Stars
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
Video+code lecture on building nanoGPT from scratch
Desktop tool for managing virtual machines via libvirt
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …
Cross-platform text editor, written in Free Pascal
Aila(AI超元域): The premier AI integration tool for Windows, macOS, and Android. Ask once, get answers from 10+ AIs like ChatGPT, Gemini, Claude3, Copilot, Poe, perplexity and more. Features customiza…
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
No fortress, purely open ground. OpenManus is Coming.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
MTEB: Massive Text Embedding Benchmark
A modular graph-based Retrieval-Augmented Generation (RAG) system
Real-time face swap for PC streaming or video calls
Zero-Shot Speech Editing and Text-to-Speech in the Wild
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
VirtualWife是一个虚拟数字人项目，支持B站直播，支持openai、ollama
fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。
Industry leading face manipulation platform
ComfyUI nodes to edit videos using Genmo Mochi
An open-source RAG-based tool for chatting with your documents.
A massively parallel, optimal functional runtime in Rust