A PyTorch native library for large-scale model training

Run LLMs with MLX

Lightblue LLM Eval Framework: tengu, elyza100, ja-mtbench, rakuda

An extremely fast implementation of whisper optimized for Apple Silicon using MLX.

Everything you need to build state-of-the-art foundation models, end-to-end.

Make websites accessible for AI agents

MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. It implements OpenAI-compatible API endpoints, enabling seaml…

https://docs.openwebui.com

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

Desktop app for prototyping and debugging LangGraph applications locally.

Preferred Generation Benchmark

FastMLX is a high performance production ready API to host MLX models.

Large Language Model Text Generation Inference

Composable building blocks to build Llama Apps

Serverless replay of web archives directly in the browser

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

High-resolution models for human tasks.

EVA Series: Visual Representation Fantasies from BAAI

Ultralytics YOLO11 🚀

Open-Sora: Democratizing Efficient Video Production for All

㊙️ Create standard barcodes with Python. No external dependencies. 100% Organic Python.

A high-throughput and memory-efficient inference and serving engine for LLMs

The most accurate natural language detection library for Python, suitable for short text and mixed-language text

A lightning fast Finite State machine and REgular expression manipulation library.

A Gradio web UI for Large Language Models with support for multiple inference backends.

AutoRaise (and focus) a window when hovering over it with the mouse

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.