Getting Started

Deploy your first AI agent in under 10 minutes. This guide walks you through local setup, configuration, and your first agent deployment.

Prerequisites

  • Docker & Docker Compose — version 20.10+ recommended
  • Node.js 18+ — for running the CLI and management tools
  • PostgreSQL — included in Docker Compose, or use your own instance
  • API Keys — for your chosen model provider (Claude, OpenAI, etc.)

Installation

# Clone the repository
git clone https://github.com/agentaworks/platform.git
cd platform

# Install dependencies
npm install

Configure Environment

Copy the example environment file and configure your API keys and database connection:

cp .env.example .env

# Edit .env with your settings:
DATABASE_URL=postgresql://agenta:password@localhost:5432/agentaworks
JWT_SECRET=your-secret-key-here
ANTHROPIC_API_KEY=sk-ant-...
OPENAI_API_KEY=sk-...

Run Migrations

Initialize the database schema:

npm run db:migrate

Start with Docker Compose

Launch the platform locally:

docker-compose up -d

# Check status
docker-compose ps

# View logs
docker-compose logs -f agenta-api

The API will be available at http://localhost:3000

Your First Agent

Create an agent via the API:

# Create an agent
curl -X POST http://localhost:3000/api/v1/agents \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -d '{
    "name": "Support Assistant",
    "slug": "support-assistant",
    "model": "claude-sonnet-4-5",
    "system_prompt": "You are a helpful support assistant.",
    "skills": []
  }'

# Deploy the agent
curl -X POST http://localhost:3000/api/v1/deployments \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -d '{
    "agent_id": "AGENT_ID_FROM_ABOVE",
    "replicas": 1
  }'

# Send a message
curl -X POST http://localhost:3000/api/v1/agents/support-assistant/message \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -d '{
    "message": "Hello, how can you help me?"
  }'

Next Steps

  • • Explore the API Reference to see all available endpoints
  • • Read Concepts to understand agents, skills, and deployments
  • • Configure your first skill to extend agent capabilities