Coding & Development

MultiButton is a highly efficient and flexible button driver library specifically designed for embedded systems. It utilizes a state machine architecture to reliably detect and manage various button events, including press down, press up, single click, double click, long press start, long press hold, and repeat press. The library incorporates hardware debouncing to eliminate contact bounce, ensuring accurate event detection. Its linked-list architecture allows for an unlimited number of button instances, making it suitable for complex projects. Developers can choose between callback-based or polling-based event handling and configure timing thresholds and debounce depth to suit their specific application needs. MultiButton also offers a thread-safe option for RTOS environments with zero overhead on bare-metal systems.

HyperView is a terminal-first TradingView strategy lab designed for traders who want to develop strategies like engineers. It allows users to download market data directly from TradingView's websocket, supporting up to 40K historical bars on paid plans. Users can run their strategy logic in Python, leveraging TA-Lib's 150+ indicators, and backtest with fill behavior closely mirroring Pine Script. A key feature is its ability to simulate realistic Stop Loss/Take Profit (SL/TP) execution and use Bayesian optimization (Optuna TPE) to find optimal parameter ranges. This eliminates the need for manual CSV exports or browser automation, providing a streamlined workflow for strategy validation and iteration.

Prism: Word Search Game, available through MindMash, offers an engaging platform for word search enthusiasts. Users can dive into a variety of challenges by playing both custom-made and AI-generated word search puzzles. The tool provides a creative outlet for users to design their own puzzles, adding a personalized touch to the gaming experience. A unique feature of Prism is its support for NFT sharing of puzzles, allowing users to share their creations in a novel way. This platform caters to individuals looking for a fun and interactive way to test their vocabulary and puzzle-solving skills, offering a fresh take on the classic word search game.

LSP-AI is an open-source language server designed to bring AI capabilities directly into code editors. It provides functionalities such as in-editor chatting with Large Language Models (LLMs), allowing developers to interact with AI without leaving their coding environment. Additionally, LSP-AI offers intelligent code completions to streamline the coding process and enhance productivity. The tool is built to empower software engineers by integrating advanced AI assistance seamlessly into their workflow, and it is compatible with any code editor that supports the Language Server Protocol (LSP).

Immutable AI is dedicated to fostering transparency and trust within the artificial intelligence landscape. The platform is actively developing a secure and decentralized computing network specifically designed for AI applications. Their core mission revolves around creating an energy-efficient future for AI, emphasizing solutions that are both human-centric and tamper-proof. While specific features are not detailed on the currently down website, the overarching goal is to provide a robust and trustworthy infrastructure for AI development and deployment, ensuring integrity and accountability in AI systems.

stack-chan is an open-source project featuring a JavaScript-driven robot embedded in M5Stack. This super-kawaii robot can display a range of cute faces and expressions, including happy, angry, and sad. Users have the flexibility to customize the robot's face and expressions, as well as add various M5Units for enhanced functionality. The project provides all necessary components, including firmware source codes, stereolithography (STL) files for the case, and schematics with board layout data. It supports driving serial (TTL) and PWM servos and encourages users to develop their own applications. The project is distributed under the Apache version 2.0 license, making it accessible for developers and hobbyists.

Neurecon is an open-source project offering unofficial PyTorch implementations of advanced neural rendering techniques for multi-view 3D reconstruction. It focuses on unifying neural implicit surfaces and radiance fields, as seen in papers like UNISURF, NeuS, and VolSDF. The tool allows users to reconstruct 3D surfaces and appearance from pure posed RGB images, without requiring masks, depths, or ground truth meshes. It leverages volume rendering to efficiently learn rough shapes early in training and then refines fine details, bridging the gap between implicit 3D surfaces and volume rendering. Neurecon is a valuable resource for researchers and developers exploring the cutting edge of 3D reconstruction.

Tensorflow_Object_Tracking_Video is an open-source project developed for object tracking in videos, encompassing localization, detection, and classification. Originally created for the ImageNET VID competition, it leverages TensorFlow technology. The project integrates popular object detection systems like YOLO (You Only Look Once) and TensorBox, along with Inception for classification. It features a modular architecture that includes a general object detector, a tracker, and a smoother. The repository provides scripts for both YOLO and VID TENSORBOX usage, allowing users to process videos, set parameters, and obtain real-time object tracking results. It also includes dataset scripts for preparing and processing data for training, particularly for the VID classes, and offers pre-trained weights for Inception and TensorBox.

