> ## 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.
# What we provide
> The full stack Cadenza Labs gives physical-AI teams, end to end.
Cadenza is built as one stack with layers you can enter at any point. The same
physics core, action library, and policy interface run from your first one-liner
to a deployed robot.
## The stack at a glance
```mermaid theme={null}
flowchart LR
A["Project
env.json mission spec"] --> B["Simulation
MuJoCo physics core"]
B --> C["Rollouts
logged + scored"]
C --> D["Fine-tuning
VLA data + LoRA"]
D --> E["Deploy
Go1 / G1 hardware"]
E --> B
```
## What's included
A MuJoCo-based simulator with quadruped and humanoid robots (Go1, G1),
composable scenes, and contact-rich physics out of the box.
Reusable, phase-aware robot actions — gaits, manipulations, sequences — that
you call by name or compose into multi-phase missions.
Describe a multi-phase task as a single `env.json`: the scene, the phases,
success/fail predicates, and reward shaping.
Every tick of every run is captured and scored by an LLM judge, giving you
structured, labeled trajectories automatically.
Convert rollouts into VLA training data and train LoRA adapters — RL and
supervised fine-tuning behind one command.
Orchestrate policies and world models — sequential, chain-of-thought, or your
own VLA — through a clean inference interface.
Push a tested policy to physical hardware over DDS, SSH, or a bridge, using
the exact loop you ran in simulation.
Parse commands like "walk forward then sit" into action calls — a fast path
from intent to motion.
## Who it's for
* **Robotics researchers** prototyping policies and gathering training data
without building a sim pipeline from scratch.
* **Applied ML teams** fine-tuning VLA models on task-specific rollouts.
* **Robot product teams** that need a reproducible path from simulation to a
deployed unit.
How our stack compares to the status quo.