AI Agents & Automation

MOTOR Ai develops Level 4 autonomous driving software grounded in cognitive neuroscience and fundamental German research. Their system is based on the highest international standards, ensuring the highest safety levels globally. The technology uses an independent cognitive AI approach with Active Inference, allowing autonomous vehicles to make deductive decisions and adapt to complex traffic situations without relying on pre-trained data. MOTOR Ai emphasizes safety, reliability, and explainability, utilizing a full sensor stack including LIDAR, radar, camera, microphone, GPS, and ultrasound, combined with sensor fusion for precise 3D scene understanding. The system also features a four-times redundant computer system and an additional Minimal Risk Maneuver (MRM) computer for vehicle operation, aiming to advance European, certifiable, and transparent autonomous mobility.

KoalaKonvo is a Telegram bot that functions as an AI assistant, leveraging OpenAI's advanced capabilities. It offers a range of features including the ability to build and execute JavaScript code snippets, browse the web to provide summaries and data, and generate images. Users can also fix grammar, manage multiple conversation threads, and select different AI models. The service operates on a pay-as-you-go model, requiring users to supply their own OpenAI API key, thus avoiding monthly subscription fees. It also allows for sharing conversations in a browser. KoalaKonvo is currently free to use during its beta phase, though usage costs are incurred through the user's OpenAI API key.

ShapeLLM-Omni is an open-source, native multimodal Large Language Model (LLM) specifically designed for advanced 3D generation and understanding. This tool, highlighted at NeurIPS 2025, enables users to perform complex 3D tasks such as text-to-3D generation, image-to-3D conversion, 3D captioning, and 3D editing. It offers pretrained weights for both ShapeLLM-Omni (7B) and 3DVQVAE, along with a dataset of 50k high-quality 3D edited data pairs. Researchers and developers can leverage its capabilities for various applications in 3D AI, with ongoing developments including the release of the full 3D-Alpaca dataset and training code.

MapLink Router is a privacy-focused Safari extension designed for iOS and iPadOS that enables users to open map links directly in their preferred navigation app. Users can choose between Apple Maps, Google Maps, or Waze. The tool operates entirely locally on the device, ensuring no tracking, analytics, or telemetry, prioritizing user safety and privacy. It's a one-time purchase with no subscriptions, offering a clear and honest scope for Safari-only use. The extension works by routing common link shapes for searches, coordinates, and directions, providing a consistent experience even with unusual or incomplete links. It explicitly states what is supported and what is not, such as other browsers or short links requiring expansion.

Dictalm2.0 Instruct Demo is a demonstration space for the Dicta-LM 3.0, a new Hebrew language model developed by DICTA: The Israel Center for Text Analysis. This AI chatbot allows users to experience the capabilities of the model firsthand. While the primary focus is on showcasing the model's performance in Hebrew, the demo provides a practical way to understand how such language models can be applied. It is available under the Apache 2.0 license, indicating its open-source nature and potential for community contributions or further development. The tool is designed for educational and demonstration purposes, offering a glimpse into advanced natural language processing for Hebrew.

Systown AI LAB is developing a Physical AI World Model platform, powered by Wittra 4D Fabric, designed to provide mission-critical insights for advanced robotics and autonomous systems. This innovative platform offers highly accurate GPS-denied positioning, achieving ±10cm precision, which is crucial for real-world embodied AGI. As an NVIDIA Inception Program partner, Systown AI LAB focuses on building the infrastructure for LLM-driven robotics, utilizing a Physical AI Neural System Feedback Loop where deployed models continuously feed real-world data back to a 4D Fabric Twin, sharpening accuracy over time. The platform supports simulating, training, evaluating, and deploying AI models in complex environments, even without 5G connectivity.

NOA Business Automation is an automation agency specializing in developing scaling and AI-integrated workflows for startups and SMEs. They leverage both low-code tools and classic coding to create tailored solutions. The agency offers custom tools to monitor operations and provides services on a project-based or subscription basis, functioning as an Automation as a Service (AaaS) provider. Their core focus is on enhancing productivity through custom web-based tools and advanced data optimization services, helping businesses automate tedious tasks, reduce costs, and gain data-driven insights for innovation.

