AI Agents & Automation

Agile Loop develops AI agents powered by its proprietary Action Model, designed to understand software interfaces and complete real tasks end-to-end. Their technology, built on Large Action Models, is trained on thousands of software interfaces to reliably execute workflows. Key products include Tera, which allows users to instantly turn ideas into mobile apps with no code and full customization, and SAM-X, an enterprise-grade solution for automating Excel tasks using plain English, featuring multi-sheet understanding and data cleaning capabilities. Agile Loop also offers SAM Desktop, an AI agent that controls your computer with natural language, running locally and performing cross-app automation. The platform focuses on intelligent analysis of screen content, workflow planning, and continuous optimization to ensure effective task completion within real software.

GobbleCube is an AI-powered growth agent specifically designed for brands aiming for market dominance. It helps businesses scale revenue by intelligently identifying areas of inefficiency, spotting market opportunities, and automating various growth initiatives across their digital commerce operations. The tool leverages AI to transform raw data into actionable insights, providing analysis and visualization to support strategic decision-making. GobbleCube is built to assist brands in optimizing their digital presence and maximizing their revenue potential through automated and data-driven strategies.

ML Agents Walker is a Unity game environment designed to showcase the capabilities of machine learning-driven agents. Within this interactive space, AI agents autonomously navigate and interact with pyramid structures. The tool requires no direct input from the user; instead, it offers a passive observation experience where users can watch the agents' behavior and interactions unfold. This platform serves as an accessible demonstration of AI agents operating within a simulated environment, highlighting their ability to perceive, decide, and act. It's hosted on Hugging Face Spaces, making it easily accessible for anyone interested in observing AI in action.

SLAM-LLM is a comprehensive deep learning toolkit designed for researchers and developers to train custom multimodal large language models (MLLMs). It specializes in processing speech, language, audio, and music, offering detailed recipes for training and high-performance checkpoints for inference. The framework supports multi-task training, dynamic prompt selection, and iterative datasets for large-scale industrial applications, including datasets on the order of 100,000 hours. Key features include DeepSpeed training for reduced memory usage, multi-machine multi-GPU inference, and dynamic frame batching to significantly reduce training and evaluation times. It also provides flexible configuration options based on Hydra and dataclass, allowing for a combination of code, command-line, and file-based configurations.

snake-ai is an open-source project featuring an AI agent designed to master the classic game "Snake." The agent is trained using deep reinforcement learning, offering two distinct versions: one based on a Multi-Layer Perceptron (MLP) and another utilizing a Convolutional Neural Network (CNN). The CNN-based agent demonstrates superior performance, consistently achieving higher average game scores. The project provides program scripts for the game itself, along with trained models for both AI versions, allowing users to test and observe their performance. It also includes scripts for retraining models and viewing training process curves via Tensorboard, making it a valuable resource for those interested in practical applications of deep reinforcement learning in gaming.

Cortica is a pioneer in Autonomous AI, having invested over $250M and secured 300+ patents over 15 years to develop its groundbreaking technology. Its revolutionary AI mirrors how the human cortex processes information, utilizing signatures for generic representations, adaptive architecture for scenario-focused adaptivity, and self-learning neural networks independent of manually labeled data. This technology enables efficient data processing, superior performance, and scalability on low-compute platforms. Cortica partners with global market leaders to build AI companies like Qualisense (quality inspection), Autobrains (autonomous vehicles), Corsight (facial recognition), SeeTrue (threat detection), CORDiguide (cardiovascular procedures), and Corsound (voice biometrics), providing them with a technological and business advantage in large market opportunities.

ChatGemini.net offers a free AI chatbot experience powered by the Google Gemini Pro API. Users can engage in dynamic conversations and explore the capabilities of AI without any cost. The platform emphasizes ease of use, providing a seamless experience for interacting with advanced AI models. It is designed to be accessible, allowing anyone to chat with Google's Gemini AI directly through the website. The tool aims to make AI interaction straightforward and enjoyable for a broad audience.

