Repo AI đang lênCập nhật hằng ngày từ GitHub

Siamese and triplet networks with online pair/triplet mining in PyTorch

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

Turn code into clarity. Generate accurate technical docs and AI-ready context in minutes—perfectly structured for human teams and intelligent agents.

torch-optimizer -- collection of optimizers for Pytorch

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Run AI models end-to-end encrypted.

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

A tiny, fast Rust CLI that drives a real browser over the Chrome DevTools Protocol — built for coding agents.

Face Recognition, Face Liveness Detection, Face Anti-Spoofing, Face Detection, Face Landmarks, Face Compare, Face Matching, Face Pose, Face Expression, Face Attributes, Face Templates Extraction, Face Landmarks

🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI

OpenMMLab Model Deployment Framework

Sparsity-aware deep learning inference runtime for CPUs

Add a real-time analytics node to your operational database. Spice is a portable, accelerated SQL query, search, and LLM-inference engine in Rust for data-grounded AI apps and agents.

Synkra AIOS: AI-Orchestrated System for Full Stack Development - Core Framework v4.0

Open-source, self-hosted customer support desk in a single binary. A lightweight alternative to Intercom, Zendesk, Chatwoot.

macOS dictation app

深度学习与PyTorch入门实战视频教程 配套源代码和PPT

写作蒸馏器.skill｜蒸馏复刻任意写作风格的 agent skill | Writing DNA Distiller - distill and recreate any writing style as an agent skill

Go package for OCR (Optical Character Recognition), by using Tesseract C++ library

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

UI for your AI. Open Source Tailwind components tailored for your GPT, generative AI, and LLM projects.

Must-read Papers on LLM Agents.

Better Prometheus alerts for Kubernetes - smart grouping, AI enrichment, and automatic remediation

Foundation Architecture for (M)LLMs

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your home via Telegram, Discord or Slack. Pluggable AI skills. OpenAI, Google, Anthropic or local AI. Runs on Mac Mini & AI PC.

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

这是一个全自动（音频）视频翻译项目。利用Whisper识别声音，AI大模型翻译字幕，最后合并字幕视频，生成翻译后的视频。

fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.

Offline Gemini image watermark restoration with reverse alpha blending. Native C++ GUI/CLI, batch processing, and optional GPU denoise.

AI Powered Knowledge Graph Generator

Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative

Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, Anthropic- & Gemini-compatible APIs. Zero-dependency self-hosted reverse proxy for Claude Code, Cline & Cursor. 把 Windsurf/Devin 云端 100+ 模型变成三套兼容 API。

QuantMind is an open source agent-native knowledge extraction and retrieval framework for quantitative finance.

Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)

Collection of AWESOME vision-language models for vision tasks

TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning :fire: :zap: :rainbow:

Machine learning glossary

Represent, send, store and search multimodal data

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection

AI Multi-Agent Framework in .NET

Awesome free machine learning and AI courses with video lectures.

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

基于ChatGPT3.5 API实现的私有化web程序

Top2Vec learns jointly embedded topic, document and word vectors.

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.