g-wellsa Claim this profile

一项关于大语言模型内在驱动力的诱饵实验与理论框架

当前 AI 工具都是"一个人干活"——你问一句，它回一句。**三和 3And 让 AI 变成一个团队**：你说一句话，天书(调度官)识别意图并派活，观澜(情报官)做调研分析，执戈(执行官)写代码做网页做游戏——三个 AI 角色自动分工、并行工作、互相验收、交付成果。

The "All-in-One GUI for Training and Detection or Segmentation with YOLOv8" simplifies object training, detection, and segmentation using the YOLOv8 model. Its user-friendly interface and advanced features make it suitable for various applications and reduce barriers to implementing advanced computer vision solutions.

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

Baidu Map MCP Server

MCP server for Taobao/Tmall product scraping integration with Claude

Chinese e-commerce MCP servers — let AI agents read merchant business data (Ocean Engine, Douyin Shop, JD.com, Taobao, Pinduoduo). 电商经营数据 MCP 连接器。

欢迎来到电子书下载宝库，一个汇聚了各类电子书下载链接的地方。无论你是喜欢阅读经典文学、经管励志、终身学习、职场创业、技术手册还是其他类型的书籍，这里都能满足你的需求。 该库涵盖了帆书app(原樊登读书)、微信读书、京东读书、喜马拉雅等读书app的大部分电子书。

Let's use AI to Earn!

Open-source AI job search: scan job portals, score listings A-F, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Gemini, Codex, OpenCode…)

汉语古典文本资料库

多源招聘信息爬虫 - OpenClaw Skill

一站式更换 WSL 的 apt, pip 和 npm 的镜像源到国内

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

We write your reusable computer vision tools. 💜

last30days-cn 是一个 AI Agent 技能（Skill），能够自动搜索中国互联网 8 大主流平台最近 30 天的内容，综合分析后生成有据可查的研究报告。

An agentic skills framework & software development methodology that works.

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

AgentCine 是一个面向 AI 漫剧/短剧创作的全流程工业级工作台，支持从文本分析、角色场景资产管理到分镜、配音与视频生成的统一协作。 AgentCine is an end-to-end workspace for AI-powered cinematic creation, unifying text analysis, character and scene asset management, storyboard editing, dubbing, and video generation.

Shared starter template configuration and CLAUDE.md memory bank system for Claude Code

Shannon Lite is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

Simplified Gemini for Claude Code.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

android platform agent

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

中文繁体和简体字符对照表

Claude Code国内如何使用 ？最容易懂的 Claude Code 介绍与教学指南（2026年最新）

180 个即插即用的 AI 专家人设（中文版）— 覆盖 17 个部门，支持 Claude Code / OpenClaw / Cursor / Trae 等 11 种工具 | Chinese AI agent personas for dev tools

A pixel office for your OpenClaw: turn invisible work states into a cozy little space with characters, daily notes, and guest agents. Code under MIT; art assets for non-commercial learning only.

多Agent可视化看板 - 实时展示OpenClaw Agent状态、任务进度和API异常

OpenClaw Q&A 社区 — AI Agent 记忆系统、多Agent架构、进化系统、具身AI | 龙虾茶馆 🦞

飞书多 Agent 协作方案 - 基于 OpenClaw

使用openclaw打造的，多Agent 产研团队，包含产品总监，架构设计师，测试经理，开发经理，一整个团队协作。

OpenClaw 社区 — 多 Agent 聊天群 + 页游社区，让 AI 实例像真人一样生活、工作、社交

A community collection of OpenClaw use cases for making life easier.

All versions of all skills that are on clawdhub.com archived

Android real-time display control software

ComfyUI wrapper for segment anything 3

Some awesome comfyui workflows in here, and they are built using the comfyui-easy-use node package.

Official front-end implementation of ComfyUI

🚀🧨📝 Series of Tutorials to learn about Jetpack Compose with subjects Material Widgets, Layout, SubcomposeLayout, custom layouts, State, custom rememberable, recomposition, LaunchedEffect, side-effects, Gesture, Animation, Navigation, Canvas, UIs like whatsapp and others.

