> ## 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.

# DreamZero DROID

> Stream three DROID views and measured Franka state to obtain joint targets.

The DROID variant serves the
[DreamZero-DROID checkpoint](https://huggingface.co/GEAR-Dreams/DreamZero-DROID) for a seven-joint
Franka arm and gripper.

| Property | Contract |
| - | - |
| Model identifier | `reactor/dreamzero` |
| Documented model release | `1.0.1`; see [release notes](/robotics/dreamzero/droid/changelog) |
| Inputs | `exterior_1`, `exterior_2`, `wrist`; seven measured joints; gripper; task |
| Output | `action_chunk` with `(24, 8)` actions |
| Joint representation | Absolute radians when measured joint state is supplied |
| Execution | Client-owned; the RoboLab path executes at 15 Hz |
| Session behavior | One episode stream with causal context; use separate sessions for separate robots |

With no measured joint state, the zero fallback makes the joint outputs relative to a zero anchor.
Always stream actual joint state when you intend to execute absolute targets.

Start with [Get your first actions](/robotics/dreamzero/droid/quickstart), which requires no local
GPU or robot. The [RoboLab gateway](/robotics/dreamzero/droid/simulation) provides a simulation
path. For your own bridge, use the [wire reference](/robotics/dreamzero/droid/reference) and
[integration guide](/robotics/dreamzero/droid/integration). These pages do not supply a validated
physical robot driver.


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