Time to First Request: 5 Minutes

1Deploy the Core Engine & Generate API Key

Selixes is containerized for zero-friction local development. Run the core engine (Control Plane + Data Plane) on your local machine:

docker run -d -p 4000:4000 --name selixes-core selixes/core:latest

Next, generate your first API key to authenticate requests. Run this CLI command inside the container:

docker exec -it selixes-core selixes-cli generate-key

*(Save this key, you will need it in the next step).*

22-Line SDK Drop-in

Selixes is fully compatible with the standard OpenAI SDK. Swap the `baseURL` and `apiKey` to point your existing application to the local reliability layer:

import OpenAI from 'openai';
 
 // Selixes integration takes exactly 2 lines:
 const openai = new OpenAI({
   apiKey: process.env.SELIXES_API_KEY,     // 1. Secure reliability key
   baseURL: 'http://localhost:4000/v1'      // 2. Swapped base URL
 });

3Dispatch Your First Reliable Request

Pass transaction cost caps, timeout limits, and semantic caching directives directly through standard HTTP request headers:

const response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Extract details from CSV invoices' }],
  headers: {
    'x-selixes-session-id': 'session_crm_batch_02',
    'x-selixes-max-session-cost': '0.15', // Autonomous block if spend exceeds $0.15
    'x-selixes-semantic-cache': 'true',   // Serve from vector DB if similar prompt exists
    'x-selixes-timeout': '5000'           // Instantly failover to Anthropic if OpenAI takes > 5s
  }
});

4Access the AI-Native Telemetry

Selixes doesn't just log requests; it tells you *why* routing decisions were made. Start the companion dashboard:

docker run -d -p 3000:3000 --name selixes-dashboard --link selixes-core selixes/dashboard:latest

Navigate to http://localhost:3000 to review active transactions, inspect provider failover rationales, and audit token economics.

*(Note: For staging or production deployments, use our `docker-compose.yml` to orchestrate both services and Redis simultaneously).*