← back to the directory
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.

InferenceLocalEngine

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.