Skip to main content

ngrok-ai-gateway

❖ Communityv1.0.0

The ngrok AI Gateway as a Hermes model provider (`--provider ngrok`, or ngrok AI Gateway in `hermes model`): one access key for all your model providers, with failover. The model list comes live from your gateway, and gateway errors (unrouted model, access-policy and upstream-key failures, out of credit) map onto Hermes' fallback instead of a generic error.

Open in Hermes Desktop
hermes plugins install ngrok-ai-gateway

What it adds

Environment variables it needs 1

NGROK_AI_GATEWAY_KEY

README

From the reviewed commit 27baaa0 ↗; it updates when the author re-pins.

ngrok AI Gateway for Hermes

Use the ngrok AI Gateway as a model provider in Hermes. The gateway gives you one access key for all the model providers you've set up in ngrok, with failover and key rotation. See the AI Gateway docs to set up providers, keys and models.

Install

hermes plugins install ngrok-ai-gateway

Enter your access key from app.ngrok.ai/keys when prompted. Hermes saves it as NGROK_AI_GATEWAY_KEY.

Plugins are installed per Hermes profile, so install it again in any other profile that needs it.

Use

Select ngrok AI Gateway in hermes model, or pass --provider ngrok. The model list comes from your gateway.

To use a different gateway endpoint, set NGROK_AI_GATEWAY_BASE_URL. The default is https://gateway.ngrok.ai/v1.

Background tasks like compression and title generation use your main model. To use a cheaper model for them, set auxiliary.<task>.provider: ngrok and auxiliary.<task>.model in config.yaml.

Disclosure

The plugin sends chat and model-list requests to the gateway endpoint with your access key. Each request has a User-Agent: hermes-agent/<version> (ngrok-plugin) header. The plugin makes no other network requests, doesn't read files, and doesn't run background processes.

← Back to the catalog · catalog built Oct 16, 2026