AI Agents & Automation

cursor-deepseek is a high-performance HTTP/2-enabled proxy server designed to bridge the gap between Cursor IDE's Composer and various powerful language models like DeepSeek, OpenRouter, and Ollama. This proxy translates OpenAI-compatible API requests into the specific API formats required by DeepSeek, OpenRouter, or Ollama, allowing Cursor's Composer and other OpenAI API-compatible tools to seamlessly integrate and utilize these models. Key features include HTTP/2 support for improved performance, full CORS support, streaming responses, function calling/tools, automatic message format conversion, and compression support. It also offers API key validation for secure access and Docker container support for easy deployment.

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.

SiamTrackers is a comprehensive collection of PyTorch implementations for deep learning-based visual object tracking algorithms. It encompasses a wide range of models from 2020-2022, including SiamFC, SiamRPN, DaSiamRPN, UpdateNet, SiamDW, SiamRPN++, SiamMask, SiamFC++, SiamCAR, SiamBAN, Ocean, LightTrack, TrTr, and NanoTrack. A key highlight is NanoTrack, designed for lightweight and high-speed performance, suitable for deployment on embedded or mobile devices, capable of running at over 200FPS on Apple M1 CPU. The repository provides PyTorch code for training with lower GPU memory cost and includes Android and MacOS demos based on the ncnn inference framework. It also offers access to various datasets and toolkits for testing and training.

Own Tutor is an AI-powered educational platform designed to offer personalized learning experiences to students. The tool enables schools to develop custom AI tutors tailored to the specific needs of individual students, fostering a learning environment where students can progress at their own pace. By providing personalized guidance and support, Own Tutor aims to enhance understanding and improve academic success. The platform also supports the creation of virtual schools and offers features for managing lessons, making it a comprehensive solution for educational institutions looking to integrate AI into their teaching methodologies.

Deep-tempest extends the original gr-tempest project, also known as Van Eck Phreaking, by integrating deep learning techniques to significantly enhance the quality of spied images. This tool focuses on recovering visual information from unintended electromagnetic emanations, particularly those originating from HDMI cables. By applying advanced deep learning architectures like DRUNet, deep-tempest can reduce the Character Error Rate from 90% in the unmodified gr-tempest to less than 30%, making the recovered text much more legible. The project includes open-sourced code and a comprehensive dataset of synthetic and real captured images for research, training, and evaluation, supporting both Python 3.10 and 3.12 environments with Conda or Pyenv + venv setups.

Maiven Energy is a platform designed to accelerate decarbonization and reduce energy costs for residents, utilities, and contractors. For utilities and energy program implementers, Maiven offers an all-in-one digital solution to streamline energy reduction, VPP, demand-side management, decarbonization, and electrification efforts, cutting costs and speeding up results. Homeowners and renters benefit from simplified access to energy technologies, rebates, and incentives, making clean energy upgrades more accessible and affordable. The platform helps residents lower energy costs and reduce their environmental impact. For trade professionals and aggregators, Maiven boosts electrification and weatherization revenue, expands reach, and cuts labor costs, while aggregators benefit from increased capacity and streamlined operations. Maiven aims to unify digital solutions for complex energy programs and enable mass electrification by making clean energy adoption easy.

Picturetotext.info is a free online OCR (Optical Character Recognition) tool designed to extract text from various image formats, including photos, handwriting, screenshots, and scanned documents. Leveraging advanced AI and OCR technology, it converts images into editable and searchable digital text with speed and accuracy. The tool supports multiple image formats like JPG, PNG, JPEG, GIF, and TIFF, and offers multi-lingual support for over 20 languages. Users can upload, copy/paste, or drag and drop images for conversion, then copy or download the extracted text as a TXT file. It also features batch image processing, with limits for free and premium users, and ensures data security by not storing images or extracted text.

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.

testRigor is an AI-based test automation tool designed to simplify software testing by allowing users to build and maintain tests using plain English. It eliminates the need for complex coding, such as Selenium or Cucumber/Gherkin, by translating high-level instructions into specific steps. The platform supports comprehensive testing across web, mobile (iOS and Android), desktop, API, email, SMS, phone calls, 2FA, and mainframe applications. testRigor boasts ultra-stable tests not dependent on XPath, leading to significantly less maintenance compared to traditional methods. It integrates with popular tools like Gitlab, Github Actions, Jenkins, Jira, and Azure DevOps, and adheres to high security standards including ISO/IEC 27001:2022, SOC 2, HIPAA, and GDPR.

