Coding & Development

Federated is a collection of Google research projects dedicated to advancing Federated Learning and Federated Analytics. Federated learning enables the training of a shared global model across numerous participating clients while ensuring their training data remains local. Federated analytics, on the other hand, focuses on applying data science methods to analyze raw data stored directly on users’ devices. Many projects within this repository leverage TensorFlow Federated (TFF), an open-source framework designed for machine learning and other computations on decentralized data. The repository serves primarily for reproducing experimental results from related papers, with each project intended as an independent unit rather than a reusable framework.

Beyond42 is an Immersive Experience Platform (IXP) designed to transform physical spaces like university campuses, cultural sites, and corporate headquarters into intelligent, interactive digital twins. This platform enables organizations to scale presence, engagement, and revenue by offering virtual experiences such as global recruitment for universities, interactive exhibitions for cultural sites, and immersive events for corporate offices. Beyond42 also provides an API, allowing integration of its immersive 3D environments into other products. The platform has demonstrated success in enhancing cultural and historical sites, boosting student engagement, and revolutionizing event efficiency and accessibility through its digital twin technology.

NeuroBlock is an AI laboratory dedicated to enhancing AI models through the use of high-quality datasets. The platform provides comprehensive enterprise AI consulting services, assisting businesses in integrating and optimizing AI solutions. A key offering includes local and private AI integrations, ensuring data privacy and tailored performance for specific organizational needs. Additionally, NeuroBlock features an OpenData platform, designed to facilitate AI model training by providing access to diverse and curated datasets. The company also develops lead generation tools, leveraging AI to identify and engage potential customers. NeuroBlock aims to deliver AI solutions that are efficient, secure, and customized to client requirements.

Magnet.me is a comprehensive career network designed to help students and professionals find their perfect job, traineeship, or internship. The platform connects over 450,000 students and professionals with more than 6,000 employers, ranging from startups to multinationals. A key feature is its AI career coach, which assists users in discovering suitable job opportunities, practicing interview skills, and making informed career decisions. Users can create a profile, connect with top employers, receive job matches based on their preferences, and even be approached by recruiters. The platform lists over 30,000 vacancies across various industries and locations, making it a robust resource for career development.

fake-bpy-module is a collection of fake Blender Python API modules specifically designed to enable robust code completion in popular Integrated Development Environments (IDEs). This tool significantly assists developers working with Blender's Python API by offering accurate suggestions and documentation, streamlining the development of Blender add-ons and scripting tasks. It supports a wide range of Blender versions, from 2.78 up to the latest daily builds, and can be installed via pip, pre-generated modules, or by manual generation. The project emphasizes long-term support and provides resources for bug reporting, feature requests, and community discussions, making it an essential utility for Blender Python developers.

Reference is an open-source project offering a comprehensive collection of quick reference cheat sheets specifically designed for developers. It covers a wide array of topics, including numerous programming languages like Python, JavaScript, Go, and C++, as well as essential toolkits such as ChatGPT, VSCode, and Emmet. Additionally, it provides cheat sheets for Linux commands and keyboard shortcuts for popular applications like Adobe Photoshop, Figma, and GitHub. The platform encourages community contributions, allowing users to share their own cheat sheets or improve existing ones, making it a dynamic and continuously evolving resource. The primary and maintained domain for accessing these up-to-date cheat sheets is cheatsheets.zip.

facexlib is an open-source library designed to provide ready-to-use face-related functions, leveraging current state-of-the-art open-source methods. It primarily offers PyTorch reference codes for various face processing tasks, including detection, alignment, recognition, parsing, matting, headpose estimation, and tracking. While it provides a collection of these algorithms, users are directed to the original repositories for training or fine-tuning. The library simplifies the integration of advanced face processing techniques into existing projects, making it a valuable resource for developers and researchers working with facial data. It is released under the MIT license, with individual components referencing their original licenses.

Fewshot_Detection is an open-source implementation of the paper "Few-shot Object Detection via Feature Reweighting," designed for researchers and developers working with computer vision. This tool addresses the challenge of detecting novel objects with limited training data by employing a meta feature learner and a reweighting module within a one-stage detection architecture. It is built upon `pytorch-yolo2` and developed with Python 2.7 and PyTorch 0.3.1. The system extracts meta features generalizable to novel object classes and transforms support examples into reweighting vectors, enhancing detection capabilities. The entire process, including a carefully designed loss function, is trained end-to-end based on an episodic few-shot learning scheme. It demonstrates significant performance improvements over established baselines on multiple datasets and settings.

4iG Space and Defence Technologies is Hungary’s first privately-owned large enterprise specializing in cutting-edge solutions for the space and defence sectors. Leveraging the expertise of the 4iG Group and its portfolio companies, the company is dedicated to building a connected ecosystem. Their offerings span from comprehensive satellite systems and mission operations to advanced Unmanned Aerial Vehicle (UAV) and Counter-UAV (C-UAV) technology. Additionally, they provide sophisticated geospatial data solutions, aiming to redefine the space and defence industry through integrated and innovative technological advancements.

