ai-agent

ml-macos-performance: Speed Up Mac AI Workloads in Swift

Name: ml-macos-performance: Speed Up Mac AI Workloads in Swift
Author: woolfel

Accelerate your macOS AI agents with a Swift library designed for high‑performance machine‑learning tasks—ideal for founders building native Mac AI products.

intermediate⏱ 1-2 hours💵 Free

98 stars6 forksSwiftGuide quality 8/10 · reviewed Oct 11Updated 6/5/2023100% free · open source

What it is

Use the Swift tool to boost AI performance on macOS.

Real use case example

"A founder needs to build a fast AI-driven recommendation engine for their e-commerce platform. They create the engine using this tool, integrate it with their existing macOS infrastructure, and after 2 hours of setup, the engine is up and running, delivering accurate product suggestions to their customers."

Best insideCodex CLIContinueAny AI Client

When to use it

•When you're developing an AI-powered app on macOS and need to optimize model performance for better user experience
•When you want to compare the performance of different AI models on your macOS device
•When you need to identify performance bottlenecks in your AI-powered workflow on macOS

Ready-to-paste prompt

swift run MLCocoaBench --model ResNet50 --input-size 224 --num-iterations 100

Heads up: Make sure you have the latest version of Xcode and the Swift compiler installed, as ml-macos-performance relies on Swift and Xcode to build and run the benchmarking tools

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/ml-macos-performance && curl -fsSL https://workflowstacks.com/api/skills/ml-macos-performance/claude-skill -o ~/.claude/skills/ml-macos-performance/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How ml-macos-performance: Speed Up Mac AI Workloads in Swift works

Codeflow

Free to inspect

Ml-macos-performance: Speed Up Mac AI Workloads in Swift is a tiny Swift project (~350 lines across 3 code files). Setup is light: small project — see the README for how to run it. Last commit 41 months ago, Apache-2.0 license, no tests found.

Size

Tiny codebase

~350 lines · 3 code files · 3 min skim

Setup

Light setup

Small project — see the README for how to run it.

Runs on

Swift

No API keys detected

Swift 100%

Where to start reading

1
README.md
Start here — what it does and how to install it

What's in each folder

Data/Data files13 files

MLMacosPerf/Folder8 files

Models/Data models & types7 files

MLMacosPerf.xcodeproj/Folder5 files

READMENo tests foundThin docsNo CIApache-2.0 licenseLast update 41 mo ago