Find the guidance you need.

Getting started

Four steps from one install command to a first Fleet workflow. Every step states only what the current candidate actually does; anything unreleased or unrecorded is labeled as such.

1. 01

   Install Codewhale

   One npm command installs the dispatcher and terminal runtime. Cargo, archives, Docker, Nix, and China mirrors are documented alternatives — published releases only.

   npm install -g codewhale
   codewhale doctor

   Full install guide →
2. 02

   Open a first session — no key needed

   Launches without any API key: short constitution-first setup, then the full interface. Explore in Plan mode — always read-only. Model replies need a provider; that's the next step.

   codewhale

   Learn the product nouns first →
3. 03

   Connect a provider

   Pick a supported route — hosted key, gateway, or keyless local runtime (Ollama, vLLM, SGLang). Provider and model stay explicit; reasoning and routing provenance stay separate, and unavailable values stay unavailable.

   codewhale auth set --provider deepseek

   Providers and models →
4. 04

   Run a first Fleet workflow

   For durable workers, ordered phases, or receipts, author a reusable agent-team profile and launch a run. Fleet state lives in the workspace ledger; ordinary single tasks need none of this.

   codewhale fleet init
   codewhale fleet run tasks.json --max-workers 4

   Fleet and Workflow docs →

Watch a real session

Below is the real-session media slot. It is deliberately in the pending state: until the v0.9.2 candidate dogfood recording exists, this site shows no placeholder or staged footage.

Where next