Coding & Development

awesome-offline-rl is a comprehensive, open-source collection of research and review papers specifically focused on offline reinforcement learning (offline-rl) algorithms. Maintained by researchers from Cornell University and Hanjuku-kaso Co., Ltd., this repository serves as a valuable index for anyone delving into the field. It organizes papers into categories such as Review/Survey/Position Papers, Offline RL: Theory/Methods, Benchmarks/Experiments, and Applications, as well as Off-Policy Evaluation and Learning. The resource also lists open-source software, implementations, blogs, podcasts, workshops, tutorials, and talks, making it a central hub for academic and practical insights into offline RL. Contributions are welcomed to expand and maintain this growing index.

Mapless Driving is a Hugging Face Space designed for an AI competition, offering a centralized platform for participants. Users can easily access comprehensive competition details, including rules and dataset information. The platform facilitates submission management, allowing competitors to track and update their entries. A key feature is the leaderboard, which provides real-time ranking and performance insights. Hosted on Hugging Face, it leverages the platform's infrastructure for AI applications, making it accessible for developers and data scientists interested in autonomous driving challenges.

PufferLib is a fast and sane open-source reinforcement learning library designed to train tiny, super-human models efficiently. It includes a learning algorithm, hyperparameter tuning, and simulation methods developed through PufferAI's research. The library offers optimized parallel simulation and high-performance environments, making it suitable for both academic research and industrial applications. PufferLib aims to simplify working with complex environments by acting as a compatibility layer. All its tools are free and open source, with documentation hosted at puffer.ai. Support is available via Discord, and the project actively seeks new contributors.

Heidi is an AI care partner designed to support clinicians throughout their entire workday, from initial documentation to evidence-based decision-making and follow-up. It began by streamlining note-taking and has expanded to support all surrounding clinical tasks. The tool offers features like AI medical scribing, which transcribes consultations and generates structured notes, and an evidence tool for looking up research and treatment information. Heidi aims to reduce administrative burden, save clinicians time, and improve work-life balance, allowing them to focus more on patient care. It supports over 1.5 million consultations weekly and is used by clinicians across more than 10 clinical specialties globally.

Reinforcement-Learning-Notebooks offers a comprehensive collection of Reinforcement Learning algorithms, primarily implemented in Python. This resource is based on Sutton and Barto's seminal book and incorporates concepts from various research papers. It serves as an excellent supplementary material for students and researchers studying reinforcement learning, providing practical code examples to accompany theoretical knowledge. The notebooks were developed during a university course and are intended to be used alongside academic texts and lectures. While the code is acknowledged to be somewhat unpolished, it provides functional implementations for understanding complex RL concepts. It's an open-source project, encouraging collaboration and improvements from the community.

Gemma-3-R1984-4B is an AI model built on Google's Gemma-3-4B, designed for advanced reasoning, multimodal processing, and deep research. This application allows users to upload various document types, including CSV, TXT, and PDF, as well as images, to generate detailed and comprehensive responses. Beyond document and image analysis, it can perform web searches based on user queries, ensuring that the answers provided are thorough and up-to-date. The tool is particularly suited for agentic AI applications, offering robust capabilities for complex information processing and retrieval.

Free AI Detector is an AI-powered tool specifically designed to analyze text and determine its origin, distinguishing between AI-generated content and human-written material. It offers broad compatibility, supporting outputs from leading AI models such as ChatGPT, Gemini, and Claude. A key feature of the tool is its integrated plagiarism scanner, which further aids in content verification. The primary goal of Free AI Detector is to help users ensure their content is authentic, original, and maintains a human-like quality.

SegmentAnythingin3D (SA3D) is an open-source framework designed for 3D object segmentation within Neural Radiance Fields (NeRFs). It allows users to segment any target object in 3D by providing prompts from a single rendered view. The tool projects 2D segmentation masks onto 3D mask grids via density-guided inverse rendering, iteratively refining the 3D masks. SA3D supports various radiance fields without requiring additional redesign. It offers both point and text prompting options through a GUI, and the entire process for obtaining a target 3D model can be completed rapidly, with recent updates allowing 3D segmentation within seconds using 3D Gaussian Splatting.

