* feat: fall back to SigV4 REST API when AWS CLI is absent (aws/lightsail) If `aws` CLI is not installed but AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY are set, provision Lightsail instances directly via the REST API instead of erroring out. - Add _lightsail_rest(): inline Bun TypeScript that computes SigV4 signatures via node:crypto and calls the Lightsail API with native fetch — no openssl or curl gymnastics required - Add _ls_json(): dot-path JSON parser, prefers jq, falls back to bun eval - ensure_aws_cli() now sets LIGHTSAIL_MODE=cli|rest; REST mode requires bun (already a project dependency) and shows a clear error if missing - All API calls in ensure_ssh_key, create_server, _wait_for_lightsail_instance, destroy_server, list_servers are gated on LIGHTSAIL_MODE - Replace all python3 JSON encoding (key import, userdata, list table) with bun eval — consistent with project tooling - No more auto-install of the 200 MB AWS CLI binary Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat: add interactive AWS CLI install when CLI is missing When neither aws CLI nor raw credentials are found, prompt the user to install AWS CLI v2 on the spot (macOS .pkg / Linux zip installer). After install, prompt for Access Key ID + Secret and validate via sts:GetCallerIdentity before proceeding. The decision cascade is now: 1. Existing aws CLI with valid creds → cli mode 2. Raw env-var creds + bun available → rest mode 3. Offer to install aws CLI → prompt for creds → cli mode 4. Creds collected during install + bun → rest mode fallback 5. Nothing worked → show manual instructions Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: eliminate code/path injection in bun eval calls (aws/lib/common.sh) Pass shell variables as process.argv arguments instead of interpolating them into JavaScript string literals: - _ls_json(): path parameter passed as process.argv[2] (was CRITICAL code injection — attacker-controlled path could escape the string) - ensure_ssh_key(): pub_path and key_name passed as process.argv[2..3] (was HIGH — path injection via $HOME) - create_server(): ud_tmp, name, az, bundle passed as process.argv[2..5] (was MEDIUM — temp file path interpolation) Agent: pr-maintainer Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude <claude@anthropic.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> Co-authored-by: B <6723574+louisgv@users.noreply.github.com> |
||
|---|---|---|
| .claude | ||
| .githooks | ||
| .github | ||
| assets | ||
| aws | ||
| cli | ||
| daytona | ||
| digitalocean | ||
| fly | ||
| gcp | ||
| hetzner | ||
| local | ||
| shared | ||
| sprite | ||
| test | ||
| .gitignore | ||
| .shellcheckrc | ||
| CLAUDE.md | ||
| LICENSE | ||
| manifest.json | ||
| README.md | ||
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!)
6 agents. 8 clouds. 48 working 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 codex hetzner # Codex CLI on Hetzner
spawn claude sprite --prompt "Fix bugs" # Non-interactive with prompt
spawn codex sprite -p "Add tests" # Short form
spawn claude # Show clouds available for Claude
spawn delete # Delete a running server
spawn delete -c hetzner # Delete a server on Hetzner
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> <cloud> --debug |
Show all commands being executed |
spawn <agent> |
Show available clouds for an agent |
spawn <cloud> |
Show available agents for a cloud |
spawn matrix |
Full agent x cloud matrix |
spawn list |
Browse and rerun previous spawns |
spawn list <filter> |
Filter history by agent or cloud name |
spawn list -a <agent> |
Filter history by agent |
spawn list -c <cloud> |
Filter history by cloud |
spawn list --clear |
Clear all spawn history |
spawn last |
Instantly rerun the most recent spawn |
spawn agents |
List all agents with descriptions |
spawn clouds |
List all cloud providers |
spawn update |
Check for CLI updates |
spawn delete |
Interactively select and destroy a cloud server |
spawn delete -a <agent> |
Filter servers to delete by agent |
spawn delete -c <cloud> |
Filter servers to delete by cloud |
spawn help |
Show help message |
spawn version |
Show version |
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)
# Note: Sprite uses `sprite login` for authentication
export HCLOUD_TOKEN=... # For Hetzner
export DO_API_TOKEN=... # For DigitalOcean
# Run non-interactively
spawn claude hetzner
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.
Troubleshooting
Installation issues
If spawn fails to install, try these steps:
-
Check bun version: spawn requires bun >= 1.2.0
bun --version bun upgrade # if needed -
Manual installation: If auto-install fails, install bun first
curl -fsSL https://bun.sh/install | bash source ~/.bashrc # or ~/.zshrc for zsh curl -fsSL https://raw.githubusercontent.com/OpenRouterTeam/spawn/main/cli/install.sh | bash -
PATH issues: If
spawncommand not found after install# Add to your shell config (~/.bashrc or ~/.zshrc) export PATH="$HOME/.local/bin:$PATH"
Agent launch failures
If an agent fails to install or launch on a cloud:
-
Check credentials: Ensure cloud provider credentials are set
# Example for Hetzner export HCLOUD_TOKEN=your-token-here spawn claude hetzner -
Try a different cloud: Some clouds may have temporary issues
spawn <agent> # Interactive picker to choose another cloud -
Use --dry-run: Preview what spawn will do before provisioning
spawn claude hetzner --dry-run -
Check cloud status: Visit your cloud provider's status page
- Many failures are transient (network timeouts, package mirror issues)
- Retrying often succeeds
Getting help
- View command history:
spawn listshows all previous launches - Rerun last session:
spawn lastorspawn rerun - Check version:
spawn versionshows CLI version and cache status - Update spawn:
spawn updatechecks for the latest version - Report bugs: Open an issue at https://github.com/OpenRouterTeam/spawn/issues
Matrix
| Local Machine | Hetzner Cloud | Fly.io | AWS Lightsail | Daytona | DigitalOcean | GCP Compute Engine | Sprite | |
|---|---|---|---|---|---|---|---|---|
| Claude Code | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| OpenClaw | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| ZeroClaw | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Codex CLI | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| OpenCode | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| Kilo Code | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
How it works
Each cell in the matrix is a self-contained bash script that:
- Provisions a server on the cloud provider
- Installs the agent
- Injects your OpenRouter API key so every agent uses the same billing
- 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
- Create
{cloud}/lib/common.shwith provisioning primitives - Add to
manifest.json - Implement agent scripts using the cloud's primitives
- See CLAUDE.md for full contributor guide
Adding a new agent
- Add to
manifest.json - Implement on 1+ cloud by adapting an existing agent script
- 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.