Skip to main content
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

​
Configuration

During deployment, configure the LLM provider.
VariableDescriptionExample
LLM_PROVIDERopenai, anthropic, or geminianthropic
LLM_API_KEYProvider API keysk-...
LLM_MODELProvider model IDgpt-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: 
    git clone https://github.com/tinykit-studio/tinykit.git
cd tinykit
  2. Install: 
    npm install
  3. Configure: cp .env.example to .env and set the LLM_* variables.
  4. Database: Download the PocketBase binary. 
    npm run pocketbase:download
  5. Run: Start the development server. 
    npm run dev
    Access at http://localhost:5173/tinykit.

​
Environment Variables

VariableRequiredDescription
LLM_PROVIDERNo*AI provider slug.
LLM_API_KEYNo*Provider API Key.
LLM_MODELNoModel ID.
LLM_BASE_URLNoOptional 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).