@prismshadow/penguin-cli

The PenguinHarness command line. Installs the penguin command: an interactive REPL, a one-shot task runner, model / vault configuration, and the launcher for the Web service.

npm install -g @prismshadow/penguin-cli   # requires Node >= 24

penguin web        # start the Web service and open http://127.0.0.1:7364
penguin server     # same service, headless

penguin config model add --model-id deepseek-v4-pro --api-key sk-... --set-default

penguin run -m "Create hello.txt containing Hello, Penguin"    # one Task, then exit
penguin chat                                                   # REPL: /compact, /clear, /exit, Ctrl-C interrupts
penguin chat --resume                                          # resume the latest session

Tool calls go through an approval gate — --approve allow-all (default) | deny-all | read-only | always-ask. Data lives under ~/.penguin/data (PENGUIN_HOME or --root override); model credentials come from the Project config or provider env vars (e.g. DEEPSEEK_API_KEY).

Prefer a one-line install with a bundled Node runtime? See Quickstart → CLI and Web App.

Documentation

• Quickstart
• CLI Reference
• Configuration Reference

Development

pnpm penguin <args>                              # run from source (repo root, via tsx)
pnpm --filter @prismshadow/penguin-cli build     # tsup → dist/index.js (the penguin bin)
pnpm --filter @prismshadow/penguin-cli typecheck
pnpm --filter @prismshadow/penguin-cli test

Part of PenguinHarness · Apache-2.0