> ## 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
> Reactor hosts multiple models, each with its own connect slug (modelName) and command/event schema. The catalog of every model — slug, typed SDK package, and links to its schema — is at /model-api-reference/overview. 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.

# reactor

> The CLI for the Reactor platform

## Description

The CLI for the Reactor platform.

**To get started:**

```sh theme={"theme":{"light":"github-light","dark":"github-dark-high-contrast"}}
reactor auth login
```

## Options

| Flag              | Description                                                                           |
| ----------------- | ------------------------------------------------------------------------------------- |
| `--server string` | Reactor API server URL (default "[https://api.reactor.inc](https://api.reactor.inc)") |
| `-v, --verbose`   | Enable verbose output                                                                 |

## See also

* [reactor auth](/deploy/cli-reference/reactor_auth) - Authentication commands
* [reactor build](/deploy/cli-reference/reactor_build) - Build the workspace's model container locally
* [reactor completion](/deploy/cli-reference/reactor_completion) - Generate the autocompletion script for the specified shell
* [reactor doctor](/deploy/cli-reference/reactor_doctor) - Check that this machine is set up to use the Reactor CLI
* [reactor gpu](/deploy/cli-reference/reactor_gpu) - Inspect accelerator (GPU) types the platform supports
* [reactor init](/deploy/cli-reference/reactor_init) - Initialize a new Reactor model workspace
* [reactor logs](/deploy/cli-reference/reactor_logs) - Stream logs for a session or model instance
* [reactor ls](/deploy/cli-reference/reactor_ls) - List models registered against the current account
* [reactor model](/deploy/cli-reference/reactor_model) - Model management commands
* [reactor regions](/deploy/cli-reference/reactor_regions) - List the canonical Reactor Regions usable in a deployment.yaml
* [reactor run](/deploy/cli-reference/reactor_run) - Run the workspace's model container locally
* [reactor validate](/deploy/cli-reference/reactor_validate) - Validate reactor.yaml and deployment.yaml without contacting the server
* [reactor version](/deploy/cli-reference/reactor_version) - Print the reactor CLI version
* [reactor weights](/deploy/cli-reference/reactor_weights) - Upload and inspect model weights
* [reactor welcome](/deploy/cli-reference/reactor_welcome) - Display the Reactor welcome screen