Find a file
A 37ae22ddb5
refactor: reduce complexity in Linode create_server and CLI dispatchCommand (#972)
Extract _linode_extract_error helper to deduplicate 3 inline Python
error-extraction blocks, and _linode_handle_create_error to reduce
create_server from 47 to 31 lines.

Extract dispatchListCommand, dispatchSubcommand, dispatchVerbAlias, and
dispatchSlashNotation from the 63-line dispatchCommand function, reducing
it to 15 lines with clear single-responsibility helpers.

Agent: complexity-hunter

Co-authored-by: A <6723574+louisgv@users.noreply.github.com>
Co-authored-by: Claude Haiku 4.5 <noreply@anthropic.com>
2026-02-13 10:58:40 -08:00
.claude fix: move CloudSigma region validation to API entry point and harden trigger-server issue param (#967) 2026-02-13 10:32:49 -08:00
.githooks Add guardrails: CLAUDE.md rules, hooks, pre-commit validation (#33) 2026-02-07 20:02:19 -08:00
.github refactor: Simplify security workflow to match discovery/refactor pattern (#929) 2026-02-13 05:26:21 -08:00
atlanticnet fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
aws-lightsail fix: improve error messages for GCP, AWS Lightsail, Cherry, and Oracle (#957) 2026-02-13 09:00:10 -08:00
binarylane fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
cherry refactor: decompose GCP and Cherry create_server functions (#965) 2026-02-13 10:15:47 -08:00
civo fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
cli refactor: reduce complexity in Linode create_server and CLI dispatchCommand (#972) 2026-02-13 10:58:40 -08:00
cloudsigma fix: move CloudSigma region validation to API entry point and harden trigger-server issue param (#967) 2026-02-13 10:32:49 -08:00
codesandbox fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
contabo fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
daytona refactor: decompose Daytona create_server and test_daytona_token into focused helpers (#939) 2026-02-13 06:46:13 -08:00
digitalocean fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
e2b fix: add actionable guidance to destroy_server failures and service timeouts (#959) 2026-02-13 09:38:58 -08:00
exoscale fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
fly fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
gcp refactor: decompose GCP ensure_gcloud and create_server into focused helpers (#964) 2026-02-13 10:19:19 -08:00
genesiscloud fix: json_escape SSH key names and fix GCP metadata injection (#958) 2026-02-13 09:03:35 -08:00
github-codespaces fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
hetzner fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
hostinger fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
hostkey fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
hyperstack fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
ionos fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
kamatera fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
koyeb fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
latitude fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
linode refactor: reduce complexity in Linode create_server and CLI dispatchCommand (#972) 2026-02-13 10:58:40 -08:00
local fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
modal refactor: replace Python with jq in Hetzner lib, fix /lab → /labs URLs (#827) 2026-02-12 23:14:11 -08:00
netcup fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
northflank fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
oracle fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
ovh fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
railway fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
ramnode fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
render fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
scaleway fix: add actionable guidance to error messages across 10 cloud providers (#962) 2026-02-13 10:10:45 -08:00
shared fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
sprite fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
test feat: add CloudSigma cloud provider (#860) 2026-02-13 06:50:25 -08:00
upcloud fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
vultr fix: add actionable guidance to agent installation failures across 126 scripts (#966) 2026-02-13 10:14:03 -08:00
.gitignore fix: address medium security findings from #753 (#755) 2026-02-12 15:48:52 -08:00
.shellcheckrc ci: add shellcheck linting infrastructure 2026-02-08 01:08:34 +00:00
CLAUDE.md feat: Add PR comment triage to security reviewer and refactor pr-maintainer (#940) 2026-02-13 06:25:45 -08:00
LICENSE Improve README with better intro, how-it-works, and dev guide (#51) 2026-02-08 18:16:46 +00:00
manifest.json feat: add CloudSigma cloud provider (#860) 2026-02-13 06:50:25 -08:00
README.md docs: Sync README matrix with manifest.json (#956) 2026-02-13 08:49:21 -08:00

Spawn

Launch any AI agent on any cloud with a single command. Coding agents, research agents, self-hosted AI tools — Spawn deploys them all. All models powered by OpenRouter. (ALPHA software, use at your own risk!)

15 agents. 36 clouds. 514 combinations. Zero config.