The Hello Co. offers expert translation and interpreting services, enabling businesses and individuals to communicate effortlessly across more than 315 languages. Their solutions span interpreting (telephone, video, face-to-face, Auslan), translation & localization (content, design, multimedia, voiceovers, subtitling), and digital language support for websites and online platforms. They also provide automation APIs to streamline language services into workflows and advisory services based on over 40 years of industry experience. The Hello Co. focuses on delivering tailored solutions to meet diverse customer needs, ensuring clear and accurate communication while aiming to reduce operational costs for businesses.

Mode Maison is an independent research lab dedicated to exploring the intersection of physics-based simulation, artificial intelligence, material science, design, and retail. The company is actively developing multimodal Large World Models (LWMs) designed to simulate and generate diverse experiences. Their work aims to introduce a new dimension of intelligence, creativity, and reality, leveraging AI to push boundaries in these fields. While specific features are not detailed, the focus is on advanced AI research and development, suggesting a highly technical and innovative approach to complex problems in scientific computing and related domains.

Holo1.5 Localization is an AI tool developed by Hcompany, available as a Hugging Face Space, designed for high-resolution UI grounding. Users can upload an image of a user interface and then specify a particular UI element they wish to locate. The application will then process the image and predict the coordinates of the specified element, marking its position on the image. This functionality is part of the broader Holo1.5 initiative, which focuses on open foundation models for computer use agents. The tool is free to use and is licensed under Apache 2.0, making it accessible for various applications in UI analysis and automation.

Fulloop AI leverages artificial intelligence to transform the technical interview process, offering AI interviewers that can conduct multi-round assessments. The platform is designed to streamline the hiring workflow for technical roles, supporting various assessment types including coding challenges and system design questions. By providing structured feedback, Fulloop AI helps companies gain deeper insights into candidate performance, ultimately improving the efficiency of their hiring process. It aims to help identify top tech talent faster and more effectively. The tool offers both autopilot and co-pilot modes, providing flexibility in how interviews are managed and assessed.

LobeHub is an ultimate space for work and life, designed to facilitate the discovery, creation, and collaboration with AI agent teammates. It takes agent harnessing to the next level by enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction. The platform offers features like an Agent Builder for personalized AI teams, access to over 10,000 skills and MCP-compatible plugins, and Agent Groups for scalable collaboration. LobeHub also emphasizes co-evolution through Personal Memory and Continual Learning, allowing agents to adapt and grow with user workflows. Additional features include a desktop app, smart internet search, Chain of Thought visualization, branching conversations, and support for Claude Artifacts, file uploads, and multiple model service providers.

Lobe Vidol is an open-source platform designed to make virtual idol creation accessible to everyone. It boasts an exquisite UI and integrates support for MMD dance content, allowing users to bring their virtual idols to life with dynamic performances. The platform also enables seamless conversations with characters through text and video chat modes, offering an immersive interactive experience. Users can create custom virtual idols, set touch responses, and upload VRM models. Lobe Vidol supports a diverse range of multi-model providers, including AWS Bedrock, Google AI, Anthropic, and more, ensuring rich and varied conversation options. It also features a character and dance marketplace, TTS & STT voice conversations, and is available as a Progressive Web Application (PWA) for a seamless experience across devices.

MetaY is a groundbreaking Chrome extension that empowers users to contribute their unused GPU resources for AI deep learning inference tasks. By leveraging the excess capacity of your GPU, MetaY enables you to earn rewards while supporting cutting-edge AI research and development. The app is simple to set up and run, ensuring you make the most out of your GPU without compromising your own usage. It features optimized GPU utilization, a secure and transparent operation, and a user-friendly interface to monitor contributions and track earned points. MetaY is ideal for tech enthusiasts, AI researchers, gamers, and GPU owners looking to monetize their idle computing resources.

Volvice Technologies Pvt. Ltd. specializes in empowering businesses with next-generation technology, offering a comprehensive suite of IT solutions. Their services include custom software development, AI-led products and platforms, and advanced data intelligence solutions. They focus on transforming business challenges into growth opportunities by leveraging cutting-edge technologies like AI, machine learning, and cloud solutions. Volvice also provides cyber consulting services, education services, and a strong emphasis on cybersecurity with a dynamic security architecture. Their mission is to provide next-gen tech solutions that propel businesses forward, with a client-focused approach and deep commitment to data protection.

Comparia Leaderboard is a specialized AI Agents & Automation tool hosted on Hugging Face Spaces, designed to track and compare the performance of chatbots used within the French government's arena. This platform offers a transparent view of how different conversational AI agents are performing, which is crucial for evaluating their effectiveness and identifying areas for improvement. Licensed under Etalab 2.0, it serves as a public resource for monitoring and benchmarking chatbot solutions in a government context. While the live website currently shows a build error, its intended purpose is to provide a clear leaderboard for performance metrics.

