AI Agents & Automation

DR Tulu is an open-source Deep Research (DR) model designed for tackling long-form research tasks. The DR Tulu-8B model has demonstrated performance comparable to OpenAI DR on long-form DR benchmarks. This repository provides the official code for DR Tulu, including an agent library with a MCP-based tool backend, high-concurrency async request management, and a flexible prompting interface for developing and training deep research agents. It also includes RL training code based on Open-Instruct and SFT training code based on LLaMA-Factory, allowing for supervised fine-tuning and reinforcement learning with GRPO and evolving rubrics. An interactive CLI demo is available for users to experiment with DR Tulu-8B.

Float16 is a comprehensive GPU management platform designed for deploying, managing, and scaling AI models. It offers a full spectrum of services including AI-as-a-Service (AaaS) for instant access to ready-to-use AI models without coding, Platform-as-a-Service (PaaS) for flexible resource allocation, and Infrastructure-as-a-Service (IaaS) for bare-metal GPU instances. The platform emphasizes ease of use with one-click deployment, significantly reducing setup time from weeks to minutes. Float16 provides dedicated and isolated GPU resources, ensuring zero interference and optimal performance for workloads. It features a credit-based quota system for flexible GPU utilization, eliminating waste from fixed time slots. Supported by NVIDIA Inception Program, Float16 is ideal for ML engineers, data scientists, software developers, and researchers seeking efficient and scalable GPU solutions.

MindLumen offers AI therapy through an AI companion designed to improve mental wellbeing, boost confidence, and provide support for mental health. It utilizes therapeutic techniques to guide users toward self-reflection, relaxation, and emotional balance, offering tools, exercises, and gentle reminders. The platform provides immediate accessibility, affordability, and a non-judgmental environment, making it beneficial for individuals managing daily stress, practicing self-care, or seeking initial steps toward improved mental wellbeing. MindLumen is intended for adult users and complements traditional therapy by helping practice coping skills and mindfulness techniques between sessions, though it is not a replacement for professional one-on-one support for serious mental health issues. The tool prioritizes user privacy and data security.

Halleluyah Healthcare leverages AI, powered by JadaAI, to offer comprehensive healthcare information, integrating traditional remedies with modern health suggestions. The platform functions as a digital health companion, providing holistic guidance and facilitating connections to essential healthcare services. It is specifically designed to extend valuable health resources to underserved populations, promoting better living through accessible and intelligent health insights. The tool focuses on empowering individuals with knowledge to manage their health proactively, combining technological innovation with the wisdom of holistic traditions for a well-rounded approach to wellness.

Ashdeck is a Chrome extension designed to enhance productivity by transforming your New Tab Page into a focused workspace. It integrates a Focus Timer, often based on the Pomodoro technique, to help users manage their work intervals and breaks effectively. Additionally, Ashdeck features a Site Blocker, allowing users to restrict access to distracting websites during their focus sessions, thereby minimizing interruptions and improving concentration. The tool also includes a todo list manager, enabling users to organize their tasks directly from their new tab. By combining these features, Ashdeck aims to help users maintain focus, manage their time, and boost overall productivity.

Neuropod is a library designed to offer a uniform interface for running deep learning models across various frameworks, including TensorFlow, PyTorch, TorchScript, Keras, and Ludwig. It aims to simplify the productionization of deep learning models, enabling researchers and developers to build models in their framework of choice without being constrained by deployment complexities. A key benefit is framework-agnostic inference code, allowing easy switching between deep learning frameworks without altering runtime code. Neuropod also supports defining a problem API, which helps in building generic tools, pipelines, and comparing models solving the same problem, even if they originate from different frameworks. It supports both C++ and Python, offers efficient zero-copy operations, and ensures model isolation with out-of-process execution.

EasyML is a general-purpose dataflow-based system designed to ease the process of applying machine learning algorithms to real-world tasks, especially on distributed platforms such as Hadoop and Spark. It formulates learning tasks as directed acyclic graphs (DAGs), where each node represents an operation or algorithm. The system includes a distributed machine learning library with algorithms for pre/post-processing, data transformation, feature generation, and performance evaluation, primarily based on Spark. A GUI-based studio allows users to create, configure, submit, monitor, and share machine learning processes using a drag-and-drop interface. EasyML also offers a cloud service for executing tasks, scheduling nodes automatically on Linux, Spark, or Map-Reduce based on their implementation. Users can upload their own algorithm packages and datasets.

drl_grasping is an open-source project focused on advancing robotic manipulation through deep reinforcement learning. It enables robots to acquire robust grasping policies for diverse objects using compact 3D observations in the form of octrees. The project emphasizes sim-to-real transfer, allowing policies trained in simulation to be evaluated on real robots with zero-shot transfer. It includes multiple RL environments for robotic manipulation, supporting continuous actions in Cartesian space and various observation variants like RGB images, depth maps, and octrees. The framework is compatible with Gym API and has been tested with end-to-end model-free actor-critic algorithms like TD3, SAC, and TQC, with a setup for model-based algorithms also provided.

