Coding & Development

MLAPP_CN_CODE is an open-source GitHub project dedicated to providing a comprehensive Chinese translation of Kevin P. Murphy's influential textbook, "Machine Learning: A Probabilistic Perspective." Beyond just translation, the project also includes Python implementations of the algorithms discussed in the book, making complex concepts more accessible. Users can find code files directly linked to the graphics within the translated articles, facilitating a deeper understanding of the theoretical material through practical application. The project is actively maintained, with recent updates covering topics like deep learning, decision theory, optimization, and information theory, ensuring its relevance and timeliness for students and researchers alike.

numpy_neural_network is an open-source project that allows users to implement neural networks from scratch using only NumPy. It covers essential components such as backpropagation formula derivation, construction of fully connected layers, convolutional layers, pooling layers, and Flatten layers. The project also includes various activation functions (ReLU, LeakyReLU, PReLU, ELU, SELU) and loss functions (mean squared error, cross-entropy). It provides practical examples for image classification and fine-tuning networks, making it an excellent resource for learning and experimenting with neural network architectures. The repository is continuously updated and offers insights into advanced topics like RNN, LSTM, GRU, and Batch Normalization.

Pinferencia is a Python library designed to be the simplest machine learning inference server ever. It allows users to deploy models with just a few lines of code, providing both a GUI and a REST API out-of-the-box. The tool supports various deep learning frameworks like Hugging Face, PyTorch, and TensorFlow, making it versatile for different model types. Pinferencia emphasizes minimal code and transformation, fast deployment, and robust testing with 100% test coverage. It also offers automatic API documentation with an online try-out feature and compatibility with Kserve API, ensuring easy integration with platforms like Kubeflow, TF Serving, Triton, and TorchServe.

RecSys is a comprehensive open-source repository dedicated to recommendation systems, computational advertising, and machine learning, with a strong emphasis on Click-Through Rate (CTR) and Conversion Rate (CVR) prediction. It serves as a valuable resource for developers and data scientists interested in these fields, offering a curated collection of learning materials, classic research papers, and practical tools. The repository covers a wide range of topics, from foundational statistical learning models to advanced deep learning architectures, and includes insights from real-world applications at major tech companies like Google, Alibaba, and Facebook. It also features practical code examples and references to significant industry competitions, making it an excellent resource for both theoretical understanding and hands-on implementation.

text-classification-cnn-rnn is an open-source project designed for Chinese text classification, leveraging both Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) built on TensorFlow. The project includes detailed implementations of both CNN and RNN models, along with scripts for data preprocessing, vocabulary building, and category mapping. It utilizes a subset of the THUCNews dataset, covering 10 categories such as sports, finance, and technology, with pre-defined training, validation, and test sets. Developers can train and evaluate models, with performance metrics like accuracy, precision, recall, and F1-score provided. The project is ideal for those looking to implement or understand text classification in Chinese using deep learning.

colab_stable_diffusion offers a Colab deployment of stable_diffusion_webui, designed to provide a customized and efficient Stable Diffusion experience. It comes pre-configured with popular plugin dependencies and initial settings, streamlining the setup process. Key features include a mod management system with thread pool parallel downloading, enabling faster deployment without occupying excessive cloud storage. The tool also incorporates JavaScript scripts for local image information reading, saving server interaction time and traffic, and automatic image saving. It supports mobile adaptation for a better user experience and allows for custom VAEs and plugins. The project is free, open-source, and continuously maintained, offering a powerful solution for AI image generation without requiring a dedicated graphics card.

stable-diffusion-webui-extensions serves as the official extension index for the Stable Diffusion Web UI, providing a centralized repository for users to find and integrate additional functionalities. This open-source project allows developers to submit their extensions, which are then reviewed and added to the index, making them accessible to a wider user base. The platform facilitates the customization and enhancement of stable diffusion workflows by offering a variety of extensions, each tagged for appropriate categorization. It includes guidelines for submitting new extensions, ensuring they are functional and properly described. The index also provides important tags like 'online' for extensions requiring external server connections and 'ads' for those containing advertisements, promoting transparency for users.

Starter-Guide, developed by the PKU-DAIR team, is an open-source repository designed to provide a comprehensive guide for beginners in the fields of data management (DM) and artificial intelligence (AI). It consolidates core papers and shared experiences from the team to help newcomers quickly familiarize themselves with cutting-edge areas and build a solid technical foundation. The guide covers various research directions including AI systems, AutoML, Database, AI Agent, Data-Centric ML, Diffusion Models, AI for Science, and Graph. It aims to support users in their learning and research journeys, whether they are just starting out or looking to deepen their understanding.