Perplexity AI is a Python module designed as an unofficial API wrapper for Perplexity.ai, offering enhanced functionality and flexibility. A key feature is its ability to leverage Emailnator for automatic generation of new accounts, effectively bypassing query limits and providing unlimited pro queries. The module supports both synchronous and asynchronous APIs, catering to different programming needs. For users who prefer a graphical interface, it also includes a web interface that automates account creation and usage. This tool is particularly useful for developers and data scientists looking to integrate Perplexity.ai's capabilities into their applications or workflows without the constraints of official API keys, offering robust error handling, comprehensive logging, and streaming responses.

PiML-Toolbox (Python Interpretable Machine Learning) is a comprehensive Python toolbox designed for the development and diagnostics of interpretable machine learning models. It offers both low-code interfaces and high-code APIs, supporting a growing list of inherently interpretable ML models such as GLM, GAM, Tree, FIGS, XGB1, XGB2, EBM, GAMI-Net, and ReLU-DNN. The toolbox facilitates various outcome testing, including accuracy, explainability (PFI, PDP, ALE, LIME, SHAP), fairness, weak spot identification, overfitting detection, reliability assessment, robustness, and resilience evaluation. PiML-Toolbox aims to empower model developers and validators with tools for transparent, interpretable, and robust machine learning, particularly in high-stakes regulatory settings.

Generative-ai-docs is a GitHub repository that previously served as the source for guides and tutorials related to Google's Generative AI developer site, specifically for the Gemini API and Gemma. The repository is now deprecated and no longer maintained, but it provides essential links to the active Gemini Documentation, Gemini Cookbook, and Gemma Cookbook. These resources are crucial for developers and data scientists looking to work with Google's generative AI models, offering examples, demos, and documentation to facilitate integration and development. While the repository itself is archived, its historical context and redirection to current resources make it a relevant entry for understanding the evolution of Google's generative AI offerings.

gore is an open-source Go REPL (Read-Eval-Print Loop) designed to enhance interactive Go development. It offers essential features such as line editing with history, multi-line input, and robust code completion, which requires `gopls` for optimal functionality. Developers can evaluate Go expressions, statements, and function declarations directly within the REPL environment. The tool also supports package importing with completion, showing documents, and auto-importing. While gore provides significant value for Go users, it's noted that its implementation, which runs code using `go run` for each input, can lead to slower execution compared to more actively maintained REPLs like `gomacro` or `yaegi`. It supports Go modules, allowing users to load local modules and automatically download remote ones without manual `go get` commands.

PyRCA is a Python machine learning library designed to facilitate root cause analysis (RCA) in complex IT environments, particularly those utilizing microservices architectures. It offers a comprehensive suite of state-of-the-art RCA algorithms, primarily focusing on metric-based analysis. Users can identify anomalous metrics using methods like ε-diagnosis or pinpoint root causes based on topology/causal graphs through techniques such as Bayesian inference and Random Walk. The library also provides a convenient tool for building and refining causal graphs from time series data and domain knowledge, simplifying the development of graph-based RCA solutions. PyRCA supports various methods including ε-Diagnosis, Bayesian Inference-based RCA, Random Walk-based RCA, Root Cause Discovery, and Hypothesis Testing-based RCA, with plans to expand to trace and log-based RCA in the future. It also includes a benchmark for evaluating different RCA methods.

Relic is an award-winning spatial entertainment platform designed for creating and deploying interactive spatial experiences. It simplifies the content creation process by allowing users to generate 3D assets from 2D images/videos, animate, and rig them using simple prompts, eliminating the need for coding or complex game engines like Unity or Unreal Engine. The platform integrates various 3D AI tools into an agentic interface, making it accessible for creators of all skill levels. Content can be easily deployed on the Relic App, embedded via an SDK, or shared as a WebXR Link. Relic also enables users to watch 4D AR, 6DoF, and fully Spatial Movies, bringing characters to life and transforming viewing experiences into immersive worlds.