PDF Extractor API provides a reliable solution for developers to convert HTML strings, including CSS and JavaScript, into PDF documents with a single API request. It eliminates the complexities of managing headless browsers, offering consistent output powered by Chrome's rendering engine. The API is designed for production workloads, ensuring fast and scalable PDF generation. Developers can integrate it using any HTTP client, sending JSON input and receiving PDF output. It supports template engines like Handlebars/Mustache for separating data from design, and offers secure API key authentication. The service is built to handle thousands of PDFs per minute, scaling automatically to meet demand.

TextsBert™ is a powerful productivity tool designed to streamline repetitive browser form filling and document processing. It intelligently fills web forms using copied text and pre-saved business details, significantly reducing manual retyping. A key differentiator is its local-only data processing, ensuring privacy by keeping sensitive information on your device rather than sending it to cloud AI services. Users can review every fill before submission, maintaining control over the final output. The tool offers 'Normal Auto Fill' for stable, reusable details and 'Magical Fill' for dynamic, messy copied text. It also includes PDF Fill capabilities for fillable PDFs and offers optional end-to-end encrypted Sync for continuity across devices.

NeuroBlock is an AI laboratory dedicated to enhancing AI models through the use of high-quality datasets. The platform provides comprehensive enterprise AI consulting services, assisting businesses in integrating and optimizing AI solutions. A key offering includes local and private AI integrations, ensuring data privacy and tailored performance for specific organizational needs. Additionally, NeuroBlock features an OpenData platform, designed to facilitate AI model training by providing access to diverse and curated datasets. The company also develops lead generation tools, leveraging AI to identify and engage potential customers. NeuroBlock aims to deliver AI solutions that are efficient, secure, and customized to client requirements.

FoodAI is an AI-powered application designed to revolutionize meal planning by generating recipes based on ingredients users already have. This innovative tool helps reduce food waste by suggesting creative uses for items in your pantry or fridge. Users can select their available ingredients, and the AI will provide a range of recipe options, catering to diverse tastes and dietary requirements. Whether you're vegetarian, vegan, or celiac, FoodAI can adapt to your needs. It also allows users to filter out disliked ingredients and choose from different cuisines, making meal preparation both personalized and efficient. FoodAI aims to simplify cooking, inspire new culinary ideas, and promote sustainable eating habits.

facexlib is an open-source library designed to provide ready-to-use face-related functions, leveraging current state-of-the-art open-source methods. It primarily offers PyTorch reference codes for various face processing tasks, including detection, alignment, recognition, parsing, matting, headpose estimation, and tracking. While it provides a collection of these algorithms, users are directed to the original repositories for training or fine-tuning. The library simplifies the integration of advanced face processing techniques into existing projects, making it a valuable resource for developers and researchers working with facial data. It is released under the MIT license, with individual components referencing their original licenses.

Fedlearner is a multi-party collaborative machine learning framework designed to enable joint modeling of data distributed across various institutions. This open-source tool, developed by Bytedance, focuses on secure data sharing and analysis for machine learning applications. It supports collaborative AI development without centralizing sensitive data, making it suitable for scenarios requiring privacy preservation and data governance. The framework is built with Python, TypeScript, and Go, indicating a robust and versatile technical foundation for developers looking to implement federated learning solutions.

AI Product Engineer (AIPE) is an interactive learning platform designed to master AI product development. Through engaging quests and hands-on experience, users can learn to build agentic AI systems and production-ready AI software. The platform emphasizes a code-first approach, providing tutorials and a community for aspiring AI product engineers. Users earn XP and level up their skills with Quackster the DuckTyper, making the learning process gamified and engaging. AIPE also hosts live events, such as discussions on the AI Cluster and its role in agentic AI, offering insights into industry-relevant tools and frameworks like Apify's AI Cluster.

Artifact Hospitality provides full-service luxury property management in Dubai, focusing on maximizing ROI for property owners in high-demand areas such as Palm Jumeirah, Dubai Marina, and Business Bay. The platform fully automates property operations, including data and reporting, smart lock integration, and an AI concierge service. It also offers comprehensive guest support and cleaning services, ensuring a seamless experience for both owners and guests. As a member of the Dubai AI Campus Network, Artifact Hospitality leverages advanced AI to optimize occupancy and nightly rates through data-driven pricing and multi-channel distribution, aiming for significant annual growth in revenue and improved guest satisfaction.

