Coding & Development

Code Converter is a free online tool designed for developers to instantly convert code between more than 30 programming languages. Leveraging AI, it facilitates real-time translation between popular languages such as JavaScript, Python, Java, C++, and TypeScript. The platform supports a wide array of languages, from common ones like PHP, C#, and Go to more specialized ones like Rust, R, MATLAB, and Scala. Users can paste their source code, select the desired input and output languages, and receive converted code quickly. It also includes features like conversion history, syntax highlighting, and the ability to copy converted code to the clipboard, making it a practical resource for developers needing quick syntactical translations.

Swift-Concurrency-Agent-Skill offers comprehensive Swift Concurrency guidance for AI coding tools, leveraging the Agent Skills open format. It's designed to assist with safe concurrency practices, performance optimization, and seamless migration to Swift 6. Based on an extensive Swift Concurrency Course, this skill distills complex knowledge into actionable, concise references for AI agents. It is particularly beneficial for teams transitioning to Swift 6 or strict concurrency, developers debugging data races or isolation errors, and anyone seeking performance-minded concurrency patterns like actors, tasks, Sendable, and async streams. The skill provides expert knowledge, is non-opinionated, and is ready for Swift 6.2 features, including default actor isolation and global actor conformance for protocols.

Goast.ai is an AI-powered assistant designed to streamline the bug-fixing process for engineering teams. It integrates with popular error monitoring platforms like Sentry, Datadog, BugSnag, and Google Cloud to automatically analyze and resolve issues from error logs. Goast.ai can perform root cause analysis, generate step-by-step solution plans, create context-aware code, and push fixes as pull requests to your git provider. It supports major frameworks and languages including React, Flutter, TypeScript, Go, JavaScript, and Python. The tool aims to significantly reduce time-to-resolution and improve merge rates for pull requests, allowing engineers to focus on development rather than tedious bug fixing.

Visualizer is a specialized tool designed to simplify the process of visualizing attention maps within deep learning models, particularly those based on Transformer architectures. It addresses common challenges faced by developers, such as the difficulty of extracting deeply nested attention maps without modifying model code or encountering out-of-memory errors. The tool provides a non-intrusive method using Python decorators and PyTorch hooks, allowing users to precisely retrieve intermediate variables like attention maps. This ensures consistency between training and testing phases, as no code changes are required for visualization. It's particularly useful for analyzing complex models like Vision Transformers, enabling the extraction of all attention maps across multiple layers with minimal effort.

Computer-vision-in-action is a comprehensive, open-source learning platform designed for individuals interested in mastering computer vision. It offers a closed-loop learning environment where users can interactively run code directly online, eliminating the need for complex local setup. The platform features an electronic book, available in both Chinese and English, covering fundamental theories, practical applications, and advanced topics like Transformer models and generative adversarial networks. It includes detailed project guidance, code implementations, and a community forum for reader interaction and support. The platform emphasizes a 'learn by doing' approach, allowing users to modify code and observe results in real-time.

computervision-recipes is a comprehensive open-source repository from Microsoft, offering best practices, code samples, and documentation for various computer vision tasks. It provides examples and guidelines for building computer vision systems, leveraging state-of-the-art libraries like PyTorch. The repository covers scenarios such as image classification, object detection, image similarity, keypoint detection, image segmentation, action recognition, and tracking. It aims to reduce development time by simplifying the process from problem definition to solution deployment, providing Jupyter notebooks and utility functions. The target audience includes data scientists and machine learning engineers looking for solution accelerators for real-world vision problems, with content ranging from fine-tuning models to hard-negative mining and model deployment.

Awesome-deepseek-coder is a curated list of open-source projects and resources centered around DeepSeek Coder. It provides direct links to official DeepSeek Coder models hosted on Hugging Face, including base and instruct versions across various sizes (1.3B, 5.7B, 6.7B, 33B). Beyond official releases, the repository highlights community-built models that leverage DeepSeek Coder, such as OpenCodeInterpreter-DS and Magicoder-DS. It also features quantized models in AWQ, GGUF, and GPTQ formats, optimized for different deployment scenarios. The list includes integrations with AI coding assistants like Copilot refact and Tabby, showcasing DeepSeek Coder's capabilities in code completion and improvement. Additionally, it points to tools for finetuning data and API examples, making it a comprehensive resource for developers working with DeepSeek Coder.