Warp-yg is a comprehensive, multi-functional script designed for managing WARP configurations. It offers seamless switching between warp-go and wgcf, providing flexibility for users. A key feature is its ability to generate an unlimited number of WARP-Wireguard configuration files, catering to diverse needs. The tool also supports upgrading WARP+ and WARP team accounts, enhancing connectivity options. Beyond configuration, Warp-yg allows users to check their VPS local IP address and determine the Netflix and ChatGPT unlock status, which is crucial for users relying on these services. The script is compatible with pure IPv4 and IPv6 VPS installations and supports mainstream Linux systems, making it a versatile solution for network management.

txt2mask is an addon for AUTOMATIC1111's Stable Diffusion Web UI, designed to simplify the inpainting process by automatically generating image masks from natural language prompts. Users can input a text string in img2img mode, and the tool, powered by clipseg, creates a corresponding mask, eliminating the need for manual brushwork. It offers features like adjustable mask precision, the ability to search for multiple objects using delimiters, and mask padding to refine selections. Additionally, users can define negative mask prompts to exclude specific areas and combine text masks with the brush tool or uploaded image masks for enhanced control. This script is ideal for those looking to streamline their Stable Diffusion inpainting workflow.

Whisper-Finetune is an open-source project designed to fine-tune the Whisper speech recognition model. It offers flexible training options, including support for data with or without timestamps, and even training without speech data. The tool significantly accelerates inference processes and provides versatile deployment capabilities across Web, Windows desktop, and Android platforms. It leverages techniques like Lora for fine-tuning and supports CTranslate2 and GGML for accelerated inference. The project includes detailed instructions for environment setup, data preparation, single and multi-GPU training, model merging, evaluation, and various prediction interfaces, making it a comprehensive solution for customizing and deploying Whisper models.

vibe-vibe is an open-source, systematic tutorial designed to make AI-assisted coding accessible to everyone, regardless of prior programming experience. It introduces the concept of "Vibe Coding," where users interact with AI through natural language to create applications, shifting the focus from writing code to conversational creation. The tutorial is structured into four main sections: a foundational 'Basic' part for AI programming essentials, an 'Advanced' section covering full product delivery, a 'Practice' section with project-based learning, and a 'Quality Articles' section for continuous learning. It aims to empower individuals, from students to entrepreneurs, to quickly realize their ideas and enhance productivity using AI.

TransGPT is the first open-source large language model specifically designed for the transportation industry in China. It aims to provide practical value by offering functionalities such as traffic condition prediction, intelligent consultation, public transportation services, traffic planning and design, traffic safety education, management assistance, and accident reporting and analysis. The model also supports autonomous driving assistance systems. TransGPT serves as a general knowledge base for various transportation sectors, including road, bridge, tunnel engineering, highway and waterway transportation, and urban public transport. It is available in two main models: TransGPT-7B and TransGPT-MM-6B, with both text and multimodal capabilities. The project provides training and inference code, along with commercial-use-approved datasets for pre-training and fine-tuning.

Tinyflow is a lightweight, open-source AI agent solution designed as a development component rather than a standalone product. It enables developers to integrate AI agent orchestration capabilities into existing applications. The frontend is built with Web Components, ensuring compatibility with popular frameworks like React, Vue, Angular, and Svelte, as well as native HTML, CSS, and JavaScript. For the backend, Tinyflow supports various languages including Java, Python, and Node.js, with Java backend implementation available and Python/Node.js versions currently under development. This flexibility makes Tinyflow a versatile tool for enhancing traditional applications with advanced AI agent functionalities.

Prompt-Engineering-Guide-Chinese is a comprehensive, open-source guide designed to help individuals understand and master prompt engineering. It is a translated and updated version of a popular English guide, specifically enhanced with AIGC (AI-Generated Content) prompt sections to make the learning process more accessible for Chinese-speaking users. The guide covers the development and optimization of prompts for effectively utilizing large language models (LLMs) across various applications and research topics. It aims to improve understanding of LLMs' capabilities and limitations, offering insights for researchers to enhance LLMs' performance on tasks like Q&A and arithmetic reasoning, and for developers to design powerful prompting techniques for LLM interfaces.

STUD is an open-source AI coding assistant specifically designed for Roblox Studio, offering deep integration to streamline development workflows. It enables developers to write and edit Luau scripts, manipulate game instances, and query DataStores directly from their terminal interface. Beyond Roblox-specific tasks, STUD functions as a general coding assistant, supporting file read/write/edit, glob and grep searches, and bash execution. The tool features a robust permission system, ensuring users approve sensitive actions like writes and shell commands, maintaining full control over every session. STUD is model-flexible, allowing users to configure different model providers and settings to suit their needs and budget, making it a versatile and powerful solution for Roblox developers.

