Skip to content

Forge

Purpose

Native AI module hub — prompt handoff from AI Center, links to AI providers and GPU passthrough. Dedicated agent builder is not shipped on this page yet.

When to use it

  • Land a prompt forwarded from AI Center (?prompt= / ?vm=)
  • Open AI provider configuration (OpenAI, Anthropic, Ollama, air-gap)
  • Jump to GPU passthrough inventory
  • Confirm where routing and models are configured today

How to get there

  • Route: /forge
  • Nav: AI → Forge (AI) (workspace switcher AI tile also points here)
  • Related: /ai-center, /settings/ai-providers, /gpu

Operate from the console (UX)

  1. Open /forge from the sidebar, workspace switcher, or command palette (⌘K / Ctrl+K).
  2. Read the editorial intro (eyebrow Intelligence, title Forge), then use the prompt card (if forwarded from AI Center) and the links to AI providers / GPU.
  3. Use the center’s primary CTA (create, scan, open workbench, ask Zeus when reasoning is required).
  4. Deterministic navigation and filters call the router directly — do not round-trip those through Ask Zeus.
  5. Pin frequent pages to Favorites (/favorites).
  6. Empty / fail: No data → check auth, namespace filter, and that required operators (KubeVirt/CDI/monitoring) are installed; purpose was: Native AI module hub — prompt handoff from AI Center, links to AI providers and GPU passthrough. Ded.
  7. Success: Live inventory or job progress matches the deck line; you can navigate to a related center without re-auth.

Use https://<host>:30050/ (NodePort) or your ingress URL — never publish lab IPs. HTTPS is required for in-browser VNC. Browse lists are safe; power actions live on workbenches.