External-Attention-pytorch is a comprehensive GitHub repository offering PyTorch implementations of numerous attention mechanisms, Multi-Layer Perceptrons (MLPs), re-parameterization techniques, and convolution operations. This resource is designed for developers and researchers looking to deepen their understanding of these fundamental components in deep learning models. It includes detailed examples and usage instructions for over 30 different attention mechanisms, such as External Attention, Self Attention, MobileViT Attention, and many more. Additionally, it covers various backbone architectures like ResNet and MobileViT, several MLP types, and re-parameterization methods like RepVGG. The repository serves as a valuable educational and practical toolkit for implementing advanced neural network architectures.

LarAgent is an open-source framework designed to integrate powerful AI agents into Laravel projects with minimal configuration and maximum extensibility. It provides Laravel-grade productivity for AI agent development, making it ideal for automating internal operations or building conversational experiences. Key features include an Eloquent-style API for defining agents, tools, memories, and workflows, a first-class tooling system with MCP server support, pluggable memory and context management, and multi-agent workflows with queues and chainable tasks. The framework also supports structured output, multi-modal input, modular provider support, and extensive event systems for customization and observability. It is officially powered by Redberry, a Diamond-tier Laravel partner, ensuring continuous evolution and support.

MCP Client for Ollama (ollmcp) is a powerful, interactive terminal application (TUI) designed for connecting local Ollama LLMs to one or more Model Context Protocol (MCP) servers. This client facilitates advanced tool use and workflow automation for developers. It offers a rich, user-friendly interface to manage tools, models, and server connections in real-time without requiring coding. Key features include agent mode for iterative tool execution, multi-server support, streaming responses, human-in-the-loop tool execution for safety, and advanced model configuration. It's built for developers working with local LLMs, streamlining their workflow with features like fuzzy autocomplete, hot-reloading for development, and comprehensive history management.

rnn-tutorial-rnnlm is an open-source project available on GitHub, offering a comprehensive tutorial for implementing Recurrent Neural Networks (RNNs). Specifically, it focuses on Part 2 of a tutorial series, guiding users through the process of building an RNN in Python and Theano. The repository includes all necessary code, a Jupyter Notebook for interactive learning, and detailed setup instructions. It covers both local development environments and advanced configurations for CUDA-enabled GPU instances on platforms like EC2, making it suitable for developers looking to understand and implement RNNs for language modeling and other sequential data tasks. The project is licensed under Apache-2.0.

Xonsh (pronounced "consh") is a powerful, open-source shell that combines the best features of Python 3 with traditional shell functionality. It allows users to execute both Python code and shell commands directly, offering a unique and flexible environment for scripting, automation, and interactive command-line tasks. Xonsh is cross-platform, working on Linux, macOS, and Windows, and is designed to be AI-friendly, facilitating integration with AI tools and workflows. Its extensibility through "xontribs" enables users to customize and enhance its capabilities, from prompt customization to deep integration with other tools like ChatGPT and GitHub Copilot. This makes xonsh an ideal choice for developers and data scientists seeking a highly programmable and adaptable shell.

Nativeline is an AI-powered platform designed to help users build native Swift iOS, iPad, and Mac applications without writing any code. It generates actual SwiftUI code, not web wrappers, ensuring apps are fast, smooth, and responsive. Users can describe their app idea in plain English, and the AI builds it, including database creation. The platform supports one-click deployment to TestFlight and the App Store, making it easy to ship apps to real users. Nativeline offers full code access and editing for developers, console logs, and debugging. It's suitable for first-timers, entrepreneurs looking to launch MVPs quickly, and developers who want to accelerate their workflow by skipping boilerplate code.

The AI SDK is a free and open-source TypeScript toolkit developed by the creators of Next.js, Vercel. It is designed to simplify the development of AI-powered applications and agents, offering a provider-agnostic API that integrates with popular UI frameworks such as Next.js, React, Svelte, Vue, and Angular, as well as runtimes like Node.js. The SDK supports interaction with major model providers including OpenAI, Anthropic, and Google, often leveraging the Vercel AI Gateway for seamless access. Developers can generate text, structured data, and build complex agents with integrated tools. It also includes a UI module with framework-agnostic hooks for creating chatbots and generative user interfaces.

