AI Agents & Automation

KitOps is an open-source DevOps tool, governed by the CNCF, designed for packaging, versioning, and securely sharing AI/ML projects. It leverages OCI (Open Container Initiative) technology to bundle models, datasets, code, and configurations into versioned and layered artifacts, stored in existing container registries. This approach ensures immutability, tamper-proofing with SHA-256 digests, and cryptographic signing via Cosign, making it ideal for security-conscious enterprises and regulated industries. KitOps integrates seamlessly with AI/ML, CI/CD, and DevOps tools, supporting full lifecycle versioning from development to production. It also provides artifact and project metadata for establishing chain-of-custody and provenance, aligning with compliance frameworks like the EU AI Act and NIST AI RMF.

mdistiller is a comprehensive PyTorch library designed for implementing and experimenting with classical knowledge distillation algorithms across mainstream computer vision benchmarks. It serves as the official implementation for two significant research papers: "Decoupled Knowledge Distillation" (CVPR 2022) and "DOT: A Distillation-Oriented Trainer" (ICCV 2023). The library supports various distillation methods on datasets like CIFAR-100, ImageNet, and MS-COCO, offering researchers and developers a robust framework for model compression and performance enhancement. It provides tools for evaluation, training, and extending custom distillation methods, making it a valuable resource for advanced AI research and development.

Milksnake is an open-source setuptools extension designed for Python developers to efficiently distribute dynamic linked libraries within Python wheels. This tool stands out by offering a flexible hook to integrate custom build processes, such as those using 'cargo' for Rust binaries, directly into the Python packaging workflow. Unlike other projects that focus on Python extension modules, Milksnake aims to build regular native libraries that are then loaded at runtime using CFFI. This approach ensures greater portability across various platforms including Linux, Mac, and Windows, often requiring only a few universal wheels regardless of the number of Python interpreters targeted. It supports common setuptools commands like `bdist_wheel`, `build`, `build_ext`, and `develop`, and can generate universal wheels for broad compatibility.

HoloPart is an innovative AI tool available as a Hugging Face Space, designed to process segmented mesh files in GLB format. Users can upload their GLB files, and the application will intelligently separate the shape into its distinct, complete components. The tool then provides two new GLB files: one containing each individual part of the original mesh, and another presenting an exploded view that visually spreads out these components. This functionality is particularly useful for detailed analysis, visualization, or further manipulation of complex 3D models, offering a clear breakdown of their constituent elements.

model-viewer is an open-source 3D model viewer developed by PlayCanvas, designed to support glTF and 3D Gaussian Splats. This tool is blazingly fast and fully compliant with the glTF 2.0 specification, making it ideal for developers and designers working with 3D assets. Users can easily load glTF 2.0 scenes, including embedded glTF and binary glTF (GLB), by dragging and dropping files or folders directly into the 3D view. It also supports dragging and dropping images to set equirectangular or cube map backgrounds. The viewer offers URL query parameters for overriding aspects like initial camera position and specifying a glTF scene URL. Built on the PlayCanvas Engine, PCUI, and Observer libraries, it provides a robust platform for 3D model visualization.

Office-DDE-Payloads is a collection of Python scripts and templates designed to generate Microsoft Office documents (Word and Excel) embedded with Dynamic Data Exchange (DDE) payloads. This technique allows for macro-less command execution, making it a valuable tool for sanctioned red team engagements and phishing campaigns. The tool incorporates obfuscation and evasion techniques, particularly for Word DDE, inspired by security researchers. Users can generate simple or obfuscated DDE command strings and choose between various delivery methods, including hosting payload documents on a user-controlled server or sending them directly to targets. It also provides guidance on removing personal information from documents for operational security.

OpenEA is an open-source library and benchmarking study focused on embedding-based entity alignment for knowledge graphs. It addresses the challenge of finding entities that refer to the same real-world object across different knowledge graphs. The project surveys 23 recent embedding-based entity alignment approaches, categorizing them by technique, and provides a new KG sampling algorithm to generate dedicated benchmark datasets with various heterogeneity and distributions for realistic evaluation. The library integrates 12 representative embedding-based entity alignment approaches and several relationship and attribute embedding models, offering a flexible framework for researchers. It is developed using Python and TensorFlow, emphasizing loose coupling, functionality, and extensibility for easy integration of new methods.

oxml_xxe is a specialized open-source tool designed for security professionals and developers to test for XXE (XML External Entity) vulnerabilities within different file formats. It facilitates the embedding of XXE/XML exploits into OXML document types such as DOCX, XLSX, and PPTX, as well as ODT, ODG, ODP, ODS, SVG, and XML files. The tool is built using Ruby with Sinatra, Bootstrap, and Slim, offering flexible installation options including Docker, Docker Compose, or direct Ubuntu setup. It's a valuable resource for those looking to identify and understand XML-related security flaws in document processing applications.