MY-BASIC is a lightweight BASIC interpreter implemented in standard C, provided in dual files for easy integration. It aims to be highly embeddable, extendable, and portable across various platforms. The interpreter supports dynamic typing, structured syntax, and a unique blend of prototype-based object-oriented programming with functional programming via lambda abstraction. Its core is compact, allowing it to be used as a standalone interpreter or seamlessly embedded into existing projects developed in C, C++, Java, Objective-C, Swift, C#, and more. Developers can customize its functionality by adding their own scripting interfaces, making it a versatile tool for various programming needs.

microprofile is an embeddable profiler designed for C++ projects, offering robust capabilities for performance analysis and bottleneck identification. It integrates easily into existing codebases, requiring just a few lines to start profiling. Key features include CPU and GPU timing across multiple APIs like OpenGL, D3D11, D3D12, and Vulkan, as well as support for multithreaded renderers. The tool also provides counter tracking, a timeline view for longer-duration events, and a live web view for real-time monitoring and capture generation. A standout feature is dynamic instrumentation for Intel x86-64, allowing injection of markers into running code without recompilation, though it's noted as experimental. Captures can be compared, and the tool supports compressed captures using miniz to manage file sizes.

HeadPoseEstimation-WHENet is an end-to-end head-pose estimation network designed for real-time, fine-grained prediction of Euler angles across the full range of head yaws from a single RGB image. Unlike many existing methods that perform well only for frontal views, WHENet targets head poses from all viewpoints, making it suitable for applications in autonomous driving and retail. The network builds on multi-loss approaches with adapted loss functions and training strategies for wide-range estimation. It also uniquely extracts ground truth labelings of anterior views from a panoptic dataset. WHENet is compact and efficient, making it suitable for mobile devices and applications, and meets or beats state-of-the-art methods for frontal head pose estimation.

WildGS-SLAM is an open-source research tool designed for monocular Gaussian Splatting SLAM in dynamic environments. Developed for Computer Vision and Pattern Recognition (CVPR) 2025, it excels at accurately tracking camera trajectories and reconstructing 3D Gaussian maps for static elements from monocular video sequences, even when captured in the wild with dynamic distractors. The tool effectively removes all dynamic components to provide a clear static reconstruction. It supports various datasets including Wild-SLAM Mocap, Wild-SLAM iPhone, Bonn Dynamic, and TUM RGB-D, and also allows users to integrate their own custom datasets. WildGS-SLAM provides functionalities for camera pose evaluation and novel view synthesis, making it a valuable resource for researchers in the field.

llm-twin-course is a free educational resource designed to guide users through the process of building a production-ready Large Language Model (LLM) and Retrieval Augmented Generation (RAG) system. The course emphasizes LLMOps best practices, offering practical, hands-on lessons and accompanying source code. It covers the entire development lifecycle, from initial data gathering to the final stages of productionizing LLMs, with a specific focus on creating an AI replica.

LuaRadio is a lightweight and embeddable flow graph signal processing framework specifically designed for software-defined radio (SDR). Built on LuaJIT, it offers a small binary footprint and no external hard dependencies, making it highly portable. The framework provides a comprehensive suite of source, sink, and processing blocks, along with a simple API for defining and running flow graphs, creating custom blocks, and managing data types. It's ideal for rapidly prototyping software radios, developing modulation/demodulation utilities, and conducting signal processing experiments. LuaRadio can also be embedded into existing radio applications, serving as a user-scriptable engine for advanced signal processing tasks. It supports computational acceleration through LuaJIT's FFI to wrap external libraries like VOLK, liquid-dsp, and others, ensuring efficient performance.

whatlanguage is a Ruby library designed for efficient text language detection. It leverages bloom filters to achieve high speed and memory efficiency, making it suitable for processing larger text blocks like blog posts or comments. The library supports a wide array of languages including Dutch, English, Farsi, French, German, Italian, Pinyin, Swedish, Portuguese, Russian, Arabic, Finnish, Greek, Hebrew, Hungarian, Korean, Norwegian, Polish, and Spanish. While effective for longer texts, it is noted to perform poorly on very short or Twitter-esque content. The project, initially built in 2007, has received minor updates to ensure compatibility with modern Ruby implementations, though the core algorithms remain largely unchanged.

ChillArcade provides a free and accessible online gaming experience, allowing users to play a variety of games instantly in their web browser. A key differentiator is its use of AI to generate games, offering a unique and constantly evolving gaming library. The platform is designed for casual play, eliminating the need for downloads or installations, making it easy for anyone to jump in and start playing.

