AI Agents & Automation

Gemma3n Visual (Audio) Question Answering is an AI tool that enables users to interact with images using audio queries. By uploading an image and speaking a question, users receive a text-based answer. This functionality makes it a valuable resource for multimodal AI research, allowing for exploration into how AI can process and respond to combined visual and auditory inputs. The tool is built as a Hugging Face Space, indicating its accessibility and potential for community-driven development and experimentation in the field of AI agents and automation.

Explainerdashboard is an open-source Python package designed to quickly build Explainable AI dashboards for 'blackbox' machine learning models. It offers interactive plots to visualize model performance, feature importances, feature contributions to individual predictions, and 'what if' analysis. The tool supports various models including scikit-learn, xgboost, catboost, lightgbm, and skorch. Users can explore components in a notebook environment, design custom layouts, or combine multiple dashboards into an ExplainerHub. Dashboards can be exported to static HTML, making it easy to share insights and integrate into CI/CD processes.

herearemytimes is a privacy-first calendar availability tool designed to simplify scheduling. It connects with Google Calendar to merge selected calendars and identify free slots, removing overlapping busy times. Users can set date ranges, time windows, slot durations, and timezones to generate precise availability. The tool then converts this complex calendar data into simple, copy-ready text that can be shared immediately. It prioritizes privacy by only using calendar free/busy access to calculate intervals and format output, storing only encrypted tokens, calendar IDs, and preferences, without storing event details like titles, attendees, or descriptions.

UVIONIX Innovations provides an advanced solution for warehouse inventory management and verification, leveraging Autonomous Flying Robots (AFRs) and AI-driven perception. Their system, which includes the U-Vee drone and Uvionix.Cloud platform, monitors and reports live data to ensure comprehensive operational visibility and near 100% inventory accuracy. It creates live digital twins of warehouse spaces, meticulously tracking material movements. By delivering precise, unbiased data and being immune to human error, the platform significantly enhances material planning, reduces stock losses, and lowers labor costs. The U-Vee drone offers over 60 minutes of flight time, self-recharging capabilities, and fully autonomous operations without human intervention, making facility monitoring radically more efficient, accurate, and scalable.

MiniMax-M1 is the world's first open-weight, large-scale hybrid-attention reasoning model, powered by a hybrid Mixture-of-Experts (MoE) architecture combined with a lightning attention mechanism. Developed based on the MiniMax-Text-01 model, it features 456 billion parameters with 45.9 billion parameters activated per token. A key differentiator is its native support for a context length of 1 million tokens, significantly larger than competitors. The lightning attention mechanism ensures efficient scaling of test-time compute, consuming 25% of the FLOPs compared to DeepSeek R1 at a generation length of 100K tokens. MiniMax-M1 is trained using large-scale reinforcement learning (RL) on diverse problems, including mathematical reasoning and software engineering. It offers two versions with 40K and 80K thinking budgets, outperforming other strong open-weight models on complex software engineering, tool-using, and long-context tasks. It also supports function calling capabilities and provides a chatbot and API for general use and evaluation.

mmrazor is a comprehensive model compression toolkit and benchmark developed as part of the OpenMMLab project. It offers four mainstream technologies: Neural Architecture Search (NAS), Pruning, Knowledge Distillation (KD), and Quantization. Designed for flexibility and compatibility, mmrazor can be easily integrated with various OpenMMLab projects and allows for plug-n-play incorporation of different algorithms. Its modular design enables developers to implement new model compression algorithms with minimal code or by modifying configuration files. The toolbox supports a wide range of algorithms within each category, including DARTS, DetNAS, SPOS for NAS; AutoSlim, L1-norm, Group Fisher, DMCP for pruning; and various methods like CWD, WSLD, ABLoss for KD. It also includes PTQ, QAT, and LSQ for quantization, making it a versatile tool for optimizing deep learning models.

motion_imitation is a code repository accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals." It provides a Gym environment for training a simulated quadruped robot to imitate various reference motions, offering example training code for learning policies. The tool supports Python 3.7 or 3.8 on Ubuntu, MacOS, and Windows, and can be installed as a pip package. It includes features for training and testing imitation models, working with motion capture data, and implementing locomotion using Model Predictive Control (MPC). The repository also details how to run MPC on real A1 robots, making it a comprehensive resource for researchers and developers in robotic locomotion.

