天涯古巷

superpowers. An agentic skills framework & software development methodology that works.

hermes-agent. The agent that grows with you

claude-code. 原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复

gstack. Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

E2FGVI. Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

outline. The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.

ClashBox. HarmonyOS NEXT的代理软件

ddgksf2013. 墨鱼去广告计划 | QuantumultX 去广告 | 去开屏广告 | 应用净化 | 会员解锁 | 墨鱼配置 | 应用增强 | 网页优化 | 网盘资源 | 模块去广告 | 圈 X 配置 | Shadowrocket配置 | 墨鱼规则 | Clash配置 | 小火箭去广告 | 资源库 | AdBlock | 网页广告 | 不完全指北

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

one-small-step. 这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

clash-verge-rev. A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

Xray. 最好用的 Xray 一键安装脚本 & 管理脚本

iptv-api. ⚡️IPTV直播源自动更新工具：自动采集、校验、测速并生成可播放结果，支持 M3U/TXT/API 输出、自定义频道、IPv4/IPv6、Docker、GitHub Actions、CLI 与 GUI 多端部署

Fin-R1. Fin-R1 is a large language model for complex financial reasoning developed and open-sourced with the joint efforts of the SUFE-AIFLM-Lab at the School of Statistics and Data Science, Shanghai University of Finance and Economics and FinStep.AI.

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

llm-course. Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

llm-action. 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）

DeepSeek-R1.

iptv. iptv最新可用直播源,支持iptv4/iptv6双栈访问。直播电视系统，这里有折腾好的，直接下载用吧。直播电视app电视手机全部兼容。

clash-dashboard. HTML

yacd. Yet Another Clash Dashboard

FFmpeg-Builds. Shell

shadowrocket-rules. 小火箭规则🚀，小火箭模块，小火箭配置，shadowrocket规则，shadowrocket rules，最全面的直连（DIRECT）、代理（PROXY）、屏蔽（REJECT）规则，自动构建，每日更新

Shadowrocket-ADBlock-Rules-Forever. 提供多款 Shadowrocket 规则，拥有强劲的广告过滤功能。每日 8 时重新构建规则。

OpenClash. A Clash Client For OpenWrt

shadowrocket-rules. 小火箭 shadowrocket 配置文件 模块 脚本 module sgmodule 图文教程 规则 分流 破解 解锁

Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

aimoneyhunter. ai副业赚钱大集合，教你如何利用ai做一些副业项目，赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English version for more insights.

CogVLM2. GPT4V-level open-source multi-modal model based on Llama3-8B

Shadowrocket. Shadowrocket_2.1.11.ipa 爱思助手安装

Paint-by-Example. Paint by Example: Exemplar-based Image Editing with Diffusion Models

architecture.of.internet-product. 互联网公司技术架构，微信/淘宝/微博/腾讯/阿里/美团点评/百度/OpenAI/Google/Facebook/Amazon/eBay的架构，欢迎PR补充

video-subtitle-translator. 视频字幕翻译，输入srt文件生成翻译后的srt文件。无需申请第三方API，本地实现字幕翻译。基于深度学习的视频字幕翻译框架。Srt file translation, generate translated srt file from input SRT file. No need to apply third-party API, local implementation of subtitle translation. Based on deep learning framework for video subtitle translation.

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Magisk. The Magic Mask for Android

TikTokDownload. 抖音去水印批量下载用户主页作品、喜欢、收藏、图文、音频

STTN. [ECCV'2020] STTN: Learning Joint Spatial-Temporal Transformations for Video Inpainting

AnimateDiff. Official implementation of AnimateDiff.

FunASR. Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

cv. Print-friendly, minimalist CV page

Video-Auto-Wipe. Erase specific content from the video that you don't wanna see

MixtralKit. A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

lama. 🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

OCR-SAM. [Open-Source Project] Combining MMOCR with Segment Anything & Stable Diffusion. Automatically detect, recognize and segment text instances, with serval downstream tasks, e.g., Text Removal and Text Inpainting

NeumAI. Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.

CogVLM. a state-of-the-art-level open visual language model | 多模态预训练模型

RapidOCR. 📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.

