Javis486

llm-compressor. Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

LocateAnything-vLLM. use vLLM with nvidia/LocateAnything-3B (develop and test and 2080ti s)

auto-yolo. 本地YOLO模型数据闭环平台：大模型生图 → 自动标注 → 手动修正 → 一键训练 → 模型测试

mem0. Universal memory layer for AI Agents

FlowPilot. Chrome扩展：支持Codex / kiro / Grok注册、验证码获取、CPA/sub回调验证与自动恢复

openhuman. Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.

DeepSeek-Reasonix. DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

any-auto-register. Auto-register & manage accounts for ChatGPT, Cursor, Kiro, Grok, Windsurf, Trae & 13+ AI platforms · Protocol/browser dual-mode · Plugin-based · One-click Mac/Windows desktop app

deepagents. The batteries-included agent harness.

OpenHarness. "OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"

ClaudeCode-Python. 用 ~5000 行 Python 还原 CC 的核心 Agent Runtime。

AutoJs6. 安卓平台 JavaScript 自动化工具 (Auto.js 二次开发项目)

wecom_aibot_sdk. 企业微信智能机器人websocket python sdk

nanobot. Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

mini-openclaw. A hands-on AI Agent teaching and research project — build a phenomenal agent from scratch by studying the OpenClaw architecture.

WeChat3.9-32bit-Compatibility-Launcher. 让微信3.9.12 32位版本能够在64位Windows操作系统上正常运行，并且不显示"版本过低"的提示

Qwen3-TTS. Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

awesome-agent-skills. Agent Skills 终极指南：快速入门、资源推荐、精选技能与实用工具 ｜The Ultimate Guide to Agent Skills: QuickStart, Resources, Features&Toolkit

ShizhenGPT.

Chinese-medical-dialogue-data. Chinese medical dialogue data 中文医疗对话数据集

TensorRT-YOLO11. Based on tensorrt v8.0+, deploy detection, pose, segment, tracking of YOLO11 with C++ and python api.

silero-vad. Silero VAD: pre-trained enterprise-grade Voice Activity Detector

index-tts-vllm. Added vLLM support to IndexTTS for faster inference.

kokoro. https://hf.co/hexgrad/Kokoro-82M

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

MuseTalk. MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

index-tts. An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Baichuan-M2-32B. Beyond the Model: Scaling Medical Capability with a Large Verifier System

DeepSeek-OCR. Contexts Optical Compression

python3-cookbook. 《Python Cookbook》 3rd Edition Translation

fastrtc-local-cn. 使用本地模型，实现实时AI语音对话，适用于中文环境。

inference. Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

ai-tools-mng. 基于 Tauri 的跨平台桌面应用，用于管理多平台 AI 账号 Augment、Antigravity、Windsurf、Cursor、OpenAI（Codex、API）、Claude Code 与 API 账号，以及订阅、书签管理与邮箱管理。A Tauri-based cross-platform desktop app for managing multi-platform AI accounts (Augment, Antigravity, Windsurf, Cursor, OpenAI Codex/API, Claude Code and API), plus subscriptions, bookmarks, and email management.

website. AGE animation official website URL release page（AGE动漫官网网址发布页）

cursor-free-everyday. 完全免费, 自动获取新账号,一键重置新额度, 解决机器码问题, 自动满额度

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

LiveTalking. Real time interactive streaming digital human

WeChatMsg.

gewechat-python. gewechat python client

memobase. User Profile-Based Long-Term Memory for AI Chatbot Applications.

learning-langchain. Python

dify-on-wechat. 本项目为 chatgpt-on-wechat下游分支, 额外对接了LLMOps平台 Dify，同时支持gewechat，相比itchat更加稳定。

Gewechat. 微信机器人框架，个人微信二次开发，最简单易用的免费二开框架,微信ipad登录（非HOOK破解桌面端）

WXBizMsgCrypt. WXBizMsgCrypt for python 3 and cryptography

WindTerm. A professional cross-platform SSH/Sftp/Shell/Telnet/Tmux/Serial terminal.

LLMs-Zero-to-Hero. 从无名小卒到大模型（LLM）大英雄~ 欢迎关注后续！！！

langchain. The agent engineering platform.

DeepSeek-R1-FineTuning. Fine-Tuning of DeepSeek-Style Reasoning Models | RL + Quantization Implementation

Pytorch_practice. Some cases for pytorch

annotated-transformer. An annotated implementation of the Transformer paper.

kvm. C

qemu. Official QEMU mirror. Please see http://wiki.qemu.org/Contribute/SubmitAPatch for how to submit changes to QEMU. Pull Requests are ignored. Please only use release tarballs from the QEMU website.

