FelixChen

libemf2svg. Microsoft (MS) EMF to SVG conversion library

LeaferJS. 绚丽多彩的 HTML5 Canvas 2D 图形渲染引擎， 可结合 AI 绘图、生成界面。能让你拥有瞬间创建 100 万个图形的超强能力，免费开源、易学易用、场景丰富。

StealthHumanizer. 🔓 Free open-source AI text humanizer — bypass GPTZero, Turnitin & AI detectors with 16+ Languages support. 35 providers, 4 rewrite levels, 6 Writing Styles, 9 Text Purposes, 13 Tone Presets, multi-pass ninja mode. No login. Built for students & writers.

kiss-translator. A simple, open source bilingual translation extension & Greasemonkey script (一个简约、开源的 双语对照翻译扩展 & 油猴脚本)

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

docker-thunderbird. Web accessible Thunderbird inside an Ubuntu Container

moosey-cms. A drop-in Markdown CMS for FastAPI with Hot Reloading

saleor. Saleor Core: the high performance, composable, headless commerce API.

3x-ui. Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Hysteria, Tunnel, Mixed, HTTP, Tun, MTProto)

nps. 基于NPS 0.26.10 版本二开而来，NPS接力项目。

nps. NPS Enhanced — Lightweight intranet tunneling and reverse proxy with Web UI | NPS 内网穿透 反向代理 增强版 全修 新版 二开

PasteMD. 一键将 Markdown 和网页 AI 对话（ChatGPT/DeepSeek等）完美粘贴到 Word、WPS 和 Excel 的效率工具 | One-click paste Markdown and AI responses (ChatGPT/DeepSeek) into Word, WPS, and Excel perfectly.

SenseVoice. Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

FunASR. Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

PyMuPDF. PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

ubisoft-laforge-binaryalign. BinaryAlign: Word Alignment as Binary Sequence Labeling

simalign. [EMNLP 2020] Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)

stalwart. All-in-one Mail & Collaboration server. Secure, scalable and fluent in every protocol (IMAP, JMAP, SMTP, CalDAV, CardDAV, WebDAV).

RapidLayout. Analysis of Chinese and English layouts 中英文版面分析

chatbox. Powerful AI Client

langextract. A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

paddle2onnx-PP-DocLayoutV2. Python

pp_doclayoutv2_ov. Using OpenVINO to speed up inference of PP-DocLayoutV2 model

PageIndex. 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

ZLUDA. CUDA on non-NVIDIA GPUs

docxjs. Docx rendering library

GOT-OCR2.0. Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

unitable. UniTable: Towards a Unified Table Foundation Model

RapidTable. 基于序列表格识别算法推理库，集成PP-Structure和modelscope等表格识别算法。

EasyTier. A simple, decentralized mesh VPN with WireGuard support.

web_b2b. 独立站搭建教程。基于搬瓦工服务器搭建的B2B企业网站，适用于外贸独立站、企业官网、产品官网等场景。

automerge-py. Python

lingua-rs. The most accurate natural language detection library for Rust, suitable for short text and mixed-language text

omml2mml. 提取office mathml(word公式) 转换为mathml

dwml. Convert omml to latex for displaying in web browsers (KaTeX)

camelot. A Python library to extract tabular data from PDFs

NVIDIA-patcher. Adds 3D acceleration support for P106-090 / P106-100 / P104-090 / P104-100 / P102-100 / CMP 30HX / CMP 40HX / CMP 50HX / CMP 70HX / CMP 90HX / CMP 170HX mining cards as well as RTX 3060 3840SP, RTX 3080 Ti 20 GB, RTX 4070 10 GB, L40 ES, and RTX 5080M ES N22W-ES-A1.

pyo3. Rust bindings for the Python interpreter

openaiee. OepnaiEE 支持多个 API 服务集成，包括 OpenAI、Groq、Gemini 和 Claude，使其能够在 Vercel 和 Netlify 等平台上快速部署。

OnnxOCR. 基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.

TableStructureRec. 整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX | Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.

Dolphin. The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

docling. Get your documents ready for gen AI

DailyHot. DailyHot 今日热榜前端页面 | API：https://github.com/imsyy/DailyHotApi

playwright-python. Python version of the Playwright testing and automation library.

mupdf. mupdf mirror

docutranslate. 文档（小说、论文、字幕）翻译工具（支持 pdf/word/excel/json/epub/srt...）Document (Novel, Thesis, Subtitle) Translation Tool (Supports pdf/word/excel/json/epub/srt...)

