Stars
💡 Use Docker Compose to deploy Xiaoya services in a more elegant way, supports one-click deployment of Alist + Emby + Jellyfin, full-platform support, Linux/Windows/Mac/Synology, X86/Arm architecture
Xiaomi Home Integration for Home Assistant
Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.
The agent that grows with you
https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成
All in one Qwen3-ASR Server, compatible with OpenAI API
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
Home Assistant integration for Dreame robot vacuums with map support
Take your Home Assistant dashboard to the next level with dynamic, customizable animated cards that bring your smart home dashboard to life.
Minimalistic graph card for Home Assistant Lovelace UI
Causal depthwise conv1d in CUDA, with a PyTorch interface
🚀 Efficient implementations for emerging model architectures
PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models
AI Audio Datasets (AI-ADS) 🎵, including Speech, Music, and Sound Effects, which can provide training data for Generative AI, AIGC, AI model training, intelligent audio tool development, and audio a…
MS-Agent: a lightweight framework to empower agentic execution of complex tasks
Easy-to-understand AI learning resources for beginners.
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
天气预报HomeAssistant集成，支持15天及逐小时预报、各种生活指数，兼容彩云卡片，无需申请appkey
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A cookiecutter project template for generating the structure for a new custom component.
This repository contains a summary of knowledge cut-off dates for various large language models (LLMs), such as GPT, Claude, Gemini, Llama, and more.
The hub for audio AI research: papers, open models, benchmarks & datasets across audio LLMs, speech recognition, TTS, music & audio generation.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.