Stagehand is an AI browser automation framework designed to control web browsers using both natural language and code. It addresses the limitations of existing tools by offering a hybrid approach, allowing developers to choose between AI-driven navigation for unfamiliar pages and precise code for known actions. This flexibility makes web automation more maintainable and reliable. Key features include the ability to preview AI actions, cache repeatable actions to save time and tokens, and a self-healing mechanism that remembers previous actions and involves AI when website changes break an automation. Stagehand is open-source and provides an optimized, low-level interface to the browser built for automation.

Embedding Atlas is an open-source tool developed by Apple for interactive visualizations of large embeddings. It enables users to visualize, cross-filter, and search embeddings and associated metadata efficiently. Key features include automatic data clustering and labeling for interactive navigation of data structures, kernel density estimation and density contours to explore dense regions and outliers, and order-independent transparency for clear rendering of overlapping points. The tool also offers real-time search and nearest neighbors functionality to find similar data, and multi-coordinated views for metadata exploration. Built with WebGPU (with WebGL 2 fallback), it ensures fast performance for up to a few million points, making it suitable for data scientists and developers working with large datasets.

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.

SmarterDx is a clinical AI platform designed to empower hospitals by analyzing complete patient records to fully capture the value of care delivered. Powered by proprietary clinical AI, SmarterDx aligns every layer of a hospital’s financial ecosystem, from documentation to reimbursement, connecting care to payment. The platform offers solutions like SmarterNotes to embed clinical and revenue cycle intelligence into every note, SmarterCharges to validate charge accuracy and uncover missed revenue, SmarterPrebill to capture missing and incorrect diagnoses, and SmarterDenials to address complex denials with comprehensive appeal letters. Trusted by over 85 health systems, SmarterDx aims to help hospitals capture more revenue, automate denials, and build a more efficient, sustainable future of care.

Roobin, also known as Kèo Nhà Cái 38, is a comprehensive platform for sports betting enthusiasts, focusing primarily on football. It offers real-time updates on various betting odds, including Asian Handicap, Over/Under (Tài Xỉu), and European (1X2) odds. The platform aims to provide accurate and fast information, allowing users to monitor odds fluctuations before and during matches. Beyond the main betting types, Roobin also covers a wide range of secondary bets such as first/last goal scorer, correct score, corners, and odd/even totals. The tool emphasizes the importance of understanding odds movements, helping users identify market trends and avoid common betting pitfalls. It serves as a crucial resource for players looking to make strategic and informed betting choices.

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.

Baby Reachy-Mini Companion is a fully local AI companion designed for babies and kids, operating on the Reachy Mini platform. This innovative tool enables interactive communication with a robot that can listen and respond naturally. Beyond conversation, it offers features like storytelling and singing lullabies to entertain children. Additionally, it functions as a baby monitor, utilizing its camera to detect crying or potential hazards, and can send alerts to parents. The tool emphasizes a fully local operation, ensuring privacy and direct control over the AI companion.

Colorify is an AI tool designed to automate tasks and customize user interface elements, specifically focusing on the creation of color gradients for thumbnails. Built with Gradio, it offers users the ability to configure display titles and emojis, providing a degree of personalization for their visual content. While the live website currently indicates a runtime error, the tool's core functionality aims to streamline the process of generating visually appealing color schemes for various applications, particularly for thumbnail design. This makes it a potentially useful asset for content creators and designers looking for quick and easy ways to enhance their visual assets.

Chat Template Playground is a SvelteKit-based application designed for developers to easily experiment with and prototype chat user interfaces and templates. Users can paste any JSON data into the left pane of the interface. Upon clicking the run button, the application processes this JSON data and displays the resulting formatted text in the right pane. This output can then be conveniently copied to the clipboard, streamlining the process of testing and developing interactive components for chat interfaces. It serves as a simple yet effective way to visualize and refine chat UI elements, making it ideal for prototyping and developing modern chat applications.