MotioNet is a deep neural network designed to reconstruct 3D human skeletal motion directly from monocular video. This library provides the source code for the network, which is based on a common motion representation. A key feature is its ability to output BVH files directly, eliminating the need for additional post-processing steps. The tool supports evaluation on both Human3.6m and wild videos, with integration for 2D pose detection tools like Openpose. Users can train models from scratch with customizable parameters or utilize provided pre-trained models for quick starts. It offers visualization through TensorBoardX for tracking training progress and includes detailed instructions for data preparation and testing. While powerful, it has limitations regarding moving cameras and dependence on 2D detection accuracy, which users should consider.

neurodiffeq is an open-source Python library built on PyTorch, designed for solving ordinary and partial differential equations (ODEs and PDEs) using neural networks. It provides a flexible framework for implementing existing techniques of using artificial neural networks (ANNs) to approximate solutions. Unlike traditional numerical methods, neurodiffeq aims to compute continuous and differentiable solutions. The library supports various features including solving systems of ODEs and PDEs, handling initial and boundary conditions, and customizing network architectures. It also offers tools for monitoring training progress, implementing transfer learning, and defining custom sampling strategies for training points. Additionally, neurodiffeq supports solving solution bundles and inverse problems, making it suitable for complex scientific and engineering applications.

Neuton TinyML, part of the Nordic Edge AI Lab, is a platform designed for building and deploying ultra-compact AI models specifically optimized for Nordic System-on-Chips (SoCs). It caters to both CPU-run edge AI with Neuton's self-growing models and NPU-enabled devices with LiteRT models, requiring no-code for wake word models and LiteRT configuration. The platform simplifies the AI development process into three steps: data upload, automated or configured model training, and deployment. It supports various intelligent applications like gesture recognition, anomaly detection, and health monitoring, focusing on low-power consumption, balanced memory and performance, and extended battery life for always-on sensing. It also includes data preprocessing tools like windowing, feature extraction, and selection, alongside model analysis features such as quality diagrams and confusion matrices.

Nummi is a spiritual and personal AI designed to provide clarity, guidance, and reflection. It integrates advanced AI memory capabilities with insights from Vedic astrology, helping users understand patterns and connect various aspects of their lives. The tool offers daily clarity messages and focuses on pattern recognition, aiming to support mental wellness and emotional balance. Nummi is available on both Android and iOS platforms, providing a private and secure environment for personal exploration and self-awareness. It is ideal for individuals seeking a deeper understanding of themselves and their life's journey through a blend of AI and ancient wisdom.

object-detection-opencv provides a Python-based solution for object detection using the YOLO (You Only Look Once) framework, integrated with OpenCV's dnn module. This tool allows developers to perform inference on pre-trained deep learning models from popular frameworks like Caffe, Torch, and TensorFlow. Specifically, it leverages YOLOv3 weights for efficient object detection in images. The project is open-source and available on GitHub, offering a practical example for computer vision tasks. It's particularly useful for those looking to implement object recognition capabilities in their applications using Python and OpenCV, providing a foundation for further development in areas like real-time video analysis or image processing.

oie-resources offers a comprehensive, curated list of resources focused on Open Information Extraction (OIE). This GitHub repository serves as a central hub for researchers and academics, providing access to a wide array of materials including research papers sorted chronologically and by category, code implementations, and datasets. It covers not only core OIE systems but also related work such as taxonomizing open relations and various downstream applications like Question Answering, Knowledge Base Population, and Event Extraction. The resource also features information on OIE systems for different languages, supervised OIE, PhD theses, and demos, making it an invaluable reference for anyone working in the field of natural language processing and information extraction.

OpenChem is a deep learning toolkit specifically designed for computational chemistry and drug design research, built with a PyTorch backend. Its primary goal is to simplify the application of deep learning models for researchers in these fields. Key features include a modular design with a unified API, allowing for easy combination of different modules, and the ability to build new models using only a configuration file. The toolkit supports fast training with multi-GPU capabilities and provides utilities for data preprocessing. It also integrates with Tensorboard for visualization. OpenChem handles various tasks such as classification, regression, multi-task learning, and generative models, supporting data types like character sequences (SMILES, amino acids) and molecular graphs, with automatic conversion of SMILES to graphs.

RecommenderSystem-Paper is an open-source GitHub repository that serves as a curated collection of significant papers, tools, and frameworks within the domain of recommender systems. It is designed to assist researchers and academics by providing a centralized resource for reading and exploring key advancements. The repository categorizes papers by conference (e.g., KDD, ICDM, AAAI, WWW, NIPS, ICML, CIKM, SIGIR, Recsys, WSDM) and by interesting topics such as Cold Start and Deep Learning. Beyond academic papers, it also lists useful recommender system engines like Mosaic and Crab, and algorithm frameworks such as Surprise and LightFM, making it a comprehensive resource for understanding and implementing recommender technologies.

