Skip to main content



🚧 Cortex is under construction.

Cortex Cover Image

Cortex is a fast, cross-platform AI engine. Developers can use Cortex to build LLM apps or run model operations on-device. Cortex has a Docker and Ollama inspired CLI, and it can be used as a server or imported as a library.

Cortex currently supports 3 inference engines:


Real-world Use: Cortex powers Jan, our on-device ChatGPT-alternative.

Cortex has been battle-tested across 1 million+ downloads and handles a variety of hardware configurations.


Cortex aims to be compatible with OpenAI API (see coverage tracker).

Our goal is to make it easy for developers to provide on-device AI and to build more secure applications, using a fully open-source stack.


Cortex's architecture features a C++ inference core, with higher-order features in Typescript.

Our long-term mission is to enable more on-device and robotics use cases.