Official Jetpack Compose samples.

RikkaHub is an Android APP that supports for multiple LLM providers.

Breakthrough Method for Agile Ai Driven Development

bmad-method使用教程及个人实践

所有小初高、大学PDF教材。

☁️A native Android app for ChatGPT, Gemini, Claude, and DeepSeek ☁️ChatGPT、Gemini、Claude 和 DeepSeek 的原生安卓应用程序

Virtual whiteboard for sketching hand-drawn like diagrams

API, CLI, and Web App for analyzing and finding a person's profile in 1000 social media \ websites

🎯 告别信息过载，AI 助你看懂新闻资讯热点，简单的舆情监控分析 - 多平台热点聚合+基于 MCP 的AI分析工具。监控35个平台（抖音、知乎、B站、华尔街见闻、财联社等），智能筛选+自动推送+AI对话分析（用自然语言深度挖掘新闻：趋势追踪、情感分析、相似检索等13种工具）。支持企业微信/飞书/钉钉/Telegram/邮件/ntfy推送，30秒网页部署，1分钟手机通知，无需编程。支持Docker部署⭐ 让算法为你服务，用AI理解热点

bestblogs.dev - 汇集顶级编程、人工智能、产品、科技文章，大语言模型摘要评分辅助阅读，探索编程和技术未来

No description.

高性能 高精度 大陆车牌、港澳车牌、台湾车牌识别 代码开源，方便移植嵌入式和安卓端使用，支持12种车牌识别，支持港澳车牌识别，支持大角度车牌识别，准确率高达99%+

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

ChatGLM-6B：开源双语对话语言模型

A complete implementation of Airplay Server(Receiver)

Java Chromium Embedded Framework (JCEF). A simple framework for embedding Chromium-based browsers in other applications using the Java programming language.

Adds touch functionality to Android ImageView.

一键将视频和音频转化为小红书/公众号/知识笔记/思维导图/视频字幕等各种风格的文档。

Android wav/pcm 录音机，支持暂停、再录制。支持跳过静音区模式。

No description.

中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、IT词库、财经词库、成语词库、地名词库、历史名人词库、诗词词库、医学词库、饮食词库、法律词库、汽车词库、动物词库、中文聊天语料、中文谣言数据、

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

The JoyTag Image Tagging Model

移动端快速人脸检测模型是基于RetinaFace的优化去掉stride8以及stride32和stride16的landmark 在CPU位Intel(R) Pentium(R) CPU G2020 @ 2.90GHz(2900 MHz)的设备中人脸检测可达到40ms/帧

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Fast and Simple Face Swap Extension for StableDiffusion WebUI (A1111 SD WebUI, SD WebUI Forge, SD.Next, Cagliostro)

Xiangqi syncing tool based on Yolov5 / 基于Yolov5的中国象棋连线工具

通用规范汉字表+拼音+笔画+部首+五行

UPnP/DLNA library for Java

基于DLNA实现iOS投屏，SSDP发现设备及SOAP控制设备

Ant Media Server is a live streaming engine software that provides adaptive, ultra low latency streaming by using WebRTC technology with ~0.5 seconds latency. Ant Media Server is auto-scalable and it can run on-premise or on-cloud.

Lightweight low-latency RTSP client library for Android

动态抓取wss链接获取抖音弹幕

一个可在Minecraft内获取抖音直播弹幕的Fabric mod

Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别

yolov8s在rk3588的推理部署，并使用多线程池并行npu推理加速

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Android Voice Activity Detection (VAD) library. Supports WebRTC VAD GMM, Silero VAD DNN, Yamnet VAD DNN models.

Concurrently chat with ChatGPT, Bing Chat, bard, Alpaca, Vincuna, Claude, ChatGLM, MOSS, iFlytek Spark, ERNIE and more, discover the best answers

获取斗鱼&虎牙&哔哩哔哩&抖音&快手等 58 个直播平台的真实流媒体地址(直播源)和弹幕，直播源可在 PotPlayer、flv.js 等播放器中播放。

Labeling tool with SAM(segment anything model),supports SAM, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

FFmpegMediaMetadataRetriever provides a unified interface for retrieving frame and meta data from an input media file.

