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

# Quick Start

> Deployment and setup instructions.

tinykit can be deployed to Railway or run locally.

## Railway Deployment

Deploy a new instance in less than a minute with a single click, no configuration necessary. This template provisions the necessary environment variables and a persistent volume.

[![Deploy on Railway](https://railway.app/button.svg)](https://railway.com/deploy/tinykit?referralCode=RCPU7k\&utm_medium=integration\&utm_source=template\&utm_campaign=generic)

### Configuration

During deployment, configure the LLM provider.

| Variable       | Description                        | Example     |
| :------------- | :--------------------------------- | :---------- |
| `LLM_PROVIDER` | `openai`, `anthropic`, or `gemini` | `anthropic` |
| `LLM_API_KEY`  | Provider API key                   | `sk-...`    |
| `LLM_MODEL`    | Provider model ID                  | `gpt-4o`    |

Once deployed, access the builder at `/tinykit` (e.g., `https://your-project.up.railway.app/tinykit`).

## Local Development

### Prerequisites

* Node.js 20+
* Git

### Setup

1. **Clone**:
   ```bash theme={null}
   git clone https://github.com/tinykit-studio/tinykit.git
   cd tinykit
   ```

2. **Install**:
   ```bash theme={null}
   npm install
   ```

3. **Configure**:
   cp `.env.example` to `.env` and set the `LLM_*` variables.

4. **Database**:
   Download the PocketBase binary.
   ```bash theme={null}
   npm run pocketbase:download
   ```

5. **Run**:
   Start the development server.
   ```bash theme={null}
   npm run dev
   ```
   Access at `http://localhost:5173/tinykit`.

## Environment Variables

| Variable       | Required | Description                            |
| :------------- | :------- | :------------------------------------- |
| `LLM_PROVIDER` | No\*     | AI provider slug.                      |
| `LLM_API_KEY`  | No\*     | Provider API Key.                      |
| `LLM_MODEL`    | No       | Model ID.                              |
| `LLM_BASE_URL` | No       | Optional base URL for compatible APIs. |

\*Can also be configured via `/tinykit/settings` UI after deployment.

## Estimated Costs

**Railway (Hobby)**: \~\$5/month (variable based on usage).
**LLM API**: Billed directly by the provider (OpenAI, Anthropic, etc).