..
lib Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
aider.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
amazonq.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
claude.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
cline.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
codex.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
gemini.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
goose.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
gptme.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
interpreter.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
nanoclaw.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
openclaw.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
opencode.sh fix: Use robust OpenCode install method across all clouds (#48) 2026-02-07 23:02:18 -08:00
plandex.sh Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00
README.md Add RunPod GPU cloud provider (#39) 2026-02-07 21:43:10 -08:00

README.md

RunPod

RunPod GPU cloud pods via GraphQL API. RunPod

Prerequisites

  1. A RunPod account with API key from Settings
  2. SSH public key added to your RunPod account (same settings page)

Agents

Claude Code

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

OpenClaw

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

NanoClaw

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

Aider

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

Goose

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

Codex CLI

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

Open Interpreter

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

Gemini CLI

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

Amazon Q CLI

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

Cline

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

gptme

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

OpenCode

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

Plandex

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

Non-Interactive Mode

RUNPOD_SERVER_NAME=dev-gpu \
RUNPOD_API_KEY=your-api-key \
OPENROUTER_API_KEY=sk-or-v1-xxxxx \
  bash <(curl -fsSL https://openrouter.ai/lab/spawn/runpod/claude.sh)

Environment Variables

Variable Description Default
RUNPOD_API_KEY RunPod API key (prompted)
RUNPOD_SERVER_NAME Pod name (prompted)
RUNPOD_GPU_TYPE GPU type ID NVIDIA RTX A4000
RUNPOD_GPU_COUNT Number of GPUs 1
RUNPOD_IMAGE Docker image runpod/pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04
RUNPOD_VOLUME_GB Persistent volume size (GB) 50
RUNPOD_CONTAINER_DISK_GB Container disk size (GB) 20
RUNPOD_CLOUD_TYPE Cloud type (ALL, COMMUNITY, SECURE) ALL
OPENROUTER_API_KEY OpenRouter API key (prompted via OAuth)

Notes

  • RunPod is a GPU cloud provider -- pods come with NVIDIA GPUs and CUDA pre-installed
  • SSH keys must be added via the RunPod web console (not via API)
  • Pods use Docker containers; base tools are installed automatically on first run
  • SSH access is via direct TCP port mapping or RunPod's SSH proxy