GPU Finder is a platform designed to assist customers in discovering and comparing available GPU instances from various global public cloud providers. It provides information on GPU instances like NVIDIA A100, V100, and Tesla M40, helping users identify suitable options for their computing needs. The tool aims to simplify the process of finding and renting GPU servers, making it easier to access GPU computing platforms for tasks such as AI and machine learning workloads. By sourcing exchange rates and displaying real-time availability, GPU Finder helps users make informed decisions when selecting GPU instances.

wonderful-prompts is an open-source project featuring a meticulously curated collection of high-quality Chinese prompts designed to significantly enhance the usability and effectiveness of ChatGPT. This resource provides hundreds of prompts, complete with illustrative examples and usage guidelines, making it easier for users to master AI interactions. The project is continuously updated and encourages community contributions. It also offers a comprehensive ChatGPT Chinese guide, covering tutorials, selected open-source projects, and other AI tools, making it an invaluable resource for anyone looking to deepen their understanding and application of ChatGPT.

SoftSpell, formerly CodeSpell, is an AI-powered platform designed to accelerate and streamline the entire Software Development Life Cycle (SDLC) for enterprises. It offers a suite of tools including ReqSpell for requirements extraction and tracing, CodeSpell for AI-assisted code generation and documentation, and TestSpell for automated test case creation and validation. The platform focuses on modernizing legacy systems by transforming outdated applications, fragmented documentation, and rigid testing into scalable, AI-accelerated solutions. Key benefits include faster time-to-market, improved code consistency, reduced modernization risks, and predictable development timelines. SoftSpell integrates seamlessly across various IDEs, languages, and deployment pipelines, making it a comprehensive co-pilot for engineering teams.

ChatLM-mini-Chinese is an open-source project featuring a 0.2B parameter Chinese dialogue model (ChatLM-Chinese-0.2B). It provides comprehensive code for the entire model development lifecycle, including data cleaning, tokenizer training, model pre-training, SFT instruction fine-tuning, and RLHF optimization. The project is designed to be resource-efficient, capable of pre-training on machines with as little as 4GB VRAM and requiring only 512MB VRAM for float16 inference. It also supports downstream task fine-tuning, with an example provided for triplet information extraction. All dataset sources, data cleaning processes, and training procedures are openly shared, making it an excellent resource for researchers and developers working with small-scale Chinese language models.

cui was a modern web UI designed for Claude Code agents, powered by the Claude Code SDK. It offered browser-based access to agent sessions, enabling users to interact with and manage their Claude-based AI agents directly through a web interface. Key features included support for parallel background tasks, push notifications, and multi-model capabilities. The project has since been archived by its owner, as Anthropic has released official alternatives that supersede cui's functionality, such as Claude Code Web for cloud VM execution and Remote Control for accessing local Claude Code sessions.

SAG, developed by Zleap.AI, is an open-source, SQL-driven RAG engine designed for automatically building knowledge graphs during querying. It transforms raw text into "semantic atomic events" and extracts multi-dimensional "natural language vectors" for each event. Unlike traditional methods, SAG dynamically constructs relationship networks at query time, rather than relying on pre-maintained knowledge graphs. Its core capabilities include automatic understanding of documents, intelligent association through dynamic graph building, precise recall via a three-stage search (Recall → Expand → Rerank), complete traceability of results, and flexible extensibility with custom entity types. SAG is production-ready and suitable for developers, enterprise tech teams, and researchers interested in GraphRAG/RAG+KG.

SakuraLLM is an open-source, large language model designed for Japanese to Chinese translation, specifically optimized for light novels and Galgame content. It leverages SFT and RLHF models, incorporating knowledge of universal character and relationship attributes to deliver ACGN-style translations. The project emphasizes offline self-deployment and provides various model sizes, from 1.5B to 32B parameters, built upon Qwen model series. Key features include improved translation accuracy, support for glossaries (GPT dictionaries) to maintain consistency in proper nouns and pronouns, and enhanced retention of control characters. SakuraLLM also offers API support in OpenAI format, making it compatible with various existing translation tools and platforms.

Foolbox is a Python library designed to facilitate the creation of adversarial examples that can fool neural networks. Built on EagerPy, it offers native performance across PyTorch, TensorFlow, and JAX, allowing for a unified codebase without duplication. The toolbox provides a comprehensive collection of state-of-the-art gradient-based and decision-based adversarial attacks. It emphasizes type checking to catch bugs early and includes extensive documentation, guides, and tutorials for ease of use. Foolbox is ideal for machine learning researchers and security engineers focused on evaluating and improving the robustness of their models against adversarial attacks.