Pix2Text. An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

PolyglotPDF. (eBook，PDFs Translation) A multilingual eBook processing tool supporting all eBook formats. Features online and offline translation while preserving original layouts. Compatible with both scanned and digital PDFs. Elegant user interface. The world's highest-performing open-source layout-preserving eBook translator.

SVG2HTML. Python

pdf-document-layout-analysis. A Docker-powered service for PDF document layout analysis. This service provides a powerful and flexible PDF analysis service. The service allows for the segmentation and classification of different parts of PDF pages, identifying the elements such as texts, titles, pictures, tables and so on.

ChatGPT-Next-Web. A well-designed cross-platform ChatGPT UI (Web / PWA / Linux / Win / MacOS).

MegaTTS3. Python

MathTranslate. translate scientific papers in latex, especially arxiv papers

PolyglotPDF-fonts. PolyglotPDF的字体文件库

Xiangcui-Dengcusong. 香萃等粗宋，一款开源中文字体项目

AdaptoFlux. An algorithm that implements intelligence based on a Method pool (a collection containing multiple types of functions). 一种基于方法池（包含多种类型的函数的集合）实现智能的算法

DocLayout-YOLO. DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

md2word. md转为word,包括latex语法公式和表格内容，完美解析llms输出md报告转为word

ArxivFlow. ArxivFlow - Periodic Track on arXiv Paper

Test2504. Python

latex2md. latex to md

core. Read-only LibreOffice core repo - no pull request (use gerrit instead https://gerrit.libreoffice.org/) - don't download zip, use https://dev-www.libreoffice.org/bundles/ instead

lobehub. 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

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

Neural-Network-Accelerator. A Convolutional Neural Network Accelerator implementation on FPGA, xilinx （xczu7ev-ffvc1156-2-i）, The inference of yolov8 took 60ms.

ocr-based-qwen. 接口已恢复 | 基于 https://chat.qwenlm.ai/ 的OCR。测试Token：可见readme 。已支持Docker一键部署,切换分支可见

EasyTcp4Net. A high-performance TCP communication package developed by .NET that supports multiple unpacket strategies

Humanize-AI. Humanize is an undetectable AI bypass ALL detectors, including Originality.ai, GPTZero, Turnitin, etc.

Stark. 基于Spark+SparkMLlib+Debezium+Deequ打造的简单易用、超高性能大数据治理引擎。适用于批流一体的数据集成和数据分析，支持CDC实时数据采集、机器学习算法模型、数据质量校验、数据标注、敏感数据识别、数据建模、算法建模和OLAP数据分析

SocialED. A python library for social event detection

small-doge. Doge Family of Small Language Models

jyf-drawing-board. jyf-drawing-board是一个背景透明的Web画板项目，使用HTML5 的<canvas>元素来实现绘图功能。

PaperPlume. ai creat your paper

marktext. 📝A simple and elegant markdown editor, available for Linux, macOS and Windows.

whisperX. WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

whisper_streaming. Whisper realtime streaming for long speech-to-text transcription and translation

RealtimeTTS. Converts text to speech in realtime

LatexToMathML. Latex转Word格式的公式

EasyTrans. 支持谷歌翻译、百度翻译、有道翻译的免费接口，基于Django、PyMuPDF实现了pdf文档英译汉的功能，翻译后的pdf格式基本保持不变，可以下载docx和pdf格式的翻译文档，基本解决复制caj中文论文时的格式问题，简单的满足看论文以及写总结的需求。

Office-Add-in-samples. Code samples for Office Add-in development on the Microsoft 365 platform.

whisper_real_time. Real time transcription with OpenAI Whisper.

speaches. Python

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

whisper_streaming_CN. Whisper realtime streaming for long speech-to-text transcription and translation

FileUploading. A Simple yet functional File Uploading WebApp, with HTML, CSS and JAVASCRIPT

pdf2htmlEX. Convert PDF to HTML without losing text or format.

HMGC. COLING'24 Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack

recycleMe. A script written in Golang to help detect and humanize text flagged as AI generated content.

