GitHub Repository

M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.

136 starsTypeScript

M-Courtyard – Fine-tune LLMs on your Mac with zero code

Name: M-Courtyard – Fine-tune LLMs on your Mac with zero code
Availability: InStock
Author: tuwenbo0120

by tuwenbo0120·Feb 17, 2026·1 point·1 comment

Visit Project View on HN

AI Analysis

●●SolidNiche GemShip It

Wraps mlx-lm fine-tuning into a guided desktop UI, but local LLM tools are crowded.

Strengths

•End-to-end pipeline in one app: document import → dataset generation → training → Ollama export with quantization.
•Real-time loss visualization and LoRA config UI lower friction vs. scattered CLI + Python script workflows.

Weaknesses

•Apple Silicon–only (Tauri limitation), excluding Windows/Linux ML practitioners still using local training.
•No distinguishing technical innovation: mlx-lm and Ollama do the heavy lifting; UI wrapper on known tools is table stakes.

Post Description

Hi HN! I built M-Courtyard because fine-tuning LLMs locally was frustrating — CLI tools, Python scripts, and scattered documentation.

This app wraps the full pipeline (document → dataset → fine-tune → test → export to Ollama) into a single desktop app that runs entirely on Apple Silicon.

Tech: Tauri 2.x + React + mlx-lm + Ollama License: AGPL 3.0

Would love feedback on what models or features would be most useful.