TechXueXi. 强国通 科技强国 学习强国 xuexiqiangguo 全网最好用开源网页学习强国助手：TechXueXi （懒人刷分工具 自动学习）技术强国，支持答题，支持 docker 45分/天

techxuexi-js. 油猴等插件的 学习强国 js 代码 45分/天

XXQG_TiKu. 学习强国 挑战答题题库 (已适配新版本)

design-pattern. Python3实现设计模式，致力于将设计模式的思想应用在开发中。创建型模式有：简单工厂模式、工厂方法模式、抽象工厂模式、 建造者模式和单例模式；结构型模式：适配器模式、桥模式、组合模式、外观模式和代理模式；行为型模式：责任链模式、观察者模式、策略模式和模板方法模式。设计模式是对软件设计中普遍存在或反复出向的各种问题所提出的解决方案。每一个设计模式系统地被命名、解释和评价了面向对象系统中一个重要和重复出现的设计。

bypyoauth. The OAuth relay server for bypy

AndroidHttpCapture. AndroidHttpCapture网络诊断工具 是一款Android手机抓包软件 主要功能包括：手机端抓包、PING/DNS/TraceRoute诊断、抓包HAR数据上传分享。你也可以看成是Android版的"Fiddler" \(^o^)/~

xuexi.cn. 学习强国 挑战答题 题库，⭐⭐⭐⭐⭐更新至2424+题⭐⭐⭐⭐⭐ 仅供学习交流，欢迎大家补充、完善。

modern-cpp-tutorial. 📚 Modern C++ Tutorial: C++11 to C++26 On the Fly | https://changkun.de/modern-cpp/

bypy. Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端

music-dl. search and download music 从网易云音乐、QQ音乐、酷狗音乐、百度音乐、虾米音乐、咪咕音乐等搜索和下载歌曲

UNet-Zoo. A collection of UNet and hybrid architectures in PyTorch for 2D and 3D Biomedical Image segmentation

ncnn-andriod-retainface. retainface-mobilenetv2.5 for andriod

RetinaFace_NCNN_Android_demo. A retinaface android demo based on ncnn.

DBNet.pytorch. A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization

DB. A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

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.

DeepLearningDeployment. Examples and tools for deep learning deployment

CBAM.PyTorch. Non-official implement of Paper：CBAM: Convolutional Block Attention Module

FaceRecognitionWithMask. Quickly build a server to face recognition with mask

pytorch-distributed. A quickstart and benchmark for pytorch distributed training.

LSHash. A fast Python implementation of locality sensitive hashing.

Face-Detector-1MB-with-landmark. 1M人脸检测模型(含关键点)

Pytorch_Retinaface. Retinaface get 80.99% in widerface hard val using mobilenet0.25.

insightface. State-of-the-art 2D and 3D Face Analysis Project

dlib-models. Trained model files for dlib example programs.

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

FaceMaskDetection. 开源人脸口罩检测模型和数据 Detect faces and determine whether people are wearing mask.

Real-World-Masked-Face-Dataset. Real-World Masked Face Dataset，口罩人脸数据集

spinal_detection_baseline. Python

big_transfer. Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.

CenterNet-pytorch-detection-simple-tutorial. Python

labelme-for-dicom. 使得labelme能够看和标注ct图像。

nocode. The best way to write secure and reliable applications. Write nothing; deploy nowhere.

taichi. Productive, portable, and performant GPU programming in Python.

12306. 12306智能刷票，订票

autojs. autojs 脚本集

Auto.js. Automation&Workflow JavaScript IDE on Android(安卓平台上的JavaScript编程IDE)

DPlayer. :lollipop: Wow, such a lovely HTML5 danmaku video player

kudu-rpm. RPM packages for Apache Kudu on CentOS 7

jQuery.print. Easy to use, Element Printing Plugin for jQuery

h-player-v2. 资源采集站在线播放

BioSPPy. Biosignal Processing in Python

TextMatch. QAmatch(qa_match)/文本匹配/文本分类/文本embedding/文本聚类/文本检索（bow/ifidf/ngramtf-df/bert/albert/bm25/…/nn/gbdt/xgb/kmeans/dscan/faiss/….）

interview_internal_reference. 2025年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。

QuestionAnsweringSystem. QuestionAnsweringSystem是一个Java实现的人机问答系统，能够自动分析问题并给出候选答案。

high-speed-downloader. 已不再维护

bcbio-nextgen. Validated, scalable, community developed variant calling, RNA-seq and small RNA analysis

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

pyensembl. Python interface to access reference genome features (such as genes, transcripts, and exons) from Ensembl

u_net_liver. Python

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.

Detectron.pytorch. A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

kmcEx. C++

tianchi_lvcai. 天池竞赛Baseline分享（2018广东工业智造大数据创新大赛——智能算法赛，线上0.921无调参）

TIANCHI_XUELANG_AI_2. 天池雪浪布匹瑕疵检测，复赛线上746，排名14/2403

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

TIANCHI_XUELANG_AI. 天池雪浪布匹瑕疵检测，初赛线上949，排名9/2403

faster-rcnn.pytorch. A faster pytorch implementation of faster r-cnn

XueLangTianchi. 雪浪制造AI挑战赛—视觉计算辅助良品检测

sceneReco. ctpn+crnn Scene character recognition

PaintsChainer. line drawing colorization using chainer

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

imgaug. Image augmentation for machine learning experiments.

roi-pooling. C++

unet. unet for image segmentation

Mask_RCNN. Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

PyTorch-Tutorial. Build your neural network easy and fast, 莫烦Python中文教学

group_normalization. pytorch implementation of group normalization in https://arxiv.org/abs/1803.08494

sppnet-pytorch. A simple Spatial Pyramid Pooling layer which could be added in CNN

iGAN. Interactive Image Generation via Generative Adversarial Networks

deeplearning-biology. A list of deep learning implementations in biology

TensorFlowLaboratory. Research about Tensorflow

minepy. minepy - Maximal Information-based Nonparametric Exploration