Repo đang lênCập nhật hằng ngày từ GitHub

Cloud native, ultra-high performance AI&API gateway, LLM API management, distribution system, open platform, supporting all AI APIs.🦄云原生、超高性能 AI&API网关，LLM API 管理、分发系统、开放平台，支持所有AI API，不限于OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 请求和返回，API申请与审批，调用统计、负载均衡、多模型灾备。一键部署，开箱即用。

Create chat bots for Facebook Messenger, Slack, Amazon Alexa, Skype, Telegram, Viber, Line, GroupMe, Kik and Twilio and deploy to AWS Lambda in minutes

A modern and easy-to-use client for Ollama

0x.Tools: X-Ray vision for Linux systems

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Fast BM25 search in Python, powered by Numpy and Numba

This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"

Safety-first guardrails for AI-driven cloud and Kubernetes operations

Rough list of my favorite deep learning resources, useful for revisiting topics or for reference. I have got through all of the content listed there, carefully. - Guillaume Chevalier

AI on the way. An auto deep learning pipe dream. An RDBMS approach to deep learning. Declarative, explainable, scalable, optimizable, easy to deploy, all that good stuff.

An extension for using Cursor in Visual Studio Code.

一款包含了 Prompt管理，Skill管理，Agent管理的一站式AI工具箱，助你高效管理提示词，一键分发skills ，一站式管理Agent资产，并实现云同步，备份，版本管理 | An all-in-one AI toolbox for prompt, agent, and skills management. Reuse prompts, distribute skills with one click, manage agent assets, and support cloud sync, backup, and version control

Text Classification Algorithms: A Survey

CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2023)

A dev agent multiplexer for git worktrees and coding agents.

:art: Semantic segmentation models, datasets and losses implemented in PyTorch.

DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.

Underthesea - AI Assistant

Independent native Design (including PPT) and Video plugins for DeepSeek Harness.

PyTorch implementation of Pointnet2/Pointnet++

LM Studio TypeScript SDK

Real-time logging dashboard for Kubernetes. View logs in a terminal or a browser. Run anywhere - desktop, cluster, docker.

YouTube Full Text Search - Search all of YouTube from the command line

An Embedded Computer Vision & Machine Learning Library (CPU Optimized & IoT Capable)

中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Albert, Attention, DeepMoji, HAN, 胶囊网络-CapsuleNet, Transformer-encode, Seq2seq, SWEM, LEAM, TextGCN

Deep Learning tutorials in jupyter notebooks.

Interpretability and explainability of data and machine learning models

WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

Run OpenClaw on Android with a single command — no proot, no Linux

🚀🚀🚀 A collection of some awesome public YOLO object detection series projects and the related object detection datasets.

Tencent Server Web

Discover inspiration and create images and videos with the latest AI models. Works with ChatGPT, Claude, Cursor, and other MCP clients.

The agent that monitors anything for you. Deploying micro-agents running completely locally. Open Source.

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Easily craft fast Neural Networks on iOS! Use TensorFlow models. Metal under the hood.

心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models

1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy

Discovering Interpretable GAN Controls [NeurIPS 2020]

收集GPTS的prompt / Collect the prompt of GPTS

百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，接入openClaw，真正的个人语音助手，时延低至800ms，Mac等低配置也可运行，支持打断

DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.

supports Telegram, Discord, Slack, Lark（飞书），钉钉, 企业微信, QQ, 微信, compatible with various LLMs including OpenAI, Gemini, DeepSeek, Doubao, and OpenRouter. It offers intelligent conversation, image generation, video creation, and more. Works seamlessly in both private chats and group settings.

TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet

One SQL interface for 60+ tools (e.g., GitHub, Notion, Airtable). Plug into any LLM through MCP.

Awesome-pytorch-list 翻译工作进行中......

High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime

Deep Learning and Machine Learning stocks represent promising opportunities for both long-term and short-term investors and traders.

Democratizing AI scientists with ToolUniverse

巡影 · 开源 AI 影视自动追更与多网盘媒体库整理工具 / Open-source AI agent for cloud drive media tracking & NAS (夸克 Quark / UC / 115 / 123 / 光鸭 Guangya / 天翼 Tianyi)

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.