Coding & Development

Gaze LLE is an AI tool designed for gaze target estimation, allowing users to upload an image and determine where individuals within that image are looking. The application automatically detects each face present in the picture and then estimates their gaze direction, overlaying the original image with arrows to visually represent this information. Built with Gradio, it offers a user-friendly interface for easy interaction and testing. This tool is particularly suitable for research and development in the field of AI vision, offering a practical way to analyze human attention and interaction within visual data.

Gaze Demo is an AI tool designed for gaze detection, leveraging the Moondream model. Users can upload an image to the platform, which then identifies faces within the image and visualizes their gaze directions. The tool provides an option to use an ensemble mode, which can enhance the accuracy of the gaze detection. Built as a Hugging Face Space, it offers a straightforward interface for testing and visualizing gaze tracking capabilities. While currently paused, it is intended for research and development purposes, allowing users to explore and understand gaze detection technology.

Fastapi T5 is a specialized tool designed for deploying T5 models. It leverages the FastAPI framework for building robust APIs and integrates with Hugging Face Spaces for hosting. This allows AI engineers and NLP researchers to efficiently experiment with various natural language processing models. The tool facilitates the testing of different API configurations, providing a streamlined environment for development and iteration. It is particularly useful for those working on text-to-text tasks and exploring the capabilities of T5 models in a deployable format.

ADB shell - Debug Tool is a comprehensive mobile application designed for Android developers to efficiently manage and debug their devices without the need for a PC. It offers a local terminal for executing shell commands, alongside a robust toolbox for various development tasks. Key functionalities include connecting to ADB (Android Debug Bridge) across different Android versions (4.x to 14), pairing and connecting ADB wirelessly, and opening mobile or TV/TV Box ADB. The tool also addresses common debugging issues through its extensive FAQ section, covering topics like connection problems, command execution failures, and permission issues. It aims to streamline development workflows by enabling on-device troubleshooting and offering solutions for unstable connections or slow command execution.

Rebiber is a specialized AI tool designed to streamline the management of BibTeX entries, particularly useful for researchers and academics. Hosted on Hugging Face, this application automates several tedious tasks associated with maintaining a clean and consistent bibliography. Users can input a BibTeX string, and Rebiber will process it to replace arXiv citations with their official published versions, ensuring accuracy and proper referencing. Additionally, it intelligently deduplicates entries, sorts them for better organization, and abbreviates venue names to maintain a standardized format. This tool significantly reduces the manual effort required to prepare bibliographies for papers, theses, or presentations, making it an invaluable asset for anyone working with academic citations.

GameConfigIdea is an experimental workflow tool designed for creating story-driven games. It enables users to design narrative-driven games by providing either a JSON configuration or simple text prompts. The tool generates the story structure, creates supporting media, and facilitates playtesting of the adventure. This makes it suitable for game developers and story writers looking for assistance in prototyping game ideas and developing game configurations. It offers a streamlined approach to game design, focusing on narrative elements and interactive experiences.

CypherScribe is a no-code platform designed to rapidly create and launch interactive, SEO-optimized developer documentation. Users can connect their data sources, customize the appearance with themes, colors, and logos, and claim a custom subdomain for their documentation app, all without writing a single line of code. The platform supports a wide range of content types including headings, paragraphs, tables, code blocks, media, lists, and accordions, and even allows PDF/CSV uploads. It features a rich editor with Markdown support and custom blocks for multilingual code snippets, banners, and toasts. CypherScribe also includes built-in SEO optimization, a search algorithm, and an AI bot trained on your data to assist users. It aims to offload documentation burdens from development teams by providing a fast, customizable, and performant solution.

Bench.audio provides a platform for evaluating and comparing different audio models and agents. Users can interact with audio content, adjusting settings and listening to various samples directly within their web browser. This tool is designed to facilitate the testing and benchmarking of audio AI, offering a practical environment for developers and researchers to assess performance. It serves as an LMSYS bench specifically tailored for audio agents, ensuring a standardized approach to evaluation. The application is hosted on Hugging Face Spaces, making it easily accessible and runnable in a web environment.

NativeBridge.io offers a seamless solution for running native mobile applications directly in a browser, eliminating the need for complex setups. It supports both Android and iOS, providing access to real and emulated devices for comprehensive testing and demonstrations. This platform is designed to facilitate instant demos, reviews, collaboration, and testing, making it an ideal tool for developers and teams. By offering a fast and accessible environment, NativeBridge.io streamlines the mobile app development lifecycle, ensuring that applications can be tested and shared efficiently across various devices without any prior configuration.

