July 3, 2026
Explore Apple's open-source toolkit for exporting, authoring, and running on-device AI models with Core AI, including Python primitives, Swift utilities, and agent skills.
Explore Apple's Core AI Models repository: export recipes for popular models, Python authoring primitives, and a Swift runtime for deploying AI on macOS and iOS.
The AI boom is creating an insatiable demand for HBM, causing a global memory shortage that is pricing out budget smartphone users and threatening consumer electronics.
Discover Moonshine Voice, the open-source AI toolkit revolutionizing real-time voice applications. Running entirely on-device across iOS, Android, Python, Raspberry Pi, and more, it delivers lower latency than Whisper Large V3 with models as small as 26MB. Perfect for developers building responsive voice interfaces without cloud dependency. Get started in minutes with pip install and microphone transcription.
Discover ANE Training: a groundbreaking open-source project that reverse-engineers Apple's Neural Engine to run full transformer training (forward + backward passes) directly on M4 hardware. Achieving 9.3ms/step and 1.78 TFLOPS sustained performance with pure ANE compute - no Metal, no GPU. Includes detailed benchmarks, MIL program generation, IOSurface optimization, and channel-first layouts. Perfect for Apple Silicon ML researchers pushing hardware boundaries.