> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cadenzalabs.xyz/llms.txt
> Use this file to discover all available pages before exploring further.
# Introduction
> What Cadenza CLI is and how the pieces fit together.
**Cadenza CLI** is a command-line platform for physical-AI developers. You scaffold a
robotics project, describe a multi-phase mission as JSON, run it in simulation,
and turn the logged rollouts into fine-tuning data for a vision-language-action
(VLA) policy, all from one binary called `cadenza`.
It pairs with the **[Cadenza SDK](/sdk/introduction)** (`cadenza-lab`), the Python
library that provides the simulator, robots, action library, and inference stack
the CLI drives under the hood.
## What you can do
`mkdir` / `env init` generate a project with an `env.json` mission spec.
`env run` executes a phase-aware mission, logs every tick, and scores it.
`env action` creates reusable robot actions, synced to your account.
`env finetune` / `env lora` turn rollouts into VLA training data and adapters.
`env residual` / `env distill` adapt a frozen base, then shrink it for onboard.
`env vla` runs the governed GRD loop over a standalone model's LoRA adapter.
Every learned artifact passes a `DEPLOY \| BLOCK \| NEEDS_DATA` gate with rollback.
## How it runs
The `cadenza` binary works two ways:
* **Interactive shell.** Run `cadenza` with no arguments to get a persistent
prompt with tab-completion. Press `Ctrl+C` to exit.
* **Scriptable.** Pass a command as arguments (`cadenza env run my-project --headless`)
to execute it once and exit. This is what you use in scripts and CI.
Every example in these docs works in either mode. Inside the shell, drop the
leading `cadenza`.
Simulation and fine-tuning features depend on optional extras (`gym`, `lora`).
See [Configuration](/cli-setup/configuration).
## Next steps