You can now call models running on your own hardware through a hosted AI gateway. Privately, with one command:
`ngrok http 8000 --url https://vllm.internal`
Plus all the public models you know and love. ↓
We spend our days moving traffic across networks most people never think about.
Our devrel @endentire is building a physical model of the internet, starting with just two Pis and a cable, to make those layers impossible to ignore.
First video ↓
Two Raspberry Pis, one Ethernet cable. They can just talk… right?
Nope. That utterly fails.
Turns out "just talk" hides three very important questions. The first video from my little internet series gets that ping working, one layer at a time.
If your agent needs access to context in a customer's database what do you do? Our customers use ngrok to reach into those networks, with tightly controlled policies and observability for each individual endpoint.