Getting Started

Deploy your first AI agent with Aethyr in under 10 minutes. This guide covers installation, configuration, and creating your first agent.

Prerequisites

  • Docker - Required for containerized deployment
  • Node.js 18+ - For local development
  • PostgreSQL 15+ - With pgvector extension for RAG
  • Ollama - Optional, for local model inference

Installation

Option 1: Docker (Recommended)

The fastest way to get started is with Docker Compose. This spins up the entire stack including PostgreSQL and Redis.

Terminal
# Clone the repository (private - request access)
git clone https://github.com/aethyrai/console.git
cd console

# Start with Docker Compose
docker-compose up -d

Option 2: Local Development

For local development, you'll need to set up the dependencies manually.

Terminal
# Install dependencies
npm install

# Copy environment template
cp .env.example .env

# Run database migrations
npm run db:migrate

# Start development server
npm run dev

Configuration

Configure your environment variables in .env:

.env
# Database
DATABASE_URL="postgresql://user:password@localhost:5432/aethyr"

# Authentication
NEXTAUTH_SECRET="your-secret-key"
NEXTAUTH_URL="http://localhost:3001"

# AI Providers (optional - configure as needed)
OPENAI_API_KEY="sk-..."
ANTHROPIC_API_KEY="sk-ant-..."

# Local Models (optional)
OLLAMA_HOST="http://localhost:11434"

Create Your First Agent

Once Aethyr is running, you can create your first AI agent through the console UI or API.

1

Access Console

Navigate to localhost:3001 and log in with your credentials.

2

Create Agent

Click "New Agent" and configure the model, system prompt, and capabilities.

3

Start Chat

Begin interacting with your agent through the chat interface.

Next Steps