AlgorithmicTrading is an open-source repository offering three distinct methods for identifying and exploiting arbitrage opportunities: Dual Listing Arbitrage, Options Arbitrage, and Statistical Arbitrage. Developed in collaboration with Optiver and peer-reviewed by their staff, this resource provides a robust foundation for understanding these complex financial strategies. While the analysis offers valuable insights into how these methods operate, the repository explicitly notes that effective implementation typically requires C++ for speed and a lightning-fast connection, making it less feasible for retail investors. It serves primarily as an educational and research tool for those interested in advanced algorithmic trading concepts.

Waveformer is an open-source web application designed to generate music from text prompts. Leveraging the MusicGen technology, it offers users an intuitive and accessible platform for music creation. The tool allows for the effortless production of customized music, catering to a diverse audience. It is suitable for both professional musicians looking for new creative avenues and hobbyists interested in exploring music generation, providing a unique method to produce original tunes.

Structure_knowledge_distillation is an open-source repository providing the official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation' (CVPR 2019 ORAL) and its extension to other dense prediction tasks. This tool facilitates the transfer of structured knowledge from a larger, more complex teacher model to a smaller, more efficient student model. It includes implementations for pixel-wise, pair-wise, and holistic distillation methods, demonstrating improved performance on tasks like semantic segmentation, object detection, and depth estimation. The repository offers pre-trained models and detailed instructions for compiling and running tests, making it a valuable resource for researchers and practitioners in the field of computer vision.

OpenArm is a fully open-source 7DOF humanoid arm specifically engineered for physical AI research and deployment, particularly in contact-rich environments. Its design emphasizes high backdrivability and compliance, making it suitable for safe human-robot interaction while still providing practical payload capabilities for real-world applications. The arm features human-scale proportions and is available as a complete bimanual system for $6,500 USD, offering a flexible platform for teleoperation, imitation learning, simulation, and real-world data collection. OpenArm is under continuous development, actively seeking contributors, research partners, and company collaborators to advance practical humanoid systems.

RPi-Monitor is an open-source application specifically designed for real-time monitoring of embedded devices, with a primary focus on the Raspberry Pi B platform. It offers a robust set of features including an embedded web server for easy access, alert messaging to notify users of critical events, and SNMP integration for broader network management. The tool is engineered to separate information extraction from presentation, enhancing both performance and security. Installation is straightforward with Debian packages available for Raspbian, and documentation covers usage, customization, and development contributions. It's a valuable resource for anyone needing detailed, real-time insights into their embedded systems.

Docker Examples offers a collection of templates specifically designed for Hugging Face Spaces, enabling users to quickly deploy and configure development environments. This tool simplifies the process of setting up JupyterLab or VSCode instances, providing custom configurations to streamline workflows. It serves as a valuable resource for developers and software engineers looking to understand and implement containerization within the Hugging Face ecosystem. By offering practical examples, Docker Examples helps users grasp the fundamentals of Docker and its application in AI development environments.

DETR Object Detection is an AI tool hosted on Hugging Face Spaces by ClassCat, designed for performing object detection on images. Users can easily upload their own pictures or select from provided samples. The application offers a choice between two DETR models, ResNet-50 or ResNet-101, to conduct the object detection. Once processed, the tool returns the image with detected objects highlighted by colored bounding boxes, along with their corresponding class names and confidence scores. This makes it a valuable resource for computer vision research, AI model development, and general image analysis tasks.

FoleyCrafter is an AI tool designed to generate realistic and synchronized audio for silent video clips. Users can upload a video and provide a prompt to describe the desired sound effects, and the application will output a video with the newly generated audio. This tool is particularly useful for content creators, filmmakers, and game developers who need to quickly add high-quality Foley sound effects to their projects without extensive manual audio editing. It streamlines the audio post-production workflow by automating the creation of contextually relevant soundscapes based on textual descriptions, enhancing the overall immersive experience of visual content.

