Pico Server

A live demonstration of a fully Swift local LLM server built with MLX and CoreML, run directly from Xcode without any Python dependencies.

Overview

A few months ago I demonstrated MLX Server and a few open source Swift tools I was working on at the Palo Alto AI Tinkerers meetup. I’ve changed direction a bit, but stayed true to open source and making local AI more accessible. I wanted to show an updated version of the local LLM server I presented earlier.

Tech stack