AI Agents & Automation

cosine_metric_learning offers a repository with code for training a metric feature representation, specifically tailored for person re-identification tasks. This tool is intended to be used in conjunction with the deep_sort tracker, implementing the approach described in the 'Deep Cosine Metric Learning for Person Re-identification' paper. It includes functionalities to train models on datasets like Market1501 and MARS, with options for different loss modes such as cosine-softmax. Users can monitor training progress and evaluation metrics using TensorBoard, export features for testing, and freeze trained models for deployment with Deep SORT. The repository provides detailed instructions for setting up datasets, initiating training, and evaluating model performance.

Facetorch App is a Python library designed for comprehensive facial analysis, available as a Hugging Face Space. It allows users to upload photos or use a webcam to detect faces, generate 3D facial landmarks, and analyze various facial attributes. The app provides detailed reports on detected facial expressions, action units, and emotion scores. It also includes capabilities for extracting facial embeddings and performing face recognition. This tool is particularly useful for developers and researchers in computer vision who require advanced facial analysis functionalities for their projects.

samples-for-ai is a comprehensive collection of deep learning samples and projects designed to help beginners get started with deep learning. It encompasses a wide range of classic deep learning algorithms and applications, supporting multiple frameworks including TensorFlow, CNTK (BrainScript and Python), PyTorch, Caffe2, Keras, MXNet, Chainer, and Theano. The project offers samples in Visual Studio solution format, making it accessible for users leveraging Microsoft Visual Studio Tools for AI or Open Platform for AI. Users can run samples locally or submit jobs to OpenPAI, providing flexibility in deployment. This open-source initiative encourages contributions and adheres to the Microsoft Open Source Code of Conduct, fostering a collaborative environment for deep learning development.

SPTAG (Space Partition Tree And Graph) is an open-source library developed by Microsoft Research and Microsoft Bing, designed for large-scale vector approximate nearest neighbor search. It represents samples as vectors and compares them using L2 or cosine distances. SPTAG offers two primary methods: kd-tree (SPTAG-KDT) for efficient index building and balanced k-means tree (SPTAG-BKT) for superior search accuracy in high-dimensional data. Key features include fresh updates for online vector deletion and insertion, and distributed serving across multiple machines. The library is inspired by the NGS approach and uses k-nearest neighborhood graphs for enhanced connectivity, with balanced k-means trees replacing kd-trees for improved accuracy with high-dimensional vectors. It provides an iterative search process combining tree and graph searches.

Stable-Baselines3 (SB3) is a robust open-source library offering reliable implementations of reinforcement learning (RL) algorithms built on PyTorch. It serves as the next major version of Stable Baselines, aiming to facilitate the replication, refinement, and identification of new ideas within the RL community and industry. SB3 provides a common interface, supports custom environments and policies, and includes features like Tensorboard integration, custom callbacks, and high code coverage. While designed for ease of use, it assumes some prior knowledge of RL concepts. The library is actively maintained for bug fixes and documentation updates, with newer algorithms and faster variants developed in associated repositories like SB3 Contrib and SBX (SB3 + Jax).

Worlder TEAM Pte. Ltd. specializes in providing AI-driven solutions to help small to medium-sized businesses (SMEs) digitalize their operations and achieve global growth. The company offers a suite of cutting-edge tools, including Worlder AI Solutions and Wolo Tools, designed to empower SMEs with modern AI capabilities. Their services also include cloud solutions and consultation to facilitate digital transformation. Worlder TEAM aims to bridge the gap for businesses looking to leverage AI for operational efficiency and market expansion, focusing on practical applications of AI to drive business success.

stable-fast is an ultra-lightweight inference optimization framework specifically designed for HuggingFace Diffusers on NVIDIA GPUs. It achieves state-of-the-art inference performance across various diffuser models, including StableVideoDiffusionPipeline, with compilation times of only a few seconds, unlike other solutions that can take dozens of minutes. The framework supports dynamic shapes, LoRA, and ControlNet, and integrates key techniques such as CUDNN Convolution Fusion, Low Precision & Fused GEMM, Fused Linear GEGLU, NHWC & Fused GroupNorm, and CUDA Graph. It also improves the `torch.jit.trace` interface for more stable tracing of complex models and offers dynamic quantization for VRAM reduction, making it a powerful tool for developers working with AI models.

Teachable Machine Community is an open-source repository offering example code snippets and machine learning code for Teachable Machine. Teachable Machine is a web-based tool designed to make machine learning model creation fast, easy, and accessible for everyone, including educators, artists, students, and innovators. Users can train a computer to recognize images, sounds, and poses without needing prior machine learning knowledge or coding. The repository includes a libraries section with machine learning code utilizing Tensorflow.js for in-browser model training and execution, along with API helper libraries for integrating exported models into projects. It also features a snippets section with code and instructions for using Teachable Machine models in languages like Javascript, Java, and Python.

