Fast local LLM / VLM inference engine for Apple Silicon (MLX). OpenAI- and Anthropic-compatible, lossless speculative decoding (DFlash2 / MTP), hybrid-model pre
Fast local LLM / VLM inference engine for Apple Silicon (MLX). OpenAI- and Anthropic-compatible, lossless speculative decoding (DFlash2 / MTP), hybrid-model prefix cache with RAM/SSD tiers, native Claude Code / Codex / opencode support. Qwen3.8-27B tuned first.
Maintain this project? Show that it is featured on YunoDB.
[](https://yunodb.com/tools/yuhuanstudioyunshu?utm_source=github&utm_medium=badge)<a href="https://yunodb.com/tools/yuhuanstudioyunshu?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/yuhuanstudioyunshu.svg" alt="Featured on YunoDB" height="20"></a>
🤖 Multi-platform IM AI Agent for Telegram, WhatsApp, Lark, and WeChat. Connects ChatGPT / Claude / Kimi / DeepSeek / Ollama / Pi for auto-replies, community an
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration,
Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 600+ models (Flux, Midjourney, Kling, Sora, Veo). No c