> ## 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=` scaffolds a complete app with secure auth wired up. Typed TypeScript SDKs are published as @reactor-models/; 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. # LIBERO variant > Compatibility and observation/action contract for FastWAM LIBERO. | Property | Contract | | - | - | | Model slug | `reactor/fastwam-libero` | | Documented model release | `0.1.2`; see [release notes](/robotics/fastwam/libero/changelog) | | Reference embodiment | LIBERO Panda arm and parallel gripper | | Checkpoint | `libero_uncond_2cam224.pt` with its matching normalization statistics | | Observations | Exterior RGB, wrist RGB, eight state values, task instruction | | State | End-effector position, axis-angle orientation, two gripper joint positions | | Output | 32 × 7 LIBERO controller commands; no video output | | Protocol | Explicit `state_json` request; match the reply's `step` to `chunk_id` | The [released checkpoint](https://huggingface.co/yuanty/fastwam/blob/main/libero_uncond_2cam224.pt) targets LIBERO conventions. A seven-joint arm alone does not establish compatibility: the camera views, coordinates, and controller scaling must also match. Eight state values here do not mean DROID's seven arm angles plus one gripper fraction. ## Integration paths | Path | What this guide provides | | - | - | | First actions | A synthetic-input SDK example to run after hosted access is confirmed | | Simulation | Observation mapping, upstream evaluator links, and the required cloud adapter behavior | | Physical robot | Integration responsibilities; no validated hardware driver | Read the [quickstart](/robotics/fastwam/libero/quickstart), [simulation guide](/robotics/fastwam/libero/simulation), or [API reference](/robotics/fastwam/libero/reference). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.