🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型！A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat Work). Chat with your AI dev assistant f…

An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms

DuckDB is an analytical in-process SQL database management system

pg_lake: Postgres with Iceberg and data lake access

chat log tool, easily use your own chat data. 聊天记录工具，轻松使用自己的聊天数据

Qwen Image models through MPS

Run LLMs with MLX

DuckLake is an integrated data lake and catalog format

[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

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

Staging repo for development of native port of TypeScript

Types and functions that make it a little easier to work with Core ML in Swift.

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

An extremely fast bundler for the web

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

An open source, self-hosted implementation of the Tailscale control server

Xiaomi Home Integration for Home Assistant

Instant Terminal Sharing

MLX: An array framework for Apple silicon

A Fast TTS Engine

HunyuanVideo: A Systematic Framework For Large Video Generation Model

一个第三方哔哩哔哩客户端，A third-party bilibili client。