Application
Inference & Serving
Cortex
1Local 2AI 3engine 4for 5running 6models
the six Ws · specification
W1
Who
Maintained by Menlo Research (Jan).
W2
What
A local engine for running and serving models.
W3
Where
Self-hosted on your own hardware, C++ core.
W4
When
When embedding local inference in an app or CLI.
W5
Why
An OpenAI-compatible local runtime that powers Jan.
W6
With
Model weights and a supported machine.
W7
Watch
Company-maintained; open-source (Apache-2.0). Runs fully local on your hardware, so models and data stay on your machine.