Zum Hauptinhalt springen

Model Registry

AI Supreme Council uses a community-maintained model registry to keep its list of available models up to date. The registry is a JSON file hosted on GitHub Pages that the app fetches and caches.

How It Works​

The registry file (registry/models.json) contains a structured list of providers, their models, and pricing tiers. On page load, the AISCouncil.Registry module fetches the latest registry data with a 24-hour cache. If the fetch fails, it falls back to a locally bundled copy.

Registry Format​

The registry defines providers and models with metadata:

{
  "providers": [
    {
      "id": "anthropic",
      "name": "Anthropic",
      "models": [
        {
          "id": "claude-sonnet-4-20250514",
          "name": "Claude Sonnet 4",
          "tier": "standard"
        }
      ]
    }
  ]
}

Contributing Models​

To add or update models in the registry:

  1. Fork the repository
  2. Edit registry/models.json with your changes
  3. Run the validation script: python registry/validate.py
  4. Submit a pull request

The validation script checks for:

  • Valid JSON structure
  • Required fields (id, name, provider)
  • No duplicate model IDs
  • Correct tier values

Auto-Refresh​

The registry refreshes automatically when the page loads. The 24-hour cache prevents excessive requests. You can force a refresh by clearing the app's cached data in Settings > Privacy.

GitHub Pages Hosting​

The registry is served from GitHub Pages as a static JSON file. This means:

  • No server-side logic required
  • Changes go live as soon as the PR is merged and Pages rebuilds
  • The file is CDN-cached for fast global access
  • The app falls back gracefully if GitHub is unreachable