Verbalyze Technologies provides comprehensive AI-powered solutions designed to automate and enhance customer interactions. The platform supports automated calling, email, chat, and WhatsApp, enabling businesses to manage a high volume of customer queries efficiently. By leveraging AI, Verbalyze aims to elevate customer engagement, reduce operational costs, and ensure consistent communication across multiple channels. This tool is ideal for businesses looking to implement intelligent automation for their customer support and communication strategies, allowing for conversations without boundaries.

Eko (Eko Keeps Operating) is a production-ready JavaScript framework designed for developers to create reliable AI agents and complex workflows using natural language. It offers a unified interface, allowing agents to operate seamlessly in both computer and browser environments. Key features include multi-agent capabilities, flexible agent and tool customization, dynamic LLM integration for balancing speed and performance, and human-in-the-loop intervention. Eko supports dynamic rendering with stream planning and automates repetitive tasks with loop and listener tasks. It is built for pure JavaScript, supporting Node.js and browsers, and offers access to private web resources, making it suitable for advanced automation and orchestration tasks.

Automated Continual Learning from New Data is an AI system designed to continuously learn from new data inputs, enabling the development of adaptive AI models. This tool facilitates real-time data analysis and dynamic model training, making it suitable for applications requiring continuous adaptation and improvement. Built using the AutoGen framework, it supports multi-agent AI applications, allowing for complex interactions and sophisticated learning processes. The system is particularly valuable for scenarios where AI models need to evolve with new information without manual retraining, ensuring up-to-date performance and relevance. Its foundation in AutoGen suggests capabilities for orchestrating multiple AI agents to achieve complex tasks.

ChatExt is a Chrome extension designed to significantly enhance the ChatGPT experience by enabling direct file uploads into the chat interface. This tool supports a wide array of file types, including .java, .json, .txt, .docx, and .csv, facilitating seamless file management and intelligent file chunking for smoother conversations. Users can upload up to 10 files at a time. Additionally, ChatExt provides custom download buttons, allowing users to easily save generated code and CSV files. The extension prioritizes user data privacy, ensuring that no user data is collected or saved, making it a secure option for integrating external documents into ChatGPT workflows.

The Falcon H1 Playground is a Hugging Face Space designed for interacting with Falcon-H1 AI models. Users can input messages and engage in conversations, with the flexibility to choose different model sizes. The platform also offers adjustable parameters such as creativity and response length, allowing for a tailored conversational experience. This playground serves as an experimental environment for exploring the capabilities and behaviors of the Falcon-H1 models, making it suitable for those interested in natural language processing and AI model interaction.

My Yogi is an AI-powered yoga platform designed to enhance the yoga experience through personalized sessions and real-time feedback. The tool assists users in selecting poses and creating customized yoga sequences, streamlining the planning process. It allows for detailed pose notes and offers print options for created sequences, making it a comprehensive solution for both individual practitioners and instructors. By leveraging AI, My Yogi aims to provide a tailored and interactive approach to yoga, supporting wellness and fitness goals.

Tuning_playbook is a comprehensive, open-source guide developed by Google Research's Brain Team, offering a systematic approach to maximizing the performance of deep learning models. It addresses the common challenges and guesswork involved in getting deep neural networks to work effectively in practice. The playbook provides detailed guidance on various aspects of deep learning, including choosing model architectures, optimizers, and batch sizes, as well as strategies for incremental tuning and experiment design. It also covers practical considerations like optimizing input pipelines, evaluating model performance, and setting up experiment tracking. The document is intended for engineers and researchers with basic knowledge of machine learning and deep learning concepts, focusing on supervised learning problems. It aims to be a living document, evolving with new research and community contributions to establish best practices in the field.

MADDPG offers a PyTorch implementation of the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, specifically tailored for multi-agent reinforcement learning in environments with both cooperative and competitive elements. This tool corresponds to the research paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments." It includes a quick start guide for running simulations, such as testing the algorithm on a 'simple_tag' scenario with pretrained models. The implementation allows for training agents, like predators catching prey, within the Multi-Agent Particle Environment (MPE). Users can also modify environment settings, such as switching between sparse and dense reward structures, to suit their experimental needs.