All Documant Reader App (Word,PDF,PPT,Excel)

android DocViewer support view word excel ppt pdf txt image in sdcard & uri & assets & url

Plugin of rtmp-rtsp-stream-client-java to stream directly to RTSP player.

ijkplayer open the rtsp & h265 surpport android demo .

2023年最新整理 c++后端开发，1000篇优秀博文，含内存，网络，架构设计，高性能，数据结构，基础组件，中间件，分布式相关

高铁车载使用RTSP协议实现投屏产品Deme，相比DLNA和WifiDisplay提高设备兼容性。

python 打包成EXE GUI控制台

comfyui-模特换装(Model dress up)

自定义Comfyui节点

一款用于在Android设备上获取照片（拍照或从相册、文件中选择）、裁剪图片、压缩图片的开源工具库

No description.

简易版汤姆猫( 动作基本都实现了，音频的同步还待改进 )

简介：无需数据库，以《钦定协纪辨方书》为核心的python3 农历、黄历、二十四节气、节假日、星次、每日凶煞、每日值神、建除十二神、每日宜忌、彭祖百忌、每日五行、二十八星宿、天干地支、生辰八字、时辰凶吉等开源项目。背景： 由于三体运动（主要地球、太阳、月球）无法准确预测，目前二十四节气依然还是靠天文台观测，Yovey使用传说中[Y*D+C]-L 寿星通用公式 方法实际有很多天数不准，def getSolarTerms(_date)12个if嵌套判断让代码变得十分冗余，由简书网友“大咖_247c”首先发现计算不准问题……

使用姿态识别来玩游戏

Cross-platform, customizable ML solutions for live and streaming media.

🔥🔥🔥Banner 2.0 来了！Android广告图片轮播控件，内部基于ViewPager2实现，Indicator和UI都可以自定义。

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

The break time reminder app

(DEPRECATED) Fast and Simple Face Swap Extension for StableDiffusion WebUI (A1111, SD.Next, Cagliostro) with NVIDIA GPU Support

chatGPT + 百度云API + Stable Diffusion + MoviePy + fastapi

Real-time image and video processing library similar to GPUImage, with built-in beauty filters, achieving commercial-grade beauty effects. Written in C++11 and based on OpenGL/ES.

Inference code for LLaMA models

Adafruit 16 Channel Servo Driver for NVIDIA Jetson Development Kit

含楷体等多种字体

Code examples for running V4L2 USB Cameras on NVIDIA Jetson Developer Kits

Pytools: Some useful tools written by pure python.

Fay是一个完整的开源项目，包含Fay控制器及数字人模型，可灵活组合出不同的应用场景：虚拟主播、现场推销货、商品导购、语音助理、远程语音助理、数字人互动、数字人面试官及心理测评、贾维斯、Her。 开源项目，非产品试用！！！

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

Fast Segment Anything

Effortless data labeling with AI support from Segment Anything and other awesome models.

Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

Objects365/COCO数据集转换为xml格式，并转为yolo的txt格式，xml数据统计更改

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

Auto-Editor: Effort free video editing!

一个一站式yolov8整合包

Convolutional Neural Networks

中文LLaMA-2 & Alpaca-2大模型二期项目 + 16K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs, including 16K long context models)

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

二维码/条码识别、身份证识别、银行卡识别、车牌识别、图片文字识别、黄图识别、驾驶证（驾照）识别

CnOCR: Awesome Chinese/English OCR toolkits based on PyTorch/MXNet, It comes with 20+ well-trained models for different application scenarios and can be used directly after installation. 【基于 PyTorch/MXNet 的中文/英文 OCR Python 包。】

图灵商城

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

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

Voice data <= 10 mins can also be used to train a good VC model!