REP, or Reproducible Experiment Platform, is an ipython-based environment designed for conducting data-driven research with an emphasis on consistency and reproducibility. It provides a unified Python wrapper for several machine learning libraries, including Sklearn, XGBoost, and Theanets, allowing users to work with a consistent interface. Key features include parallel training of classifiers on clusters, classification/regression reports with interactive plots, and smart grid-search algorithms with parallel execution. REP also supports research versioning using Git and offers pluggable quality metrics for classification. It aims to extend scikit-learn by providing a better user experience and tools for meta-algorithm design, making it a valuable resource for data scientists and researchers.

pointnet.pytorch offers a PyTorch implementation of the PointNet deep learning model, specifically designed for 3D classification and segmentation using point sets. This open-source tool facilitates research and development in 3D data processing, providing a robust and tested framework compatible with PyTorch 1.0. It includes functionalities for downloading and preparing datasets, training classification and segmentation models, and visualizing results. The repository details performance metrics on datasets like ModelNet40 and ShapeNet, allowing users to compare against original implementations. It's a valuable resource for developers and researchers working with 3D point cloud data.

pwa-asset-generator automates the creation and declaration of assets for Progressive Web Apps (PWAs). It generates various image types including icons, splash screens, favicons, and mstile images, ensuring they comply with Web App Manifest specifications and Apple Human Interface guidelines. The tool automatically updates `manifest.json` and `index.html` files with the generated assets. A key feature is its ability to scrape the latest Apple Human Interface guidelines via Puppeteer to ensure compatibility with current iOS devices. It supports multiple source formats like local images, HTML files, or remote assets, and offers extensive customization options for output, including dark mode splash screens and maskable icons. The tool can be used via its command-line interface or as a JavaScript module.

Angular.dev is the official website for the Angular framework, designed to empower developers in building scalable and modern web applications with confidence. It integrates cutting-edge features such as Signals for reactive state updates, Control Flow for efficient template logic, Deferrable Views for improved performance, and Hydration for faster initial page loads. The platform emphasizes productivity and offers AI-forward resources and integrations to enhance development workflows. Angular.dev is built on opinionated yet versatile principles, leveraging Angular components and dependency injection for modular organization. It provides a fully featured platform with first-party modules for forms, routing, and more, ensuring everything works together seamlessly. Trusted by millions, Angular focuses on performance, enabling the creation of fast, reliable applications that scale with team size.

Blynkkr is a revolutionary application designed to consolidate all your social profiles into a single, secure digital identity. It leverages facial recognition AI to seamlessly add new contacts by simply scanning their face, provided they are also on the Blynkkr platform. The application is deeply integrated with blockchain technology, ensuring that your personal data is stored privately and securely, offering a tamper-proof method for managing your digital identity. Blynkkr provides highly accurate facial analysis, comparison, and search capabilities, utilizing Google ML Kit's Vision and Natural Language ML Kit face detection API for real-time processing directly on-device, enhancing user privacy and security. This combination of AI and blockchain offers a streamlined user experience while prioritizing data protection.

Sniffly is an open-source Claude Code analytics dashboard designed to help developers better understand and optimize their use of Claude Code. It offers detailed usage statistics, error analysis to pinpoint common mistakes, and a comprehensive message history analysis for reviewing past interactions. The tool runs entirely on your local machine, ensuring privacy with no telemetry and all data processing occurring locally. Users can easily share project statistics and instructions with colleagues through sharable dashboards, with options for private or public visibility. Sniffly is straightforward to set up with Python and offers configurable settings for port, host, and browser behavior, making it a flexible solution for individual developers and teams.

QP/C is a real-time event framework (RTEF) and RTOS designed for embedded systems, particularly microcontrollers like ARM Cortex-M MCUs. It implements an asynchronous, event-driven Active Object (Actor) model and supports Hierarchical State Machines (UML statecharts) for specifying behavior. Developers can manually code state machines in C or use the free graphical QM model-based design (MBD) tool for automatic code generation. QP/C is part of the larger QP framework family, offering both open-source (GPLv3) and commercial licensing options. It provides a robust software infrastructure and runtime environment for deterministic, real-time execution of Active Objects, making it suitable for developing complex embedded applications.

R1-V is an open-source project focused on enhancing the super generalization ability of Vision Language Models (VLM) with minimal computational cost. It aims to improve the perception and reasoning capabilities of VLMs through reinforcement learning. The project provides new VLM-RL environments, a comprehensive training codebase, and research papers. R1-V supports various models like Qwen2-VL and Qwen2.5-VL, and offers training datasets for tasks such as item counting and geometry reasoning. It also includes evaluation scripts for benchmarks like SuperClevr and GEOQA, making it a valuable resource for researchers and developers in the VLM domain.

Scrapling is a powerful and adaptive web scraping framework designed for both single requests and full-scale, concurrent crawls. It features an intelligent parser that learns from website changes, automatically relocating elements when pages update, ensuring data extraction remains robust. The framework includes advanced fetchers capable of bypassing anti-bot systems like Cloudflare Turnstile and offers full browser automation. Scrapling supports multi-session crawls with pause/resume functionality, automatic proxy rotation, and real-time streaming of scraped items. It also integrates AI capabilities through an MCP server for assisted web scraping, optimizing data extraction and reducing token usage for AI models. Built for performance, it boasts high speed, memory efficiency, and battle-tested architecture with extensive test coverage.