Local ML Model Workbench

Native Apple Silicon benchmarking workbench for local LLMs: tokens/sec, arena head-to-heads, live hardware telemetry, and in-app Ollama model pulls.

No-code workbench to train your own transformer LLMs on Apple Silicon GPU via Metal—tokenizers, optimizers, live loss charts—entirely on-device.

On-device LoRA training workspace: prepare datasets, run preflight checks, train adapters with Apple MLX and export inference-ready model folders.

Native Mac Segment Anything workstation: prompt or box-draw instance masks in bulk and export PNG, cutouts, COCO JSON or YOLO TXT, all on device.

Turns your Apple devices into a shared AI server, exposing on-device chat, image generation, vision, and speech via a standard HTTPS API on the Neural Engine.

Node-based real-time visual-effects canvas with 170+ nodes, Metal GPU rendering and a CoreML model-inference node for reactive on-device ML in shaders.

Offline molecular analysis for chemists: a local Graphormer model predicts HOMO-LUMO gaps and ChemBERTa predicts ADMET, alongside RDKit property calc.

Create ML data-prep workbench for Apple Silicon: bounding-box labeling, model-assisted auto-labeling, and dataset augmentation, all processed locally.

Menu-bar local AI gateway: runs open models on your Mac and exposes a drop-in API endpoint so tools like Cursor and Cherry Studio can use them offline.

Native macOS workbench for building YOLO object-detection datasets: annotate, train externally, then re-import CoreML models for inference-assisted labeling.

Desktop tool for building labeled object-detection datasets for Create ML; can load a Core ML detector to auto-propose boxes for faster iterative labeling.

Niche desktop graph/network analysis tool with a built-in AI module for decision trees and graph-similarity learning, running classification and regression locally.

AlphaZero-inspired chess opponent driven by a neural network trained on hundreds of thousands of games, running fully offline with 10 difficulty levels.

Interactive NEAT neuroevolution playground that grows and trains neural-net agents on-device with live network visualisation and lessons.

Pro Mac dashboard for Davis weather stations over the local network, with on-device ML models for local forecasting and full offline operation.

Playground for testing prompts against Apple's on-device Foundation Models with system instructions, temperature, and streaming; no API keys.

A developer workbench for crafting and testing prompts against Apple's on-device Foundation Models, exposing temperature, top-k, and inference stats.

Native quantum workbench to design circuits and simulate locally across 7 hardware vendors, with on-device Apple Foundation Models suggesting backends.

Loads your own Core ML models and runs on-device inference (classification, detection, style transfer) on live camera or images with no Xcode build needed.

A build-your-own expert system: define a neural-network topology, train it with back-propagation on your own data, then consult it for decision support, all locally.

Power-user tool that runs custom Core ML classifiers and face comparison to find and filter scenes in your video collection locally.

Checkers game whose 'Natural AI' engine is a convolutional neural network trained on 215,000+ games, AlphaZero-style, running fully offline.

Air-hockey game where you train your own Q-Learning AI models on-device and pit them against you or each other; a Swift Student Challenge winner.

Native Mac arena that pits local LLMs against each other in chess, checkers and more, supporting MLX, GGUF, Ollama and LM Studio endpoints.

Native Mac tool for building and exporting Alpaca-format JSONL instruction-tuning datasets, with local Ollama integration to test training prompts against your base models.

Evaluation suite to test and score on-device AI prompts, compare variants and judge outputs for quality and hallucination risk on macOS.