Singulr AI delivers enterprise AI governance through its unified control plane, offering complete visibility, security, and compliance. The platform helps organizations discover, secure, and optimize AI adoption at scale by addressing challenges like shadow AI, data leakage, and compliance risks. Key features include AI Risk Intelligence powered by Singulr Pulse, application-aware AI red teaming, and enhanced runtime protection. It enables cross-functional collaboration for security, IT, privacy, and compliance teams, ensuring secure innovation without creating bottlenecks and accelerating AI adoption while maintaining control.

Agentic Employment is a tool hosted on Hugging Face Spaces by ruv, designed to streamline AI agents. The primary goal of this application is to enhance the performance and efficiency of AI agents across various applications. While the current live website content indicates a runtime error, suggesting it may not be fully operational or accessible at the moment, its stated purpose is to optimize agentic workflows. It is categorized under AI Agents & Automation, specifically within AI Frameworks & Infra, indicating its focus on foundational aspects of AI agent development and deployment. The tool is intended to be free to use, making it accessible for developers and researchers interested in agentic AI.

USearch is a fast, open-source search and clustering engine designed for vectors and arbitrary objects. It offers a highly optimized HNSW implementation, boasting up to 10x faster performance than FAISS. The engine supports a wide array of programming languages including C++, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram, making it broadly compatible across different development environments. Key features include SIMD-optimized and user-defined metrics with JIT compilation, hardware-agnostic half-precision support (bf16, e5m2, i8), and the ability to view large indexes from disk without loading them into RAM. USearch also provides heterogeneous lookups, on-the-fly deletions, and binary Tanimoto/Sorensen coefficients for specialized applications like genomics. Its compact codebase and native bindings contribute to lower call latencies and faster deployments.

VINTECC empowers industries through intelligent innovation, leveraging tailor-made software solutions and state-of-the-art AI technology. Their offerings include computer vision for inspection and quality control, digital twins for simulation and validation, autonomous systems to reduce human error, and industrial IoT & data analytics for objective decision-making. By accelerating industrial processes, VINTECC aims to deliver increased efficiency, productivity, and profitability for their clients. They focus on transforming operational excellence and supporting the shift from automation to autonomy across various sectors.

StreamDeploy is a specialized deployment platform designed for robotics and edge AI fleets, offering containerized over-the-air (OTA) updates. It streamlines the deployment process for devices like NVIDIA Jetson Orin, Google Coral TPU, ROC-RK3588, and ROS2-based robots. The platform provides features such as safe rollouts with canary deployments, hardware compatibility checks, and instant rollback capabilities to ensure reliability and minimize downtime. Unlike generic IoT platforms, StreamDeploy is optimized for the unique demands of edge AI workloads and robotics workflows, offering curated, production-ready containers and version-controlled configurations for scalable fleet management.

TensorFlow Lite for Microcontrollers (tflite-micro) is an optimized port of TensorFlow Lite, specifically engineered to deploy machine learning models on devices with limited memory and processing power, such as DSPs, microcontrollers, and other embedded targets. This infrastructure facilitates the integration of AI capabilities into IoT devices and other resource-constrained environments. Key features include support for various platforms like Arduino, Espressif Systems, and Renesas Boards, along with tools for continuous integration, benchmarking, and memory management. It also provides documentation for optimized kernel implementations, porting reference kernels, and a Python development guide, making it a comprehensive solution for developers working on edge AI applications.

SoTA-Point-Cloud is a GitHub repository offering an extensive survey of deep learning techniques applied to 3D point clouds. Published in IEEE TPAMI 2020, this resource covers major tasks such as 3D shape classification, 3D object detection, and 3D point cloud segmentation. It provides comparative results on numerous publicly available datasets, including ModelNet, KITTI, and Semantic3D. The repository also offers insightful observations and outlines future research directions, making it an invaluable resource for researchers and practitioners in the field of 3D computer vision. The maintainers regularly update the page with new results and suggestions.

UAV_Obstacle_Avoiding_DRL is a comprehensive open-source project focused on developing deep reinforcement learning algorithms for autonomous obstacle avoidance in Unmanned Aerial Vehicles (UAVs). It addresses both static and dynamic environments, offering multiple approaches for each. For static environments, the project explores Multi-Agent Reinforcement Learning (MADDPG, DDPG, TD3) combined with artificial potential field algorithms. In dynamic settings, it utilizes disturbed flow field algorithms alongside single-agent reinforcement learning (PPO+GAE, TD3, DDPG, SAC). The project also includes implementations of traditional path planning methods like A* search, RRT, Ant Colony Algorithm, and D* algorithm for comparison, highlighting the superior performance of reinforcement learning approaches. It provides both MATLAB and Python implementations for various algorithms, making it a valuable resource for researchers and developers in UAV navigation.

xLearn is a robust, high-performance machine learning package developed in C++ for maximum CPU and memory utilization. It includes implementations of linear models (LR), factorization machines (FM), and field-aware factorization machines (FFM), making it ideal for solving large-scale machine learning problems, particularly with high-dimensional sparse data common in recommendation systems. The package is designed for ease of use, requiring no third-party libraries for compilation and offering simple Python and CLI interfaces. xLearn also boasts scalability, supporting out-of-core training to handle terabytes of data by leveraging disk storage, and includes features like cross-validation and early-stop mechanisms.