Docketry.ai offers an Agentic AI Platform designed for modern enterprises to transform documents into decisions, enabling faster, safer, and smarter operations. The platform provides pre-built agentic teams for various functions like FinOps, ITOps, HROps, Fraud Management, and Policy Acceptance, which can be deployed within weeks. Key products include ExtractIQ for document intelligence, NeuroDesk for cognitive intelligence, OpsIQ for operations intelligence, and CASIE for conversational intelligence. Docketry.ai aims to deliver significant efficiency gains (up to 20X), cost savings (up to 75%), and accuracy (up to 95%), helping businesses achieve AI maturity across different stages from efficiency to autonomy. It caters to industries such as insurance, financial services, banking, and supply chain.

H Company builds AI models, agents, and products designed to automate tasks and simplify complex workflows for both individuals and enterprises. Their flagship product, HoloTab, is a Chrome extension that deploys an AI agent directly in your browser. HoloTab can navigate websites, fill out forms, and complete tasks on your behalf, and users can create "Routines" to automate repetitive actions. Additionally, H Company offers the Holo Models API, providing access to their multimodal models like Holo3, which is designed to interpret content and operate across digital workflows. For enterprises, they provide a full-stack platform for deploying AI systems that combine models, advanced agents, scalable execution, and continuous learning to bring "action-oriented AI" into production.

ChatGPT Robotics is a Hugging Face Space by Microsoft, showcasing the application of ChatGPT in robotics. This tool allows users to interact with ChatGPT through prompts and high-level APIs specifically designed for robotics scenarios. It serves as a demonstration of how large language models like ChatGPT can be leveraged to control and automate various robotic tasks, providing a practical example for researchers and developers interested in AI-driven robotics. The platform aims to accompany research efforts in this domain, offering a tangible interface to explore the capabilities of ChatGPT in a robotics context.

CUA - Computer Use Agent 2.0 is an AI-powered application available as a Hugging Face Space that specializes in image captioning. Users can upload images to the platform, and the tool will automatically generate detailed, descriptive captions based on the visual content of the photo. This functionality is particularly useful for tasks requiring automated image analysis and textual representation, such as content creation, accessibility enhancements, or data annotation. The tool focuses on providing clear and comprehensive descriptions, making it a valuable asset for anyone needing to quickly understand or categorize visual information.

Awesome Machine Learning On Source Code (MLonCode) is a curated list of research papers, datasets, and software projects focused on the application of machine learning to source code. This repository provides a valuable resource for researchers and practitioners interested in topics such as program synthesis, source code analysis, neural network architectures, and embeddings in software engineering. While the repository is no longer actively maintained, it offers an extensive collection of historical and foundational works in the MLonCode domain, including digests, conference proceedings, competitions, and talks. It covers various sub-fields like program translation, code suggestion, bug detection, and code optimization.

Bigdatamatica Solutions Pvt Ltd is an AI solutions provider focused on delivering enterprise-grade applications. The company specializes in advanced areas such as agentic AI, quantum intelligence, and real-time decision systems. Their solutions are designed to help businesses unlock valuable insights from their data, eliminate operational inefficiencies, and accelerate innovation across various sectors. Bigdatamatica aims to provide comprehensive data-to-deployment intelligence platforms, catering to industries like retail and mobility, enabling them to leverage cutting-edge AI and automation technologies for strategic advantage.

MediScoper is an AI-assisted platform designed for healthcare professionals to streamline doctor-patient interactions. It offers accurate audio transcription, automated analysis reports aligned with SOAP standards, and real-time diagnostic proposals powered by cutting-edge AI. The platform supports translations in over 60 languages, bridging communication gaps. MediScoper prioritizes data security with anonymous processing, state-of-the-art encryption, and GDPR compliance, ensuring patient confidentiality. It aims to reduce administrative burdens, allowing healthcare providers to focus more on patient care. The tool also integrates seamlessly into existing systems by outputting standard documentation for EHRs, enhancing workflow efficiency.