Qlib is an AI-oriented quantitative investment platform developed by Microsoft, designed to empower quantitative research using AI technology. It supports diverse machine learning modeling paradigms, including supervised learning and reinforcement learning, making it suitable for various financial analysis tasks. The platform is equipped with tools to automate the research and development process, streamlining the creation and testing of investment strategies. As an open-source project available on GitHub, Qlib provides a robust framework for developers and data scientists to build and experiment with advanced AI models in the finance domain, fostering innovation in quantitative investment.

Attri specializes in creating AI employees designed for enterprise teams, offering a robust platform for managing and deploying these agents. The system, known as EnterpriseOS, allows for flexible deployment either on the client's cloud infrastructure or Attri's own. These AI agents are engineered to be trustworthy and are aimed at transforming operational workflows within large organizations. By providing a scalable and manageable AI workforce, Attri helps enterprises automate complex tasks, enhance efficiency, and innovate their business processes. The focus is on delivering reliable AI solutions that integrate seamlessly into existing enterprise environments.

rikkahub is an Android application designed to offer a native chat client experience for various Large Language Model (LLM) providers. Users can seamlessly switch between different LLM services within the app, enabling flexible and diverse conversational interactions. The tool aims to provide a convenient and integrated platform for accessing and utilizing multiple AI chat functionalities directly from an Android device. It focuses on delivering a smooth user experience for engaging with AI models.

RLzoo is a comprehensive open-source reinforcement learning zoo designed for simple usage, implemented with TensorFlow 2.0 and leveraging the neural network layer APIs of TensorLayer2.0+. It offers a hands-on approach for reinforcement learning practices and benchmarks, supporting basic toy-tests like OpenAI Gym and DeepMind Control Suite with minimal configuration. Additionally, RLzoo supports robot learning environments such as RLBench. The platform provides both implicit and explicit configuration interfaces for running learning algorithms, making it flexible and convenient for users. It also supports distributed training across multiple computational nodes using the Kungfu package, catering to more realistic and large-scale scenarios.

Roboflow-python is an open-source Python package designed to streamline the development of computer vision applications. It provides a comprehensive set of tools for managing datasets, training models, and deploying them efficiently. The package supports a wide range of computer vision tasks, making it a versatile choice for developers working on object detection, image classification, and other related projects. Its open-source nature fosters community collaboration and allows for flexible integration into existing workflows, providing a robust foundation for building and experimenting with AI-powered vision systems.

relational-networks is an open-source Pytorch implementation of the "A simple neural network module for relational reasoning" paper, also known as Relational Networks. This tool is designed for researchers and developers working on visual reasoning and relational AI tasks. It has been thoroughly tested on the Sort-of-CLEVR task, a simplified version of CLEVR, which involves processing images with various colored shapes and answering both relational and non-relational questions. The implementation demonstrates superior performance compared to traditional CNN + MLP models, particularly in relational reasoning tasks, and includes modifications for improved computational efficiency.

rulesync is an open-source Node.js CLI tool designed to automate the generation of configuration files for AI coding agents. This tool is particularly useful for developers and teams working on AI development projects, as it streamlines workflows and simplifies the management of agent configurations. By automating these tasks, rulesync helps to ensure consistency and reduce manual effort, fostering better collaboration within development teams. Its command-line interface makes it accessible for integration into existing development pipelines, providing a flexible solution for managing the underlying settings that drive AI coding agents.

ScreenAgent is a sophisticated computer control agent driven by visual language large models, designed to automate complex desktop tasks. It creates an environment where Visual Language Model (VLM) agents can interact with real computer screens by observing screenshots and executing mouse and keyboard operations. The tool employs an automatic control process encompassing planning, action, and reflection stages, guiding the agent to continuously interact with the environment and complete multi-step tasks. ScreenAgent supports various action types and attributes, leveraging a VNC remote desktop connection protocol for universal applicability across different desktop operating systems and applications. It also includes the ScreenAgent dataset, which comprises screenshots and action sequences from diverse daily computer tasks like file operations, web browsing, and gaming, facilitating the training of agents in task planning, image understanding, visual positioning, and tool use.

rl-agents is an open-source project providing a comprehensive collection of Reinforcement Learning agent implementations. This tool is designed for researchers and developers working in the field of AI, offering a variety of planning and learning algorithms. It serves as a valuable resource for experimentation and building new RL applications. The project's open-source nature fosters community contributions and allows for flexible integration into diverse research and development environments, making it suitable for both academic and practical applications in reinforcement learning.