Yellowbrick is an open-source suite of visual diagnostic tools, known as "Visualizers," designed to enhance the machine learning model selection process. It seamlessly integrates with scikit-learn and matplotlib, allowing users to generate insightful visualizations for their machine learning workflows. The tool supports various visualizers for feature analysis, such as Rank2D for pairwise feature comparisons, and model evaluation, like ROCAUC for classifier sensitivity and specificity. Yellowbrick is compatible with Python 3.4 or later and can be easily installed via pip or conda. It also provides access to several datasets for examples and testing, making it a comprehensive solution for data scientists and developers looking to visually steer their model development.

The Yi series models are a collection of open-source large language models developed from scratch by 01.AI. These models are designed to be bilingual, trained on a 3T multilingual corpus, and excel in language understanding, commonsense reasoning, and reading comprehension. The Yi-34B-Chat model has demonstrated strong performance, ranking highly on leaderboards like AlpacaEval. The series includes both chat-optimized and base models, with options for different parameter sizes (6B, 9B, 34B) and context window lengths (up to 200K). Yi models are built on the Transformer architecture, similar to Llama, but are not derivatives, utilizing independently created training datasets and infrastructure. They are available for deployment via pip, Docker, conda-lock, and llama.cpp, and can be fine-tuned or quantized for specific needs.

ZynqNet is an open-source project stemming from a Master Thesis, focusing on FPGA-accelerated embedded convolutional neural networks. It provides a comprehensive solution for image classification on embedded systems, featuring the ZynqNet CNN, an optimized and customized CNN topology, and the ZynqNet FPGA Accelerator, an FPGA-based architecture for its evaluation. The project also includes the Netscope CNN Analyzer, a custom tool for visualizing, analyzing, and editing CNN topologies. ZynqNet is designed for high efficiency, achieving 84.5% top-5 accuracy with minimal computational complexity, making it ideal for real-time and power-constrained applications. The repository offers the full project report, CNN prototxt, pretrained weights, HLS C++ source code for the accelerator, and firmware for the Zynq XC-7Z045 ARM processors.

SecretFlow is a comprehensive, open-source framework designed for privacy-preserving data analysis and machine learning. It features an abstract device layer that encapsulates various cryptographic protocols, enabling secure computation. The framework models algorithms as device object flows and DAGs, supporting both horizontal and vertical partitioned data. It also includes a workflow layer for seamless integration of data processing, model training, and hyperparameter tuning. SecretFlow is ideal for developers and data scientists working on sensitive data, offering tools for federated learning, homomorphic encryption, and secure multi-party computation to ensure data privacy throughout the ML lifecycle.

IntentKit is an open-source, self-hosted cloud agent cluster designed to manage a collaborative team of AI agents. It offers a cloud-native architecture for ultimate resource efficiency and is built with security in mind, ensuring agents cannot access secret keys. The framework supports collaborative AI, allowing multiple agents to interact, and comes out-of-the-box ready for use. It features an extensible skill system for adding new capabilities, optional Web3 and blockchain integrations, and seamless social media connectivity. IntentKit can be used as a Python library to add agent cluster capabilities to existing projects or interacted with via its built-in API endpoints.

temperature_scaling is an open-source Python module designed to calibrate neural networks by adjusting their confidence scores. Originally created as a demonstration for PyTorch 0.3, it implements temperature scaling, a post-processing technique that divides logits by a learned scalar parameter to minimize negative log-likelihood on a validation set. This helps address the common issue of neural networks outputting overconfident probabilities, ensuring that confidence scores better match true correctness likelihood. While the repository is unmaintained, it offers a clear example of how to integrate temperature scaling into a project for improved model calibration.

Augtech NextWealth IT Services Private Limited is an ISO 9001:2015 certified organization providing Information Technology and Information Technology Enabled Services. They focus on delivering world-class "Data Enrichment" and "Customer Interaction" services to clients in AI/ML tech, E-commerce, Fin-Tech, Education, and other sectors. Their expertise includes data collection from diverse sources, data preparation involving cleansing, consolidation, normalization, and validation, and data enrichment for AI/ML models, including multimedia annotation. The company also offers customer service operations, including inbound and outbound support. Augtech NextWealth is a social impact organization committed to providing opportunities to talent in Tier-2 and Tier-3 ecosystems.