DINOv3 Keypoint Matching is an AI tool hosted on Hugging Face Spaces, designed to identify and highlight corresponding keypoints across two uploaded images. Users can leverage various DINOv3 models to optimize the accuracy of keypoint detection and matching. This tool is particularly useful for tasks requiring precise visual correspondence, such as object recognition, image analysis, and computer vision research. Its web-based interface makes it accessible for quick experimentation and demonstration of DINOv3's capabilities in visual feature extraction and matching.

githubchart-api is an open-source tool designed to embed GitHub contribution charts as images. This utility allows developers to showcase their annual coding activity and productivity visually on personal websites, portfolios, or other online platforms. It supports custom color schemes, enabling users to personalize the chart's appearance by providing a hex color code. The tool is easy to set up and deploy, requiring Ruby and a few commands to get it running locally or deployed via Heroku. It provides a simple yet effective way to integrate GitHub's iconic green contribution calendar outside of the GitHub website, offering a unique data visualization for individual developers.

Danbooru Images is a Hugging Face Space that provides a convenient way to browse and filter a large collection of anime-style images from Danbooru. Users can apply score ranges and tags to refine their search, making it easy to find specific types of images. The tool presents results in a paginated format, displaying each image along with its associated score and tags. This functionality is particularly useful for those involved in AI model training, image analysis, or content creation within the anime domain, offering a structured approach to accessing and organizing visual data.

The Deep Reinforcement Learning Leaderboard is a Hugging Face Space designed to showcase and compare the performance of various reinforcement learning models. Users can easily search for specific models using a user ID, making it simple to track their own contributions or explore others' work. The platform provides crucial performance metrics, including mean reward and standard deviation, offering a clear overview of each model's effectiveness. This tool is invaluable for AI researchers and students who need to benchmark algorithms, understand progress in the field, and identify top-performing models in deep reinforcement learning.

Dataset Migrator is a practical tool designed to streamline the process of moving datasets between different platforms. Specifically, it enables users to transfer datasets from GitHub or Kaggle repositories directly to the Hugging Face Hub. This migration capability is crucial for AI model deployment and research activities, as it centralizes datasets for easier sharing and access within the AI community. The tool requires users to provide the source repository URL and the destination repository details. It leverages Hugging Face OAuth for necessary write and manage repository permissions, ensuring secure and authorized data transfer. The interface is built using Gradio, making it accessible and user-friendly for those looking to manage their AI datasets efficiently.

MONAI Label is an intelligent open-source image labeling and learning tool designed to reduce the time and effort of annotating new datasets, particularly for medical imaging. It allows users to create annotated datasets and build AI annotation models for clinical evaluation. The tool operates as a server-client system, facilitating interactive medical image annotation through AI, and can run locally on a machine with single or multiple GPUs. It supports various medical imaging modalities and integrates with popular viewers like 3D Slicer, OHIF, QuPath, and CVAT. MONAI Label also provides a framework for developing and deploying custom labeling apps, offering compositional and portable APIs for easy integration into existing workflows.

Dbv4 Full Tagger Playground (dbv4-full) is an AI tool designed for image tagging, enabling users to upload images and obtain detailed descriptions of their content. The platform provides access to multiple pretrained dbv4-full tagger models, allowing users to select the best option for their specific needs. This tool is valuable for applications requiring automated content organization, image analysis, and research. While the live website currently shows a runtime error, its intended functionality is to provide a user-friendly interface for advanced image tagging.

DeepLabCut Model Zoo is a specialized tool designed for animal pose estimation, hosted on Hugging Face. It enables users to upload images and apply pre-trained models to detect animals and estimate their poses. The application offers a selection of animal detectors and pose-estimation models, drawing bounding boxes and keypoint markers on identified animals. Users can also adjust confidence thresholds for more precise results. This tool is particularly useful for researchers and scientists in fields requiring detailed analysis of animal behavior and movement tracking.