Projects Services Store Blog Contact
📦
Digital Product

Sovereign Stack & Multi-LLM Router Starter Kit

$85.000

Description

Docker Compose + n8n workflows + routing prompts to set up your own multi-AI command center. Stop relying on a single API and distribute the work among 11 models.

This product does not have a purchase link configured yet.

🔄

Client Portal (Odoo)

Payment processing, invoicing, and download management are handled in our secure Odoo space.

🔑 Already purchased? Log in here to download →
Urgent Limited time

A "half-broken" piece of furniture or structure in your Airbnb costs 4× more in negative reviews than fixing it on time.

Design my structure →

This kit solves a specific problem: dependence on a single AI provider. When your workflow depends on one API and that API changes prices, limits tokens, or goes down, your operation stops.

The Starter Kit includes the complete setup for:

  • Multi-LLM Router: Task-type routing logic (code → DeepSeek, writing → GPT-4o-mini, analysis → Qwen, vision → Kimi). Based on the failover matrix documented in the digital garden.
  • Sovereign Stack in Docker: n8n + Redis + PostgreSQL + Astro in a single docker-compose.yml tested in production (4GB RAM VPS).
  • Routing Prompts: Optimized system prompt templates for each model, with formatting instructions and specific constraints.
  • Failover Matrix: Automatic backup configuration — if the primary provider fails, the router escalates to the secondary without manual intervention.

The kit is designed for someone already using AI in their workflow who wants to stop relying on a single API. You don't need to know how to program, but you should be comfortable with Docker and editing YAML/JSON files.

  • Complete docker-compose.yml: n8n + Redis + PostgreSQL + documented environment variables
  • 8 n8n workflows in JSON (direct import): task router, automatic translation, content generation, data analysis, scraping + summarization, email drafting, code review, research pipeline
  • Routing matrix in YAML: 11 models × 8 task types with real performance scores
  • 11 optimized system prompts (one per model) with formatting instructions, tone, and constraints
  • Step-by-step deployment guide: from empty VPS to operational router in 45 minutes
  • Monitoring template: n8n dashboard to view consumption per model, latency, and error rate
  • README with troubleshooting: the 12 most common errors and how to fix them
  1. Prerequisites: A VPS with at least 4GB RAM (Ubuntu 22.04+), Docker and Docker Compose installed, and at least 2 AI model API keys (OpenAI + OpenRouter is the fastest combination to start with).
  2. Clone and configure: Copy the docker-compose.yml to your server, edit the .env file with your API keys, and adjust ports if necessary.
  3. Bring up the stack: Run docker compose up -d. Wait 2 minutes for n8n to initialize.
  4. Import the workflows: Open n8n at http://your-server:5678, go to Workflows → Import from File, and import the 8 included JSONs.
  5. Configure the router: Edit the routing matrix (routing-matrix.yaml) with your available models. Mark those you don't have as disabled.
  6. Test the pipeline: Run the "router-test" workflow with a sample task. Verify that the response comes from the correct model.
  7. Iterate: Adjust the system prompts to match your tone and needs. The guide includes a chapter on prompt fine-tuning per model.

My History

    Free Diagnosis

    Does your business have invisible leaks?

    In 2 minutes, identify exactly where you're losing money — no jargon, no commitment.

    The 5 Business Leaks: the interactive checklist my clients use before the first session.

    🛠️ Go to Free Diagnosis →

    No registration. No spam. Immediate result.