Native Apple Silicon LLM server with MCP support. OpenAI & Ollama compatible APIs, tool calling, menu bar chat UI, and a plugin ecosystem. Built on MLX. Supports Apple Foundation Models.
-
Updated
Dec 5, 2025 - Swift
Native Apple Silicon LLM server with MCP support. OpenAI & Ollama compatible APIs, tool calling, menu bar chat UI, and a plugin ecosystem. Built on MLX. Supports Apple Foundation Models.
🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.
Your models on any xPU
ModernBERT model optimized for Apple Neural Engine.
PyTorch → CoreML conversion pipeline for Kokoro TTS. Unlocks fast on-device text-to-speech on Apple Neural Engine.
Add a description, image, and links to the apple-neural-engine topic page so that developers can more easily learn about it.
To associate your repository with the apple-neural-engine topic, visit your repo's landing page and select "manage topics."