Red Light Green Light is an interactive AI robotics demonstration hosted on Hugging Face Spaces by Pollen Robotics. This tool showcases the Reachy Mini robot playing the classic "Red Light, Green Light" game, providing an engaging and educational experience. Users can interact with the demonstration by entering their Reachy dashboard URL and clicking install to add apps to their robot. It serves as an accessible platform for those interested in observing and understanding the practical applications of AI in robotics, particularly in a playful and familiar context. The space highlights the capabilities of the Reachy Mini in a real-world, albeit simplified, scenario.

RoboHive is a comprehensive, open-source framework designed to facilitate robot learning through a collection of simulated environments and tasks. Utilizing the MuJoCo physics engine, it offers a robust platform for developing and testing robot learning algorithms. The framework is exposed via the OpenAI-Gym API, ensuring compatibility with popular agent training frameworks such as Stable Baselines, RLlib, TorchRL, and AgentHive. RoboHive includes diverse suites like Hand-Manipulation, Arm-Manipulation, Myo-Suite for musculoskeletal control, and MultiTask Suite, covering a wide range of robotic challenges. It's an essential tool for researchers and developers in robotics and AI, providing standardized benchmarks and environments for advanced manipulation and control tasks.

stable-baselines3-contrib is an open-source contrib package for Stable-Baselines3, designed to host experimental reinforcement learning (RL) algorithms and tools. It aims to maintain the simplicity, documentation, and style of Stable-Baselines3 while allowing for the inclusion of less matured implementations, such as those from recent publications. This repository addresses the need for a flexible space where the community can contribute niche utilities, environment wrappers, extended support, and new learning algorithms that might not fit directly into the main Stable-Baselines3 repository. It currently features RL algorithms like Augmented Random Search (ARS), Quantile Regression DQN (QR-DQN), MaskablePPO, RecurrentPPO, Truncated Quantile Critics (TQC), Trust Region Policy Optimization (TRPO), and CrossQ, alongside Gym Wrappers like the Time Feature Wrapper.

BLUE FROG ROBOTICS specializes in social robotics, developing human-centered solutions like Buddy, an emotional companion robot. Buddy is designed to foster connection, promote inclusion, and support educational, medical, and professional applications. It serves various sectors, including assisting hospitalized students, supporting seniors in nursing homes, enhancing business reception, and promoting social inclusion. The robot features an open and scalable platform with an Android SDK, allowing developers to create custom applications, integrate third-party services, and design interactive experiences tailored to specific needs. This adaptability makes Buddy a versatile tool for schools, retirement homes, and businesses seeking innovative robotic solutions.

JayDee is an AI solution that, according to its previous description, aimed to streamline business operations and enhance productivity. It was designed to offer tools for payroll services, CRM management, and ERP solutions, integrating with existing systems to save time and resources. The tool intended to maximize operational efficiency through machine learning techniques. However, the current live website displays an 'Index of /' page, indicating that the platform is either under development, experiencing technical difficulties, or is not publicly accessible in its intended form at this time. Therefore, specific features, pricing, and use cases cannot be verified from the live content.

face-api.js is an Open Source JavaScript API built on TensorFlow.js core, designed for robust face detection and recognition in both browser and Node.js environments. It offers a comprehensive set of features including face detection, 68-point face landmark detection, face expression recognition, age estimation, and gender recognition. Developers can easily load pre-trained models and utilize a high-level API to detect single or multiple faces, compute face descriptors for recognition, and compose various detection tasks. The library supports different face detectors like SSD Mobilenet V1 and TinyFaceDetector, and provides utility classes for drawing detection results. It's highly optimized for performance, especially in Node.js when integrated with `@tensorflow/tfjs-node`.