AHD Soft | عهد is a technology company that, according to its previous description, specializes in artificial intelligence, with a focus on natural language processing and big data analytics. They reportedly develop large-scale language models and intelligent agents, particularly for the Persian language, aiming to help medium and large-sized businesses reduce costs and enhance efficiency. However, the live website currently displays a redirection message in both English and Persian, stating "Transferring to the website... در ﺣﺎل اﻧﺘﻘﺎل ﺑﻪ ﺳﺎﯾﺖ ﻣﻮرد ﻧﻈﺮ ﻫﺴﺘﯿﺪ...". This prevents access to any current information regarding its features, pricing, or specific offerings.

Base Model Explorer is a specialized tool designed for navigating the vast landscape of AI models available on the Hugging Face Hub. It enables users to efficiently explore base models and identify all their fine-tuned derivatives. The application provides valuable insights by displaying popularity rankings and other relevant options, making it easier to understand the adoption and impact of different models. This tool is particularly useful for researchers, developers, and enthusiasts who need to track model lineage, assess model popularity, and discover new applications built upon existing base models. It streamlines the process of model discovery and analysis within the Hugging Face ecosystem.

ngp_pl is an open-source project that implements Instant-ngp using PyTorch and CUDA, trained with PyTorch-Lightning. It aims to provide a concise PyTorch interface for researchers, offering high-quality results at high speeds. The tool supports various datasets including NSVF, NeRF++, Colmap, and RTMV data, with clear instructions for installation and training. It also includes a GUI for usage and provides benchmarks comparing its performance against other implementations like torch-ngp and the original Instant-ngp paper, demonstrating competitive PSNR and FPS metrics. The project emphasizes legibility and ease of use for future research.

Multi HMR is an AI tool designed for 3D human pose estimation and model reconstruction. Users can upload an image, and the application will generate 3D models of humans, overlaying them onto the original image. It also provides a separate 3D view of the reconstructed models, allowing for detailed inspection. The tool offers adjustable parameters such as detection threshold and NMS kernel size, giving users some control over the reconstruction process. While the tool aims to provide advanced 3D modeling capabilities, it is currently experiencing a runtime error preventing full functionality.

AIGenesis, as presented on its website, appears to be a webmail interface, specifically Roundcube Webmail. The entire website content, including the homepage, pricing, plans, features, FAQ, and docs pages, consistently displays the title and content related to Roundcube Webmail login. This suggests that the provided URL might be misconfigured or is hosting a webmail service rather than an AI tool as described in the current stored information. Users are prompted to enter a username and password to log in to the Roundcube Webmail system.

RocksDB is a high-performance, embeddable, persistent key-value store library developed and maintained by the Facebook Database Engineering Team. Built upon the foundational work of LevelDB, it is specifically optimized for modern hardware like flash drives and RAM. Its Log-Structured-Merge-Database (LSM) design allows for flexible tradeoffs between Write-Amplification-Factor (WAF), Read-Amplification-Factor (RAF), and Space-Amplification-Factor (SAF). A key differentiator is its multi-threaded compaction capability, making it highly suitable for managing and storing multiple terabytes of data within a single database instance. RocksDB provides a robust solution for developers needing fast, scalable, and persistent data storage within their applications.

PolaroidVL 1.0 Demo offers a hands-on experience with a compact vision-language AI model, allowing users to interact directly by uploading images and posing questions. This tool is designed for detailed analysis and provides answers based on the visual and textual input. It supports common image formats like JPG, PNG, and GIF, with a file size limit of up to 10MB. Hosted on Hugging Face Spaces, it serves as an accessible platform for individuals interested in experimenting with AI's capabilities in understanding and interpreting visual information combined with natural language queries. It is particularly useful for educational purposes and research experimentation in the field of AI.

AutoMerger is an AI tool developed by mlabonne, available as a Hugging Face Space, that aims to automate code merging processes. Built with Gradio, it is intended to simplify code integration and optimize AI models. While the tool's specific functionalities for merging are not detailed, its purpose suggests it would assist developers in managing codebases more efficiently. Currently, the Hugging Face Space for AutoMerger is paused, meaning it is not actively running or available for use. Users interested in utilizing the tool are directed to the community tab to request its restart from the author.