Install

curl -fsSL https://openrouter.ai/labs/spawn/cli/install.sh | bash

Or install directly from GitHub:

curl -fsSL https://raw.githubusercontent.com/OpenRouterTeam/spawn/main/cli/install.sh | bash

Usage

spawn                         # Interactive picker
spawn <agent> <cloud>         # Launch directly
spawn matrix                  # Show the full agent x cloud matrix

Examples

spawn                                    # Interactive picker
spawn claude sprite                      # Claude Code on Sprite
spawn aider hetzner                      # Aider on Hetzner
spawn claude sprite --prompt "Fix bugs"  # Non-interactive with prompt
spawn aider sprite -p "Add tests"        # Short form
spawn claude                             # Show clouds available for Claude

Commands

Command Description
spawn Interactive agent + cloud picker
spawn <agent> <cloud> Launch agent on cloud directly
spawn <agent> <cloud> --dry-run Preview without provisioning
spawn <agent> <cloud> -p "text" Non-interactive with prompt
spawn <agent> <cloud> --prompt-file f.txt Prompt from file
spawn <agent> Show available clouds for an agent
spawn matrix Full agent x cloud matrix
spawn list Show previously launched spawns
spawn agents List all agents
spawn clouds List all cloud providers
spawn update Check for CLI updates

Without the CLI

Every combination works as a one-liner — no install required:

bash <(curl -fsSL https://openrouter.ai/labs/spawn/{cloud}/{agent}.sh)

Non-Interactive Mode

Skip prompts by providing environment variables:

# OpenRouter API key (required for all agents)
export OPENROUTER_API_KEY=sk-or-v1-xxxxx

# Cloud-specific credentials (varies by provider)
export SPRITE_API_KEY=...        # For Sprite
export HCLOUD_TOKEN=...           # For Hetzner
export DO_API_TOKEN=...           # For DigitalOcean

# Run non-interactively
spawn claude sprite

You can also use inline environment variables:

OPENROUTER_API_KEY=sk-or-v1-xxxxx spawn claude sprite

Get your OpenRouter API key at: https://openrouter.ai/settings/keys

For cloud-specific auth, see each cloud's README in this repository.

Matrix

Sprite Hetzner Cloud DigitalOcean Vultr Linode (Akamai) AWS Lightsail GCP Compute Engine GitHub Codespaces CodeSandbox E2B Modal Fly.io Civo Scaleway Daytona UpCloud BinaryLane Latitude.sh OVHcloud Kamatera Cherry Servers Oracle Cloud Infrastructure Koyeb Northflank Railway Render IONOS Cloud Exoscale Contabo Hostinger Netcup Local Machine RamNode Atlantic.Net HOSTKEY CloudSigma
Claude Code
OpenClaw
NanoClaw
Aider
Goose
Codex CLI
Open Interpreter
Gemini CLI
Amazon Q CLI
Cline
gptme
OpenCode
Plandex
Kilo Code
Continue

How it works

Each cell in the matrix is a self-contained bash script that:

  1. Provisions a server on the cloud provider
  2. Installs the agent
  3. Injects your OpenRouter API key so every agent uses the same billing
  4. Drops you into an interactive session

Scripts work standalone (bash <(curl ...)) or through the CLI.

Development

git clone https://github.com/OpenRouterTeam/spawn.git
cd spawn
git config core.hooksPath .githooks

Structure

{cloud}/lib/common.sh    # Cloud provider primitives (provision, SSH, cleanup)
{cloud}/{agent}.sh        # Agent deployment script
shared/common.sh          # Shared utilities (OAuth, logging, SSH helpers)
cli/                      # TypeScript CLI (bun)
manifest.json             # Source of truth for the matrix

Adding a new cloud

  1. Create {cloud}/lib/common.sh with provisioning primitives
  2. Add to manifest.json
  3. Implement agent scripts using the cloud's primitives
  4. See CLAUDE.md for full contributor guide

Adding a new agent

  1. Add to manifest.json
  2. Implement on 1+ cloud by adapting an existing agent script
  3. Must support OpenRouter via env var injection

Contributing

The easiest way to contribute is by testing and reporting issues. You don't need to write code.

Test a cloud provider

Pick any agent + cloud combination from the matrix and try it out:

spawn claude hetzner      # or any combination

If something breaks, hangs, or behaves unexpectedly, open an issue using the bug report template. Include:

  • The exact command you ran
  • The cloud provider and agent
  • What happened vs. what you expected
  • Any error output

Request a cloud or agent

Want to see a specific cloud provider or agent supported? Use the dedicated templates:

Requests with real-world use cases get prioritized.

Report auth or credential issues

Cloud provider APIs change frequently. If you hit authentication failures, expired tokens, or permission errors on a provider that previously worked, please report it — these are high-priority fixes.

Code contributions

See CLAUDE.md for the full contributor guide covering shell script rules, testing, and the shared library pattern.

License

Apache 2.0