Stars
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX …
An audio server, programming language, and IDE for sound synthesis and algorithmic composition.
Draw perfect pressure-sensitive freehand lines.
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to con…
Open-source UI component library and front-end development framework based on Tailwind CSS
deck is a tool for creating deck using Markdown and Google Slides.
High-performance MLX-based LLM inference engine for macOS with native Swift implementation
A PyTorch native platform for training generative AI models
Lightblue LLM Eval Framework: tengu, elyza100, ja-mtbench, rakuda
An extremely fast implementation of whisper optimized for Apple Silicon using MLX.
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
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…
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
Blaizzy / fastmlx
Forked from arcee-ai/fastmlxFastMLX is a high performance production ready API to host MLX models.
Large Language Model Text Generation Inference
Composable building blocks to build LLM 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.