
Your open-source personal assistant that lives on your server
Leon is an open-source personal assistant designed to run on your own server, giving you full control over your data and privacy. Built with Node.js, it uses NLP, text-to-speech, and speech-to-text to enable natural voice and text interactions. Leon features a modular skills architecture that lets developers create and share custom capabilities.
Runs entirely on your own server with optional offline mode, keeping your data under your control
Supports both voice commands and text input using NLP, TTS, and STT technologies
Extensible system where anyone can create, share, and install custom skills (packages and modules)
Supports Google Cloud, AWS, IBM Watson, and offline alternatives like CMU Flite and Coqui STT
Can operate fully offline for maximum privacy without relying on any third-party services
Works on GNU/Linux, macOS, and Windows with a dedicated CLI for easier management
New architecture combining local LLMs, transformers, and atomic tools for autonomous task execution
Run a fully offline personal assistant that never sends your data to third-party servers
Use voice commands to control smart home devices and automate daily routines on your own infrastructure
Build and test custom AI skills using Leon's modular architecture as a foundation for personal automation projects
Deploy within an organization's infrastructure to handle tasks like scheduling, reminders, and information retrieval without cloud dependencies
Released under the most permissive open-source license, allowing full modification and redistribution

The fastest AI code editor — built in Rust for speed and collaboration