Skip to content

Settings — AI providers

Purpose

Register and manage the language-model providers that power Zeus OS AI features, plus routing rules, API keys, stored memory, and the prompt library.

When to use it

  • Point Zeus OS at Forge, a local Ollama endpoint, or another OpenAI-compatible provider
  • Set which provider is the default and how requests are routed
  • Review or clear stored AI memory before an audit
  • Curate reusable prompts for your team

How to get there

  • Route: /settings/ai-providers
  • Nav: Settings → AI providers
  • Related: /ai-center, /forge, /nlp-command

Operate from the console (UX)

  1. Open /settings/ai-providers from the sidebar, workspace switcher, or command palette (⌘K / Ctrl+K).
  2. Read the PageHead / deck line — confirm it matches: Register and manage the language-model providers that power Zeus OS AI features, plus routing rules, API keys, stored me….
  3. Change only the section you need (General / Appearance / Advanced / API access / …).
  4. Save; API keys and SSO changes may require re-login.
  5. Cluster-wide TLS/auth/data-dir remain server env — see Admin basics.
  6. Empty / fail: No data → check auth, namespace filter, and that required operators (KubeVirt/CDI/monitoring) are installed; purpose was: Register and manage the language-model providers that power Zeus OS AI features, plus routing rules,.
  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.