Skip to main content
vlmrun-gw gives a coding agent the model catalog, vlmrun gw commands, request knobs, response shapes, and errors. After install, a plain-language ask is enough. Full skill URL: https://vlm.run/gateway/SKILL.md

Install

1

Add the skill

Use the skills CLI:
2

Ask for the result

The agent runs vlmrun gw chat, the OpenAI SDK, or VLMRun().gateway.

Zero-install skill use

Point the agent at the skill file for one session.

SKILL.md

Read the full skill source.

MCP Server

Read tools for agents that call the Gateway over MCP instead of local commands.