Ace-Translate. 一款纯离线、隐私安全的本地化多模态翻译工具，支持文本、划词、截图、图片及文件翻译，并集成多语言ASR与TTS。

pdf-c. 📄➡️🔁📃 PDF-C 🔄 Convert PDFs to DOCX, PNG, or TXT with a simple upload. Files auto-delete after 3 minutes for your security! 💼🔒🕒

pdf-translator. pdf-translator translates English PDF files into Japanese, preserving the original layout.

boss-crawler. boss直聘爬虫，使用 nodejs 和 selenium 实现，可以指定职位，获取所有有记录的城市中该岗位信息。其中表格生成使用 ExcelJs，验证码识别借助第三方平台”图鉴“。

ai-humanizer. AI Humanizer

marked. A markdown parser and compiler. Built for speed.

doc2dataset. A tool to extract text (and images) from documents (like PDFs)

ChatGPT-Next-Web-LangChain. 一键拥有你自己的 ChatGPT 网页服务。 One-Click to deploy your own ChatGPT web UI.（基于 langchain 实现的插件版本 Plugin version implemented based on langchain）

extract-info-from-pdf-paper. This Python script uses pdfminer.six, PyPDF2, pdf2image to extract information (text, image) from pdf paper.

pdf2md. Convert PDF to Markdown and TXT

pdf2md-. convert psf to mark down

pdf2md-. convert psf to mark down

pdf2md. This project, pdf2md, transforms academic paper PDF files into digestible text files. By analyzing the layout of the PDF file, the application restructures paragraphs and translates desired content. The final result is a conveniently exported text file.

nougat. Implementation of Nougat Neural Optical Understanding for Academic Documents

marker. Convert PDF to markdown + JSON quickly with high accuracy

Stirling-PDF. #1 PDF Application on GitHub that lets you edit PDFs on any device anywhere

AiTextDetectionBypass. Bypass Ai detection using undetectable.ai

gscholar. Query Google Scholar with Python

make-real-starter. Make it real

languagetool. Style and Grammar Checker for 25+ Languages

noodle. Rethinking Student Productivity

GraphGPT. Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️‍♂️

pdfGPT. PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!

Open-Generative-AI. Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 500+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.

Product. B站一键智能爬取弹幕+评论，可视化分析。

Paryatana. A front-end website for travel agency.

tiktoken. tiktoken is a fast BPE tokeniser for use with OpenAI's models.

chatbot-ui. AI chat for any model.

chatgpt-style-ui. An open source ChatGPT UI.

ChatGLM-vits-Unity-Live2D. C#

Digital_Life_Server. Yet another voice assistant, but alive.

polyglot. 🤖️ Cross-platform AI language practice app （跨平台AI语言练习应用）

openedx-platform. The Open edX LMS & Studio, powering education sites around the world!

ruoyi-vue-pro. 🔥 官方推荐 🔥 RuoYi-Vue 全新 Pro 版本，优化重构所有功能。基于 Spring Boot + MyBatis Plus + Vue & Element 实现的后台管理系统 + 微信小程序，支持 RBAC 动态权限、数据权限、SaaS 多租户、Flowable 工作流、三方登录、支付、短信、商城、CRM、ERP、MES、IM、AI 大模型、IoT 物联网等功能。你的 ⭐️ Star ⭐️，是作者生发的动力！

mall. mall项目是一套电商系统，包括前台商城系统及后台管理系统，基于Spring Boot+MyBatis实现，采用Docker容器化部署。 前台商城系统包含首页门户、商品推荐、商品搜索、商品展示、购物车、订单流程、会员中心、客户服务、帮助中心等模块。 后台管理系统包含商品管理、订单管理、会员管理、促销管理、运营管理、内容管理、统计报表、财务管理、权限管理、设置等模块。

chatdoc. Chat with your doc by openai

springboot-project. 这是一个用SpringBoot+JPA打造的基于微信服务号平台的点餐系统的后端，前端是一个使用Vue.js构建的运行于微信公众号的WebApp。前后端完全分离，前后端之间通过RESTful风格的接口相连。

cursor.

springboot_seed. A springboot seed project with features and configuration to start good

chatgpt-resume-builder. Python

chatpdf-minimal-demo. a minimal viable project of chatpdf

mybatis-3. MyBatis SQL mapper framework for Java

J.A.R.V.I.S. Iron man inspired Personal virtual assistant

awesome-project-ideas. Curated list of Machine Learning, NLP, Vision, Recommender Systems Project Ideas

CowAgent. Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)