Managed Model Endpoints

SkillAI & models

This skill lets your AI set up and keep track of model endpoints for research workflows. Once added, your AI can register local or remote model services, confirm they are working, and send requests to the right one.

Available today. Use it from your connected AI after setup.

Add the skill, then ask your AI to register or check a model endpoint for your research workflow. From there it can keep those endpoints available and route requests to them.

Then ask your AI: use the Managed Model Endpoints skill

What your AI can do with it

  • Register local or remote model services for research workflows
  • Check that model endpoints are healthy and responding
  • Audit endpoints that are already registered
  • Use stored credential references when connecting to endpoints
  • Prepare startup scripts for model services
  • Route requests to the appropriate model endpoint

What this skill tells your AI

The instructions your AI receives, as published by companion-inc/feynman in skills/managed-model-endpoints/SKILL.md and read by ahel’s review.

Use this skill to make a model endpoint usable from Feynman.

Workflow:

  1. Define the endpoint purpose, model family, input/output schema, auth method, hardware need, and expected latency.
  2. Record whether the endpoint is local, remote HTTP, Modal-backed, SSH-backed, or a custom connector.
  3. Add only non-secret endpoint metadata to settings. Store secret references as environment variable names or credential refs.
  4. Implement start/stop/health/inference checks when Feynman owns the endpoint lifecycle.
  5. Run a tiny inference smoke and save request/response shape without leaking secrets.

Expose endpoints as research infrastructure, not as permanent claims that a model is installed when health has not passed.

Signals

GitHub stars
9k
Forks
1k
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
managed-model-endpoints
Source
github.com/companion-inc/feynman