Skip to content

WWDC26: Run local agentic AI on the Mac using MLX | Apple

2026 14 min Apple Developer en YouTube

Run AI agents locally with privacy, low latency, and offline access. Dive into how MLX advancements and Mac hardware make powerful agentic workflows possible entirely on-device. You’ll explore code agents such as OpenCode, see how they integrate into Xcode, learn techniques for multi-Mac scaling, and discover how to integrate tools seamlessly — without ever leaving your machine.

Chapters

  1. 0:00 Introduction
  2. 0:32 The chat and agentic loop
  3. 2:42 Local agentic AI stack
  4. 4:36 Setting up your own agent
  5. 5:39 Making agents fast
  6. 6:53 Concurrency and distributed inference
  7. 9:20 More examples
  8. 13:01 Next steps
Channel
Apple Developer
Views
21

More like this