MLX Swift integration for React Native - InferrLM fork with enhanced features

A JavaScript implementation of Llama 3 using [node-mlx](https://github.com/frost-beta/node-mlx), code modified from [mlx-examples](https://github.com/ml-explore/mlx-examples).

OMLX provider extension for pi - Access self-hosted Qwen models through a local MLX/OpenAI-compatible server

OpenCode plugin that adds a 'local' provider with auto-detection for Ollama, LMStudio, llama.cpp, vLLM, Exo, llama-swap, oMLX, and MLX-VLM

Pi coding agent provider for MLX local AI models on Apple Silicon

LLM inference for Node.js powered by Apple MLX on Apple Silicon

Finds the route declarations in your application.

Context compaction plugin for OpenClaw - works with local models (MLX, llama.cpp) that don't report token limits

No description provided.

PAI voice server using MLX-audio Kokoro TTS

MLX steering vectors — coming soon (Python/JS library)

The foundational Node.js bridge to Apple's MLX framework via C++. Native Apple Silicon acceleration with zero-dependency Node-API bindings.

Offline transcription of iPhone voice memos on macOS — 3 engines (mlx/cpp/gigaam) optimized for Russian

MLX-powered image generation for Mac Catalyst Expo apps

Custom OpenCode MLX provider for Gemma 4 models

PipelineScore CLI — benchmark LLMs on your own hardware. Zero-config: `npx @pipelinescore/cli` auto-detects Ollama / LM Studio / llama.cpp / MLX and walks you through a run. Fully deterministic suite (no API key required), scored locally, published to the

AI SDK provider for local MLX (Swift) models on Apple Silicon (macOS).

Vision-language models and document processing pipelines for Node.js on Apple Silicon. Extract text, tables, and structure from documents and images using PaddleOCR-VL and the PP-StructureV3 pipeline — all running locally on Metal GPU.

Local vision (describe images), STT (speech-to-text), and TTS (text-to-speech). macOS uses MLX (Apple Silicon GPU). Windows/Linux use whisper, edge-tts, and transformers.

No description provided.