Installation

Lattis ships as a desktop app with a built-in gateway daemon — there’s nothing to compile and no separate service to set up.

Get the app

Prebuilt apps for macOS, Linux, and Windows are on the way — see the Download page. Once installed, open Lattis and it’s ready to use: connect a local model server (LM Studio, Ollama, llama.cpp, vLLM, …) or a cloud provider, and start sending requests.

The app runs a lightweight background service that serves the API and keeps working even when the window is closed. To have it start automatically, see Launch on Login.