InstantCoder is an AI-powered code assistant hosted on Hugging Face that allows users to generate source code for applications by simply providing a short description. Leveraging the Gemini API, the tool translates natural language requests, such as "calculator app" or "to-do list," into functional code. This makes it an accessible platform for rapid prototyping and learning, enabling users to quickly obtain code snippets without extensive manual coding. It's particularly useful for developers, students, and coding enthusiasts looking to accelerate their development process or explore new programming concepts through AI-generated examples. The tool's integration with Hugging Face Spaces also provides a collaborative environment for sharing and experimenting with AI applications.

FixThisBug.de is an AI-powered tool designed to assist developers in resolving programming errors. It functions by analyzing code snippets and associated error messages to generate potential solutions. The tool aims to streamline the debugging process, making it faster and more efficient for developers. It supports a variety of popular programming languages, including Python, JavaScript, Java, C++, and Ruby. A key feature highlighted is its commitment to data privacy and security, as it processes code on secure servers located in Germany, ensuring compliance with GDPR regulations. This focus on security and broad language support makes it a potentially valuable asset for developers seeking AI assistance in their debugging workflows.

ChatGLM-Finetuning is a comprehensive open-source project designed for fine-tuning ChatGLM-6B, ChatGLM2-6B, and ChatGLM3-6B models. It offers a variety of fine-tuning methods, including Freeze, Lora, P-tuning, and full parameter fine-tuning, allowing users to select the most suitable approach for their specific needs. The tool supports both single-card and multi-card training environments, making it adaptable to different hardware setups. It is particularly useful for tasks such as information extraction, generation, and classification. The project emphasizes maintaining model performance without severe catastrophic forgetting, even after fine-tuning. It also provides detailed instructions and code examples for implementing each fine-tuning method, along with memory usage benchmarks for different configurations, aiding developers in optimizing their training processes.

DeepLearning is an open-source project that offers a comprehensive Python-based resource for understanding the "Deep Learning" book (also known as the 'Flower Book'). It provides detailed mathematical derivations, in-depth principle analysis, and source-level code implementations using primarily the NumPy library. The project covers foundational concepts like linear algebra, probability theory, and machine learning basics, alongside advanced deep learning techniques such as deep feedforward networks, regularization, optimization algorithms, and convolutional networks. It aims to clarify complex topics that might be difficult to grasp from the book alone, making it an invaluable tool for students and researchers in the field.

DeepLearningForTSF is an open-source GitHub repository dedicated to deep learning techniques for time series forecasting. It provides comprehensive resources and code examples for predicting trends and seasonality using methods like SARIMA and triple exponential smoothing. The repository includes detailed guides on hyperparameter optimization and the development of various deep learning models, such as Multi-Layer Perceptrons (MLP), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks. It covers different model types, including stacked LSTMs, bidirectional LSTMs, CNN-LSTMs, and Encoder-Decoder LSTMs, for both univariate and multivariate time series forecasting. Additionally, it features case studies on human activity recognition, indoor movement classification, air pollution prediction, and electricity consumption forecasting, making it a valuable resource for researchers and developers in the field.

deep-learning-with-keras-notebooks is an open-source collection of Jupyter notebooks designed to help users learn and apply Keras for deep learning. This repository provides a wide range of examples, from image processing and augmentation to advanced topics like object detection with YOLOv2 and natural language processing with word embeddings. The notebooks cover practical applications such as image classification (e.g., traffic signs, fashion MNIST), facial recognition, and captcha breaking. It's an excellent resource for students and developers looking to gain hands-on experience with Keras and deep learning concepts, offering clear, runnable examples for various tasks.

konlpy is an open-source Python package specifically designed for Korean natural language processing (NLP). It provides essential functionalities for analyzing Korean text, including morphological analysis and part-of-speech tagging. This makes it a valuable tool for developers and researchers who need to process and understand the nuances of the Korean language in their applications or studies. The package is built to be user-friendly, facilitating the integration of advanced NLP capabilities into various projects. Its open-source nature encourages community contributions and ensures continuous development and improvement, making it a robust choice for Korean NLP tasks.

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.

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.

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.