> ## Documentation Index
> Fetch the complete documentation index at: https://docs.reactor.inc/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> To build and serve your own model, start at /deploy/development/quickstart and /deploy/development/overview. Deploying is the default path: reactor init scaffolds a workspace, reactor auth login authenticates, and reactor model deploy registers the model, publishes the release with the weights/ folder, and activates it on Reactor's GPUs, in one command from that workspace. Docker must be running, because the publish step builds the image locally. Bump model.version in reactor.yaml before redeploying a change, because a release that already has an image is reactivated as it is. Deployment access is granted per account, so contact team@reactor.inc if a deploy is refused. Every key in reactor.yaml is documented at /deploy/platform/reactor-yaml. Model code imports reactor_runtime; Python client code imports reactor_sdk. The runtime overview explains the model interface. Running the model on your own machine with reactor run is optional and needs a GPU you attach with --gpus; /deploy/development/local-testing covers that loop and pairs a complete brightness model with a Python client test in a separate brightness-test workspace.
> Reactor hosts multiple models, each with its own connect slug (modelName) and command/event schema. The video model catalog — slug, typed SDK package, and links to its schema — is at /model-api-reference/overview. Robotics policy documentation starts at /robotics/overview; X-WAM observations, actions, and client integration are under /robotics/xwam/; Cosmos3 Nano Policy DROID is under /robotics/cosmos/nano-policy-droid/. Some models expose one slug per experience (e.g. HappyOyster); always take the slug from the model's own pages, never guess it.
> Fastest path to a working app: `npx create-reactor-app my-app --model=<slug>` scaffolds a complete app with secure auth wired up. Typed TypeScript SDKs are published as @reactor-models/<model>; Python uses the base reactor-sdk package.
> Auth: exchange an API key (rk_...) for a JWT via POST https://api.reactor.inc/tokens from your server. Never put the API key in client-side code.
> Append .md to any docs URL for clean Markdown. Search these docs via the MCP server at https://docs.reactor.inc/mcp.

# Xiaomi Robotics 1

> Hosted XR-1 inference for the RoboCasa365 PandaOmron benchmark.

XR-1 predicts actions from camera observations, robot state, and a language task. Reactor runs
inference; your client captures observations and owns action execution, timing, and safety.

## RoboCasa365

| Property | Value |
| - | - |
| Model identifier | `reactor/xr1-robocasa365` |
| Reference embodiment | Simulated PandaOmron mobile manipulator |
| Observations | Three camera histories and four state rows |
| Action chunk | `(16, 60)`; the benchmark consumes the first 12 columns |
| Access | Public model; a Reactor API key is required |
| Reactor model release | `0.2.2` |

Start with the [RoboCasa365 quickstart](/robotics/xr1/robocasa365/quickstart) to receive actions
without a robot. The [simulation guide](/robotics/xr1/robocasa365/simulation) describes the upstream
benchmark and the cookbook's local-runtime adapter. A hosted simulator bridge still requires
integration and validation.

Use the [model reference](/robotics/xr1/robocasa365/reference) for camera names, state history,
action layout, and execution feedback. Other embodiments require their own validated checkpoint and
mapping; the model identifier does not select arbitrary robots at runtime.

[Release notes](/robotics/xr1/robocasa365/changelog) ·
[Upstream project](https://github.com/XiaomiRobotics/Xiaomi-Robotics-1)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.