LLM Gateway CLI

The LLM Gateway CLI (@llmgateway/cli) is a command-line utility for scaffolding projects, managing AI applications, and discovering models.

Installation

Run commands directly without installation:

npx @llmgateway/cli init

Install globally for faster access:

npm install -g @llmgateway/cli

Then run commands directly:

llmgateway init

Quick Start

Initialize a Project

Create a new project from a template:

npx @llmgateway/cli init

Or specify the template and name directly:

npx @llmgateway/cli init --template image-generation --name my-ai-app

Configure Authentication

npx @llmgateway/cli auth login

This opens a browser window to authenticate with LLM Gateway. Your credentials are stored in ~/.llmgateway/config.json.

Alternatively, set the LLMGATEWAY_API_KEY environment variable which takes precedence over the config file.

Start Development

Navigate to your project and start the development server:

cd my-ai-app
npx @llmgateway/cli dev

Or specify a custom port:

npx @llmgateway/cli dev --port 3000

Commands

`init`

Initialize a new project from a template.

npx @llmgateway/cli init [options]

Options:

--template <name> — Template to use (e.g., image-generation, weather-agent)
--name <name> — Project name

Examples:

# Interactive mode
npx @llmgateway/cli init

# With options
npx @llmgateway/cli init --template image-generation --name my-app

`list`

Display available project templates.

npx @llmgateway/cli list

Options:

--json — Output in JSON format

`models`

Browse and filter available AI models.

npx @llmgateway/cli models [options]

Options:

--capability <type> — Filter by capability (e.g., chat, image, embedding)
--provider <name> — Filter by provider (e.g., openai, anthropic, google)
--search <term> — Search models by name

Examples:

# List all models
npx @llmgateway/cli models

# Filter by provider
npx @llmgateway/cli models --provider openai

# Search models
npx @llmgateway/cli models --search gpt

`add`

Add tools or API routes to an existing project.

npx @llmgateway/cli add

Tools available:

weather — Weather lookup functionality
search — Web search capability
calculator — Mathematical operations

API routes available:

generate — Text generation endpoint
chat — Chat completion endpoint

`auth`

Manage API authentication.

# Login via browser
npx @llmgateway/cli auth login

# Check authentication status
npx @llmgateway/cli auth status

# Logout
npx @llmgateway/cli auth logout

`dev`

Start the local development server.

npx @llmgateway/cli dev [options]

Options:

--port <number> — Port to run on (default: 3000)

`upgrade`

Update LLM Gateway dependencies in your project.

npx @llmgateway/cli upgrade [options]

Options:

--dry-run — Show what would be updated without making changes

`docs`

Open the documentation in your browser.

npx @llmgateway/cli docs

Available Templates

Image Generation

A full-stack application for AI image generation.

Stack: Next.js 16, React 19, TypeScript
Features: Multi-provider support (DALL-E, Stable Diffusion), unified API
Use case: Image generation apps, creative tools

npx @llmgateway/cli init --template image-generation

Weather Agent

A CLI agent demonstrating tool calling capabilities.

Stack: TypeScript, AI SDK, OpenAI
Features: Tool calling, real-time data, natural language
Use case: Learning tool usage, building CLI agents

npx @llmgateway/cli init --template weather-agent

Configuration

The CLI stores configuration in ~/.llmgateway/config.json:

{
	"apiKey": "llmgtwy_...",
	"defaultTemplate": "image-generation"
}

Environment Variables

The LLMGATEWAY_API_KEY environment variable takes precedence over the config file:

export LLMGATEWAY_API_KEY="llmgtwy_..."

More Resources

Agents — Pre-built AI agents
Templates — Production-ready starter projects
GitHub Repository — Source code and issues

Need help or want to request a feature? Open an issue on GitHub.

LLM Gateway CLI

On this page