ProPainter. [ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

tacotron2. Tacotron 2 - PyTorch implementation with faster-than-realtime inference

private-gpt. Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

video-retalking. [SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

BibiGPT-v1. BibiGPT v1 · one-Click AI Summary for Audio/Video & Chat with Learning Content: Bilibili | YouTube | Tweet丨TikTok丨Dropbox丨Google Drive丨Local files | Websites丨Podcasts | Meetings | Lectures, etc. 音视频内容 AI 一键总结 & 对话：哔哩哔哩丨YouTube丨推特丨小红书丨抖音丨快手丨百度网盘丨阿里云盘丨网页丨播客丨会议丨本地文件等 (原 BiliGPT 省流神器 & AI课代表)

Retrieval-based-Voice-Conversion-WebUI. Easily train a good VC model with voice data <= 10 mins!

QPT-SDK. 建设使用QPT中所需的SDK，帮助开源项目更好适应不同平台与环境。

IOPaint. Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

kkndme_tianya. 天涯 kkndme 神贴聊房价

video-subtitle-remover. 基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

Inpaint-Anything. Inpaint anything using Segment Anything and inpainting models.

vits. VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

MAMP. Official implementation of the ICCV 2023 paper "Masked Motion Predictors are Strong 3D Action Representation Learners"

Gooey. Turn (almost) any Python command line program into a full GUI application with one line

auto-editor. Effort free video editing!

llm-cookbook. 面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

whisper.cpp. Port of OpenAI's Whisper model in C/C++

SadTalker. [CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

stable-diffusion-webui-dataset-tag-editor. Extension to edit dataset captions for SD web UI by AUTOMATIC1111

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

VABlog. YUV/PCM/H264/H265/AAC/FFmpeg/Opengl. 这有丰富的音视频开发的学习资源、开发工具、优秀书籍、教程、面试题和开源项目，旨在帮助开发者和爱好者更好地学习、实践和工作。

AISystem. AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

awesome-chatgpt-prompts-zh. ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

sd-webui-controlnet. WebUI extension for ControlNet

videosubfinder-cli. C++

stable-diffusion-webui. Stable Diffusion web UI

aliyundrive-webdav. 阿里云盘(https://www.aliyundrive.com/) 的webdav协议开源实现，支持安卓、Linux、树莓派、Docker、Windows、macOS部署， 并附带JAVA SDK支持二次开发

NextChat. ✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

sd-webui-bilingual-localization. Stable Diffusion web UI bilingual localization extensions. SD WebUI双语对照翻译插件

115push. 云传(115push)是一个将sha1导入到115网盘的工具，无需将文件下载到本地

SevenSha1UIAdvancedHelper. 转存助手ui优化版

core. :house_with_garden: Open source home automation that puts local control and privacy first.

alist. 🗂️A file list/WebDAV program that supports multiple storages, powered by Gin and Solidjs. / 一个支持多存储的文件列表/WebDAV程序，使用 Gin 和 Solidjs。

stable-diffusion. A latent text-to-image diffusion model

gh-proxy. github release、archive以及项目文件的加速项目

autocut. 用文本编辑器剪视频

style2paints. sketch + style = paints :art: (TOG2018/SIGGRAPH2018ASIA)

ChatGPT. Reverse engineered ChatGPT API

MockingBird. 🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

avatarify-python. Avatars for Zoom, Skype and other video-conferencing apps.

video-subtitle-generator. 视频音频生成字幕，生成srt文件。无需申请第三方API，本地实现音频转文本。基于Transformer的视频字幕生成框架。A GUI tool for generating subtitle from videos and generating srt files.

faceswap. Deepfakes Software For All

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

blind_watermark. Blind&Invisible Watermark ，图片盲水印，提取水印无须原图！

Watermark-Removal-Pytorch. 🔥 CNN for Watermark Removal using Deep Image Prior with Pytorch 🔥.

noise2noise. An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data"

tr. Free Offline OCR 离线的中文文本检测+识别SDK

TrWebOCR. 开源易用的中文离线OCR，识别率媲美大厂，并且提供了易用的web页面及web的接口，方便人类日常工作使用或者其他程序来调用~

Fay. 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。

bilix. ⚡️Lightning-fast async download tool for bilibili and more

PySceneDetect. :movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

Real-Time-Voice-Cloning. Clone a voice in 5 seconds to generate arbitrary speech in real-time

video-subtitle-extractor. 视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

AlphaPlayer. AlphaPlayer is a video animation engine.

