Nativ Puts a Local Chat UI and API Server on Every MLX Model on Your Mac
Nativ is a macOS desktop app from MLX-VLM developer Prince Canuma that wraps MLX with a chat interface and a localhost API server for running AI models locally on Apple Silicon.
What it is
A new macOS desktop application by Prince Canuma, the developer behind the MLX-VLM library, built around Apple's MLX framework for local model inference.
What it does
It provides both a chat interface and a localhost API server for accessing models, similar in shape to LM Studio, and picks up MLX models already present in a user's Hugging Face cache without extra setup.
Why it matters
It's an alternative to LM Studio and Ollama for Mac users specifically invested in MLX, giving vision-language and text models a proper GUI and API surface instead of raw Python scripts.
How to use it
Download the app from the Nativ site; it will detect MLX models already cached from Hugging Face downloads and expose both a chat window and a localhost API endpoint.
Claude Code 2.1.217 Adds Emoji Autocomplete and Fixes an MCP Memory Leak
Claude Code 2.1.217 adds emoji shortcode autocomplete, warns when transcript writes fail instead of losing sessions silently, and fixes a memory leak from truncated MCP tool outputs.
Why a Popular Claude Code Awesome-List Repo Auto-Commits Every 3 Hours
SKIP
Claude Code 2.1.216 Fixes Quadratic Slowdown in Long Sessions
Claude Code 2.1.216 fixes a bug where message normalization cost grew quadratically with turn count, causing multi-second stalls and slow resumes in long sessions.