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.

one-click deepfake (face swap)

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

NLP_Study_Demo

🔊 Text-Prompted Generative Audio Model

C++ library for audio and music analysis, description and synthesis, including Python bindings

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.

:iphone: Home Assistant Companion for Android

A Simple and Efficient Implementation Of Fast Fourier Transform For Audio Denoise

Auto-GPT中文版本及爱好者组织 同步更新原项目 AI领域创业 自媒体组织 用AI工作学习创作变现

汇总那些ChatGPT的平替们，仅汇总那些开源代码/模型文件以及对话语料，闭源或者部分闭源的暂时不在统计范围内

ChatGPT Java SDK支持流式输出。支持OpenAI官方所有接口。ChatGPT的Java客户端。OpenAI GPT-3.5-Turb GPT-4 Api Client for Java

本项目使用了EcapaTdnn模型实现的声纹识别

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

No description.

探索中文instruct数据在ChatGLM, LLaMA上的微调表现

Let ChatGPT teach your own chatbot in hours with a single GPU!

🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目，支持ChatGPT对话能力，还可能是首个支持脑机交互的开源智能音箱项目。

Material theme music player that works across all form factors (phones, wear, auto, cast, assistant) and uses latest tools (Kotlin, Architecture components, Room, Databinding)

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.

ChineseSemanticKB,chinese semantic knowledge base, 面向中文处理的12类、百万规模的语义常用词典，包括34万抽象语义库、34万反义语义库、43万同义语义库等，可支持句子扩展、转写、事件抽象与泛化等多种应用场景。

DomainWordsDict, Chinese words dict that contains more than 68 domains, which can be used as text classification、knowledge enhance task。涵盖68个领域、共计916万词的专业词典知识库，可用于文本分类、知识增强、领域词汇库扩充等自然语言处理应用。

Running large language models on a single GPU for throughput-oriented scenarios.

No description.

LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.

用 moviepy 把图片生成视频

Stable Diffusion web UI

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

安卓平台自动化工具，无需 root。

自媒体平台自动上传视频贴标签发布

Making large AI models cheaper, faster and more accessible

意识诞生的一点见解~

A mutex/semaphore implementation made easy to use.

本项目使用了EcapaTdnn模型实现的声纹识别

🔈 Use python to achieve voice activity detection, this little program may be helpful for voice application

Long-form text-to-images generation, using a pipeline of deep generative models (GPT-3 and Stable Diffusion)

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

手部识别操控机械臂

🔥🔥🔥Flexible and useful UVC camera engine on Android platform, supporting multi-road cameras!

library and sample to access to UVC web camera on non-rooted Android device

lib, demo, model, data

《统计学习方法》的代码实现

致力于将李航博士《统计学习方法》一书中所有算法实现一遍

手写实现李航《统计学习方法》书中全部算法

Awesome pre-trained models toolkit based on PaddlePaddle.(300+ models including Image, Text, Audio and Video with Easy Inference & Serving deployment)

Easy-to-use and Fast NLP library with awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications.

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

Multi-platform high performance deep learning inference engine (飞桨多端多平台高性能深度学习推理引擎）

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

Leading free and open-source face recognition system

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

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

1、仿泰捷视频最新TV版 Metro UI效果. 2、仿腾讯视频TV版(云视听·极光) 列表页

Convenient image annotation tool API

🔥🔥Defending Against Deepfakes Using Adversarial Attacks on Conditional Image Translation Networks

Towards deepfake detection that actually works

Android应用开发最强原创知识体系

中华人民共和国行政区划：省级（省份直辖市自治区）、 地级（城市）、 县级（区县）、 乡级（乡镇街道）、 村级（村委会居委会） ，中国省市区镇村二级三级四级五级联动地址数据。

Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.

opencv检擦形状和颜色

android studio 2.2+ ndk 15编译 polarssl

android studio 2.2+ ndk 15编译zlib

android studio 2.2+ ndk 15编译 rtmpdump

SDL用Cmake编译到Android平台

Android平台编译SDL2

A util for setting status bar style on Android App.

samples to handling multimedia data