home-assistant.io. :blue_book: Home Assistant User documentation

Home-Assistant-DIY. Home Assistant智能家居实践篇

pyobfuscate. pyobfuscate

FFmpeg. Mirror of https://git.ffmpeg.org/ffmpeg.git

Intensio-Obfuscator. Obfuscate a python code 2.x and 3.x

pyarmor. A tool used to obfuscate python scripts, bind obfuscated scripts to fixed machine or expire obfuscated scripts.

py2sec. :snake: py2sec is a Cross-Platform, Fast and Flexible tool to change the .py to .so(Linux and Mac) or .pyd(Win).

pokete. A terminal based Pokemon like game

stitching. picsew 滚动截屏 图片拼接 长图拼接 智能拼图 stitch opencv python 拼长图 拼截屏 拼聊天记录

RevokeMsgPatcher. :trollface: A hex editor for WeChat/QQ/TIM - PC版微信/QQ/TIM防撤回补丁（我已经看到了，撤回也没用了）

sewImage. 用python实现拼接截图

AnalysisAVP. 音视频学习，相关文件格式/协议分析，框架学习等。encode decode；rgb yuv h264 aac flv mp4 rtmp；libyuv x264 openh264 faac faad2 fdk-aac librtmp ffmpeg sdl2 webrtc；android ios capture videotoolbox；

vosk-api. Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

photo2cartoon. 人像卡通化探索项目 (photo-to-cartoon translation project)

SteamTools. 🛠「Watt Toolkit」是一个开源跨平台的多功能 Steam 工具箱。

ai-edu. AI education materials for Chinese students, teachers and IT professionals.

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Dango-Translator. 梦想是做出最棒的生肉翻译软件喵

Awesome-Big-Model. 📖收集国内外深度学习大模型API、论文、案例与学习资料，欢迎Star🌟

cli. 🥧 HTTPie CLI — modern, user-friendly command-line HTTP client for the API era. JSON support, colors, sessions, downloads, plugins & more.

PaddleViT. :robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

transferlearning. Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

adversarial-robustness-toolbox. Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

pyvirtualcam. 🎥 Send frames to a virtual camera from Python

ddddocr. 带带弟弟 通用验证码识别OCR pypi版

tfjs-models. Pretrained models for TensorFlow.js

modelarts.

ubuntu-wsl2-systemd-script. [Does not work anymore!] Script to enable systemd support on current Ubuntu WSL2 images

BackgroundMattingV2. Real-Time High-Resolution Background Matting

Background-Matting. Background Matting: The World is Your Green Screen

KDAT. 💥一个专为视觉方向目标检测全流程的标注工具集，全称：Kill Object Detection Annotation Tools。

TrackersListCollection. 🎈 Updated daily! A list of popular BitTorrent Trackers! / 每天更新！全网热门 BT Tracker 列表！

java-eight-part. 『Java八股文』Java面试套路，Java进阶学习，打破内卷拿大厂Offer，升职加薪！

face_recognition. The world's simplest facial recognition api for Python and the command line

awesome-cheatsheets. 超级速查表 - 编程语言、框架和开发工具的速查表，单个文件包含一切你需要知道的东西 :zap:

kcp. :zap: KCP - A Fast and Reliable ARQ Protocol

deepin-wine. 【deepin源移植】Debian/Ubuntu上的QQ/微信快速安装方式

awesome-jupyterlab. A curated list of awesome JupyterLab extensions and resources

ml-workspace. 🛠 All-in-one web-based IDE specialized for machine learning and data science.

GCMP. GPU集群管理平台（GPU Cluster Management Platform）

Cpp-Primer. C++ Primer 5 answers

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

FinancialSupportForOpenSource. 开源项目挣钱实用手册

pyTranscriber. pyTranscriber can be used to generate automatic transcription / automatic subtitles for audio/video files through a friendly graphical user interface.

wordninja. Probabilistically split concatenated words using NLP based on English Wikipedia unigram frequencies.

UTM. Virtual machines for iOS and macOS

PaddleOCR. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

WantWords. An open-source online reverse dictionary.

Nuitka. Nuitka is a Python compiler written in Python. It's fully compatible with Python 2.6, 2.7, 3.4-3.14. You feed it your Python app, it does a lot of clever things, and spits out an executable or extension module.

fucking-algorithm. Crack LeetCode, not only how, but also why.