Characters maker kids games, developed by Pazu, is a mobile application designed for children to unleash their creativity by designing and customizing cartoon characters and avatars. This dress-up game provides a rich selection of accessories, clothing, and styles, allowing kids to craft unique digital personas. It serves as a creative outlet, fostering imaginative play and character design skills in a fun and engaging environment. The app is part of Pazu's extensive library of mobile games for kids, which are trusted by millions of children and parents worldwide, emphasizing a safe and ad-free experience.

USRNet is a deep unfolding network for image super-resolution, implementing a model described in a CVPR 2020 paper. This PyTorch-based tool provides code and models for training and testing image super-resolution algorithms. It leverages both learning-based and model-based methods, offering the flexibility of model-based approaches to super-resolve blurry and noisy images across different scale factors, blur kernels, and noise levels using a single unified model. Key features include a data module for clearer HR estimation, a prior module for cleaner HR estimation, and a hyper-parameter module to control outputs. It supports various degradation models, including bicubic degradation and deblurring, and demonstrates strong generalizability to different kernel sizes.

SRGAN is a PyTorch implementation of the Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network paper from CVPR 2017. This open-source tool allows users to perform super-resolution on both images and videos, significantly enhancing their quality and detail. It provides options for various upscale factors (2x, 4x, 8x) and includes benchmarks for performance on different datasets. Users can train their own models, test on benchmark datasets, or apply super-resolution to single images and videos using pre-trained models. The project is hosted on GitHub and requires Anaconda, PyTorch, and OpenCV for setup.

SRGAN-tensorflow offers a TensorFlow implementation of the SRGAN algorithm, designed for single image super-resolution. This project is based on the impressive work "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network." It allows users to upscale images, achieving results comparable to those presented in the original research paper, even with limited resources. The tool supports both testing with pre-trained models and training new models on custom datasets like RAISE. It provides scripts for running inference, testing, and training SRResnet and SRGAN models with different perceptual losses (MSE and VGG54). The code is highly inspired by pix2pix-tensorflow and includes detailed instructions for setting up dependencies and executing various modes.

COOKING is an innovative platform that seamlessly blends creativity and functionality to redefine architectural excellence. It provides a comprehensive suite of professional services catering to a diverse clientele, including homeowners and commercial developers. Key offerings encompass renovation and restoration, continuous support, application access, consulting, project management, and architectural solutions. The platform also features an 'Études Arquitecto' application for collaboration among architects and project showcasing, alongside a newsletter offering insightful articles and design ideas. COOKING aims to save users thousands of work hours and unlock new perspectives in architectural design.

frozen is a robust JSON parser and generator specifically designed for C/C++ applications, emphasizing efficiency and a minimal footprint. It offers a familiar scanf/printf-like interface for easy integration and use, making it particularly suitable for embedded systems where resources are often constrained. The tool is ISO C and ISO C++ compliant, ensuring broad compatibility. Key functionalities include `json_scanf()` for parsing JSON strings into C/C++ variables, `json_printf()` for generating JSON output, and `json_setf()` for modifying existing JSON strings. It also supports reading and writing JSON to files, and includes built-in base64 encoding/decoding. With 100% test coverage and no external dependencies, frozen provides a reliable and lightweight solution for JSON manipulation in performance-critical environments.

FrostDB is an embeddable wide-column columnar database written in Go, designed for analytical workloads where the majority of interactions are writes, with occasional analytical queries. It leverages Apache Parquet for efficient storage and Apache Arrow for vectorized query execution. A key differentiator is its support for dynamic columns, allowing schemas to evolve at runtime, which is particularly useful for observability data like Prometheus time-series. The database maintains data immutability and uses an LSM-like index for storage, with snapshot isolation for reads. While still in its infancy and not production-ready, FrostDB offers a compelling solution for Go developers needing an embedded, high-performance columnar database for immutable, semi-structured datasets.

FastDepth is an open-source project that provides trained models and evaluation code for fast monocular depth estimation, specifically optimized for embedded systems. The project includes resources for setting up the environment, downloading pre-trained models, evaluating performance, and deploying models on hardware like the NVIDIA Jetson TX2. It leverages PyTorch for model training and evaluation, and the TVM compiler stack for efficient cross-compilation and deployment. The repository offers various MobileNet-NNConv5 architectures, including pruned versions with additive skip connections, demonstrating significant performance improvements in terms of RMSE and delta1 metrics compared to prior work, with very low runtimes on embedded GPUs.