Bit Digital (NASDAQ: BTBT) is a publicly traded digital asset platform specializing in Ethereum-native treasury and staking strategies. The company began accumulating and staking ETH in 2022, establishing itself as a significant player in institutional Ethereum staking infrastructure. Its platform offers advanced validator operations, institutional-grade custody, active protocol governance, and yield optimization. Through strategic partnerships within the Ethereum ecosystem, Bit Digital provides secure, scalable, and compliant access to onchain yield. Additionally, Bit Digital holds a majority equity stake in WhiteFiber (NASDAQ: WYFI), offering strategic exposure to AI and High-Performance Computing (HPC) infrastructure growth, diversifying its portfolio beyond digital asset volatility. This dual focus positions Bit Digital at the convergence of economic and intelligence infrastructure.

This repository, reinforcement-learning-algorithms, offers PyTorch implementations of various classic deep reinforcement learning algorithms. It includes popular methods such as Deep Q-Learning Network (DQN), Double Q-Network (DDQN), Dueling Network Architecture, Deep Deterministic Policy Gradient (DDPG), Soft Actor-Critic (SAC), Advantage Actor-Critic (A2C), Proximal Policy Optimization (PPO), and Trust Region Policy Optimization (TRPO). The project aims to provide clear and well-structured code to facilitate learning and experimentation with these algorithms. It also includes utilities for environment wrapping, experience replay, logging, and MPI training, making it a comprehensive resource for developers and researchers in the field.

Awesome-Federated-Learning is a curated list of federated learning publications, primarily re-organized from Arxiv. Hosted on GitHub, it serves as a valuable resource for researchers and practitioners interested in the field of federated learning. The repository includes a wide range of papers categorized by research areas such as statistical challenges, trustworthiness, system challenges, models and applications, and benchmarks. It highlights publications from top-tier conferences like ICML, NeurIPS, ICLR, CVPR, ACL, AAAI, and KDD, detailing their venue, year, targeting problem, and method. The latest updates and ongoing research are now maintained on the FedML repository, ensuring the list remains current and comprehensive.

PyGaze is an open-source, cross-platform Python package designed for the minimal-effort programming of eye tracking experiments. It provides a comprehensive toolbox for researchers in cognitive science and psychology to create and run gaze-contingent or non-gaze-contingent experiments. The tool supports various eye trackers and offers functionalities for data analysis, making it a valuable resource for academic research. PyGaze is freely available to use and modify under the GNU Public License (version 3), emphasizing its commitment to open science and collaborative development within the scientific community.

Surprise is an open-source Python scikit designed for building and analyzing recommender systems, specifically those dealing with explicit rating data. It offers users precise control over experiments, emphasizing clear documentation for algorithm details. The library simplifies dataset handling, allowing the use of built-in datasets like Movielens and Jester, as well as custom datasets. Surprise includes a variety of prediction algorithms, such as baseline algorithms, neighborhood methods, and matrix factorization-based approaches like SVD, PMF, SVD++, and NMF. It also provides various similarity measures and tools for evaluating, analyzing, and comparing algorithm performance, including cross-validation procedures and exhaustive parameter searches. The project is licensed under BSD 3-Clause, making it suitable for commercial applications.

Enki is an AI-powered coach designed to accelerate learning in coding, data science, and productivity tools like Python, SQL, Spreadsheets, Tableau, and Power BI. It provides personalized, AI-driven coaching combined with state-of-the-art, structured learning content, making it an interactive remote coaching experience. Users benefit from 1:1 AI coaching, personalized exercises, and interactive practice, all designed to apply new skills directly to their work. Enki also offers tailored learning paths and custom modules for teams, ensuring relevance to any company stack and maximizing efficiency. With over 3 million professionals learning on the platform, Enki aims to make tech skill acquisition cost-effective and highly impactful.

🇨🇿 BenCzechMark is an AI tool designed for benchmarking AI models by allowing users to submit their model details to a public leaderboard. Users can provide information such as team name, model name, type, parameters, input length, and a link, along with a JSON results file. After validation, the submitted models are added to the leaderboard, facilitating the evaluation and comparison of AI system performance. This platform is hosted on Hugging Face, making it accessible for developers and researchers interested in assessing their AI models against others in a standardized manner. It serves as a valuable resource for understanding the strengths and weaknesses of various AI models.