DFI. Code for our IEEE TIP 2020 paper "Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton"

deep-hough-transform. Jittor and Pytorch code for paper "Deep Hough Transform for Semantic Line Detection" (ECCV 2020, PAMI 2021)

VTuber-Python-Unity. An Implementation of VTuber (Both 3D and Live2D) using Python and Unity. Providing face movement tracking, eye blinking detection, iris detection and tracking and mouth movement tracking using CPU only.

Awesome-Edge-Detection-Papers. :books: A collection of edge/contour/boundary detection papers and toolbox.

audio_video_streaming. 音视频流媒体权威资料整理，500+份文章，论文，视频，实践项目，协议，业界大神名单。

DBFace. DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy

Objectron. Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

linux-command. Linux命令大全搜索工具，内容包含Linux命令手册、详解、学习、搜集。https://git.io/linux

yolox-pytorch. 这是一个yolox-pytorch的源码，可以用于训练自己的模型。

vnpy. 基于Python的开源量化交易平台开发框架

TFace. A trusty face analysis research platform developed by Tencent Youtu Lab

FaceImageQuality. Code and information for face image quality assessment with SER-FIQ

LearningNotes. Java学习笔记，主要来源于B站上视频的学习，同时会记录平时一些学习和项目中遇到的问题，同步更新在蘑菇博客，如果对我的博客网站感兴趣的话，欢迎关注我的 蘑菇博客项目 笔记主要涵盖：Java，Spring，SpringCloud，计算机网络，操作系统，数据结构，Vue等 如果笔记对您有帮助的话，欢迎star支持，谢谢~

spleeter. Deezer source separation library including pretrained models.

extract-video-subtittle. 使用深度学习框架提取视频硬字幕；docker容器免安装深度学习库，使用本地api接口使得界面和后端识别分离；

poetry. 地球上最全的华语现代诗歌语料库，3k+诗人，80K+诗歌，15M+字

TheK8sBook. YAML files for use with The Kubernetes Book

Python-100-Days. Python - 100天从新手到大师

QPT. [内测中]QPT - 致力于让开源项目更好通往互联网世界的Python to EXE工具（Python打包）。

YOLOX. YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

subparts_ppn_keras. Subparts PPN SSD

Yolov5-deepsort-driverDistracted-driving-behavior-detection. 基于深度学习的驾驶员分心驾驶行为（疲劳+危险行为）预警系统使用YOLOv5+Deepsort实现驾驶员的危险驾驶行为的预警监测

computer-science. 🎓 Path to a free self-taught education in Computer Science!

ebook. 🔥🔥Java相关精品电子书分享100+，书籍来自网络🔥🔥

Game-Theory-Books. "Objective facts are Nash equilibrium points in the contest of competing wills." ― E.E.E., A Warm Mirror Neuron On A Memory

deepLearningBook-Notes. Notes on the Deep Learning book from Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016)

THE-ROAD-LESS-TRAVELED_Reading-Notes. This is my reading notes from my Evernote.

Unity3DTraining. 【Unity杂货铺】unity大杂烩~

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

R-CenterNet. detector for rotated-object based on CenterNet/基于CenterNet的旋转目标检测

RepVGG. RepVGG: Making VGG-style ConvNets Great Again

RepVGG.

mit-deep-learning-book-pdf. MIT Deep Learning Book in PDF format (complete and parts) by Ian Goodfellow, Yoshua Bengio and Aaron Courville

LabelImage. 一款在线图像标注工具（矩形、多边形、持续更新中……），可用于深度学习实例分割模型训练（Mask R-CNN）等。

cv_note. 记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/

py-googletrans. (unofficial) Googletrans: Free and Unlimited Google translate API for Python. Translates totally free of charge.

rtl88x2bu. rtl88x2bu driver updated for current kernels.

face_classification. Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.

OCR-Corrector. 利用语言模型，纠正OCR识别错误

faceai. 一款入门级的人脸、视频、文字检测以及识别的项目.

manga-image-translator. Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)

FacialExpressionRecognition. 人脸识别之表情识别项目相关源码

Deep-Learning-Interview-Book. 深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

netty. Netty project - an event-driven asynchronous network application framework

caj2pdf. Convert CAJ (China Academic Journals) files to PDF. 转换中国知网 CAJ 格式文献为 PDF。佛系转换，成功与否，皆是玄学。