embedresponsively is an open-source tool designed to assist web content producers in converting fixed-width embedded content into fluid, responsive embeds. Based on research and work by Thierry Koblentz, Anders Andersen, and Niklaus Gerber, this tool allows for seamless adaptation of embedded elements like videos and iframes to different screen sizes and devices. It is licensed under the MIT license, making it a flexible and accessible solution for developers and content creators aiming to enhance the responsiveness of their web projects.

eks, or Embedded Knowledge Structure, is an open-source repository designed as a comprehensive knowledge base for embedded systems development. It covers a wide array of topics crucial for embedded engineers, including detailed information on various hardware components like CPUs (AMD, Intel, ARM, STM32, PIC), MCUs, FPGAs, and SOCs. The resource also delves into actuators, sensors, and electronic components. On the software side, eks provides insights into operating systems (uCOS, FreeRTOS, Linux, Windows CE), communication protocols (HTTP, MQTT, CAN, SPI), and programming concepts. Furthermore, it includes sections on circuit design, PCB design tools (Eagle, Altium, Kicad), and circuit simulation software. This makes eks an invaluable reference for anyone involved in embedded systems, from hardware design to software implementation.

Jupyter Agent is an AI-powered tool specifically developed for task automation. Its primary applications include content generation, where it can streamline the creation of various types of content, and educational applications, suggesting its utility in learning environments or for creating educational materials. The tool is accessible at no cost, making it a free resource for users. It is hosted and deployed on the HuggingFace platform, indicating its potential integration with other AI models and datasets available there.

Lama is an AI-powered tool available on Hugging Face that focuses on task automation. It enables users to streamline and automate a variety of tasks through artificial intelligence. The tool is provided as a free resource, making it accessible for a broad range of users. Its capabilities extend to areas such as content generation, where it can assist in creating various forms of content, and educational purposes, suggesting its utility in learning and teaching environments.

Lama Cleaner Lama is an AI tool available on Hugging Face designed to automate a variety of tasks. This tool leverages artificial intelligence to streamline processes, making it useful for different applications. It is specifically mentioned as being applicable for content generation, assisting users in creating various forms of content. Additionally, it can be utilized for educational purposes, suggesting its utility in learning environments or for creating educational materials. The tool is offered as a free resource, making it accessible to a broad audience interested in AI-powered automation.

GraphRAG is an open-source and modular system designed for Retrieval-Augmented Generation (RAG). It specializes in extracting structured data from unstructured text by leveraging Large Language Models (LLMs). This tool provides a comprehensive data pipeline and transformation suite, specifically engineered to improve an LLM's capacity to reason effectively about private or proprietary data. Its graph-based approach helps organize and connect information for better contextual understanding.

chatGPTai.org provides a convenient way to interact with ChatGPT without the need for account creation or logging in. This platform supports communication in 25 different languages, making it accessible to a global user base. Powered by advanced AI technology, it aims to offer assistance, provide answers to queries, and facilitate engaging conversations for a wide range of topics.

AppImageUpdate provides a decentralized solution for updating AppImages, leveraging information directly embedded within the AppImage file. This eliminates the need for central repositories, empowering upstream application projects to deliver easily updatable AppImages. The tool utilizes delta updates, ensuring that only the changed portions of an application are downloaded, leading to very small and efficient updates. It includes a GUI application, a command-line tool for updates, and a validation tool for signature integrity. AppImageUpdate aims to simplify the update process for users, reduce bandwidth for developers through delta updates, and maintain a distribution-independent approach. It is built in modern C++ (C++11) and is currently in beta, encouraging users to report any issues.

cuVS is an open-source library specifically designed to perform vector search and clustering operations directly on the GPU. This capability allows for significantly faster data analysis and accelerates various machine learning workflows. It provides a high-performance solution for tasks requiring efficient similarity search and data grouping, making it a valuable tool for professionals working with large datasets and complex models.

Deep3DFaceReconstruction is a powerful open-source tool for accurate 3D face reconstruction, initially implemented in TensorFlow. It leverages weakly-supervised learning to generate precise 3D face shapes and high-fidelity textures from single images or image sets. The method is robust to challenging conditions like large poses and occlusions, and it disentangles scene illumination to produce pure albedo. It also provides face pose estimation and 68 facial landmarks, useful for various downstream tasks. While the original TensorFlow repository is no longer actively maintained, a PyTorch implementation with improved performance is now available, making it a valuable resource for researchers and developers in computer vision.