GaussianEditor is an open-source AI tool presented at CVPR 2024, designed for swift and controllable 3D editing leveraging Gaussian Splatting technology. It provides capabilities for adding, deleting, and modifying objects within 3D scenes, with editing operations completing in just 2-7 minutes. The tool offers both a WebUI, powered by Viser, and a command-line interface for flexible use. It supports various editing functionalities, including generating edited 2D images as guidance using InstructPix2Pix for modifications, and employing ControlNet-Inpainting for adding new elements. GaussianEditor is built upon a foundation of other advanced repositories like Wonder3D and Threestudio, making it a powerful solution for 3D content creation and manipulation.

Perplexity AI is a Python module designed as an unofficial API wrapper for Perplexity.ai, offering enhanced functionality and flexibility. A key feature is its ability to leverage Emailnator for automatic generation of new accounts, effectively bypassing query limits and providing unlimited pro queries. The module supports both synchronous and asynchronous APIs, catering to different programming needs. For users who prefer a graphical interface, it also includes a web interface that automates account creation and usage. This tool is particularly useful for developers and data scientists looking to integrate Perplexity.ai's capabilities into their applications or workflows without the constraints of official API keys, offering robust error handling, comprehensive logging, and streaming responses.

Bunch is an AI-powered leadership coaching application designed to help managers and leaders enhance their skills in just two minutes a day. It provides personalized daily leadership guidance, AI-powered coaching, and insights to improve communication, run better meetings, and grow high-performing teams. Users can discover their leadership style, join peer learning groups for accountability, and access expert-curated sprints on specific skills. The platform also features Bunchee, an AI coach available 24/7 to answer leadership questions and offer advice. Bunch aims to make leadership development simple, practical, and accessible for first-time managers, scaling startup leaders, and HR departments.

PiML-Toolbox (Python Interpretable Machine Learning) is a comprehensive Python toolbox designed for the development and diagnostics of interpretable machine learning models. It offers both low-code interfaces and high-code APIs, supporting a growing list of inherently interpretable ML models such as GLM, GAM, Tree, FIGS, XGB1, XGB2, EBM, GAMI-Net, and ReLU-DNN. The toolbox facilitates various outcome testing, including accuracy, explainability (PFI, PDP, ALE, LIME, SHAP), fairness, weak spot identification, overfitting detection, reliability assessment, robustness, and resilience evaluation. PiML-Toolbox aims to empower model developers and validators with tools for transparent, interpretable, and robust machine learning, particularly in high-stakes regulatory settings.

AppointEze is a cloud-based appointment scheduling software designed to streamline booking processes for businesses of all sizes. It enables users to create online appointment schedulers, manage client appointments, staff availability, and calendars efficiently. The platform offers features like real-time availability display, automated scheduling, and reminders to reduce administrative overhead. AppointEze is particularly beneficial for service-based industries, allowing them to attract new clients and grow their business by simplifying the booking experience. It integrates with existing software tools and provides options for co-hosting calls with colleagues, ensuring a cohesive team scheduling environment. The system also supports screening clients before booking and reconfirming meetings, enhancing operational control.

CS TECH Ai delivers high-impact technology solutions across Geospatial, AI, and Digital Transformation domains. The company specializes in providing services such as GIS, remote sensing, and digital twin services for infrastructure, water, energy, and natural resource management. Additionally, CS TECH Ai offers product and manufacturing engineering solutions for the mobility sector, covering design, validation, industrial automation, and electrification. Their AI-enabled platforms facilitate intelligent decision-making through IoT integration, automation, and 3D reality capture, supporting scalable enterprise operations across diverse sectors. With 27 years of experience, CS TECH Ai focuses on sustainability and integrates global technologies to meet customer needs effectively.

DeGould is a global leader in providing automated vehicle inspection solutions for automotive OEMs. The system utilizes AI algorithms and high-quality images to perform digital vehicle inspections, damage detection, and specification checks. DeGould's AutoCompact system, installed at end-of-line, delivers inspection results in less than 120 seconds, covering areas manual inspection often misses. It is trained on millions of real-world images to ensure consistent defect detection and classification. The Spec Check feature automatically assesses panels for surface condition and confirms component matches against VIN data. The Inspector App allows quality teams to review and approve findings directly at the vehicle, while the DeGould Dashboard provides a centralized digital record and network visibility across multiple plants. The DVM App further extends this documentation through the supply chain, helping to resolve damage disputes by recording vehicle condition at each handover point.

GPS-Gaussian is an innovative AI tool that offers a generalizable pixel-wise 3D Gaussian representation for real-time human novel view synthesis. Developed as a highlight of CVPR 2024, this tool allows for instant generation of novel views of unseen characters without requiring any fine-tuning or optimization. It provides a robust solution for computer vision and graphics researchers and developers working with 3D human models. The repository includes detailed instructions for installation, dataset preparation, and training, supporting both synthetic and real-world data. Users can pretrain a depth prediction model and then train the full model, with options for offline disparity determination to speed up subsequent training. Pretrained models are also available for quick evaluation and testing.