Nativ is a native macOS workspace for running AI models locally on Apple Silicon with no accounts, subscriptions, or cloud dependency. It bundles an MLX-VLM inference server, a curated model library, and a polished SwiftUI chat interface supporting language, vision, code, and embedding models. Nativ also acts as an OpenAI- and Anthropic-compatible local inference server, letting users connect coding agents such as Claude Code and Codex directly to locally served models. The app is fully open source under the MIT license, with every component — from the model loader to the telemetry dashboard — publicly available on GitHub.