Agent File (.af) is an open standard file format designed for serializing stateful AI agents. Originally developed for the Letta framework, it provides a portable method for sharing agents that retain their persistent memory and behavior. This format packages all essential components of a stateful agent, including system prompts, editable memory (personality and user information), tool configurations (code and schemas), and LLM settings. By standardizing these elements, Agent File facilitates seamless transfer between compatible frameworks, enabling easy checkpointing and version control of agent states. It addresses the need for a common standard in the rapidly growing AI agent development ecosystem, promoting portability, collaboration, preservation, and versioning of AI agents.

deepseek_ocr_app is a modern OCR web application powered by DeepSeek-OCR, featuring a React frontend and FastAPI backend. It provides robust capabilities for both image and PDF processing, allowing users to extract text, describe images, find specific terms, and use custom prompts. The application supports multi-format document conversion, enabling export to Markdown, HTML, DOCX, and JSON. Key features include automatic image extraction from PDFs, preservation of formulas and formatting, and real-time progress tracking for multi-page documents. It is designed for various use cases such as document digitization, data extraction, and content migration, offering a comprehensive solution for handling diverse document types.

OpenOutreach is a self-hosted, open-source LinkedIn automation tool designed for B2B lead generation. Unlike traditional methods requiring pre-existing contact lists, users simply describe their product and define their target market. The AI then autonomously discovers, qualifies, and contacts suitable leads. It employs a Bayesian ML model to learn ideal customer profiles and an LLM to classify leads, becoming smarter with every interaction. Key features include autonomous lead discovery, undetectable browser automation mimicking real user behavior, full data ownership via a built-in CRM, and AI-powered personalized messaging with multi-turn follow-up conversations. It offers both a free self-hosted option and a managed cloud service for zero-ops convenience.

OpenMusic is an open-source project offering a state-of-the-art text-to-music (TTM) generation system. It provides a PyTorch implementation of the QA-MDT model, integrating advanced techniques from AudioLDM, PixArt-alpha, MDT, AudioMAE, and Open-Sora. Users can generate music from text prompts, with the capability for zero-shot, infinitely long music generation. The repository includes instructions for local setup using Gradio, training, and inference. It also details how to prepare datasets in LMDB format for fine-tuning, offering various training strategies with or without quality tokens. OpenMusic is ideal for researchers and developers interested in cutting-edge music AI.

Awesome-GPT-Store is an open-source GitHub repository offering a curated collection of high-quality prompts and output examples specifically designed for GPT-Image-2 via the OpenAI API. It serves as a comprehensive reference for prompt engineering, covering diverse applications such as photorealistic portraits, artistic posters, UI mockups, character sheets, and game screenshots. The repository highlights GPT-Image-2's advanced capabilities, including stronger world knowledge, improved style fidelity, better prompt adherence, photorealistic output, and enhanced typography rendering. Users can find ready-to-use prompts to unlock the full potential of GPT-Image-2 for building image generation apps or experimenting with the API.

TriloDocs, part of Genactis Group, offers AI-enhanced medical writing solutions specifically designed for medical writing professionals. Developed through collaboration between medical writers and AI engineering specialists, the platform aims to significantly reduce the time spent on creating regulatory medical documentation. It handles the heavy lifting of error-free data processing, allowing medical writers to focus on clinical interpretation and strategic messaging. TriloDocs processes source data in hours instead of weeks, adapting to study requirements and highlighting clinically relevant findings. The tool also provides user-instructed and AI-powered creation of regulatory-ready initial drafts, incorporating compliance requirements and quality standards from the first version. It is trusted by global pharmaceuticals, biotechs, and CROs for its deep regulatory understanding and real medical writing workflow integration.

Beijing IDRIVERPLUS Technology Co., Ltd. is a leading developer of autonomous vehicle technology, specializing in unpiloted systems. The company's core offering is a 'Physical AI Brain' that serves as a super-base for mobile intelligent bodies. Their solutions are applied across three main domains: public safety, where mobile intelligent platforms are designed for extreme environments like fire rescue and emergency defense; life services, focusing on automating heavy and repetitive labor to improve efficiency; and intelligent mobility, transforming transportation into a more pleasant experience. IDRIVERPLUS aims to create a future where humans and AI collaborate, making the world safer, more efficient, and better through autonomous movement capabilities.

Ception, operating as DriveU.auto, provides an autonomous terminal tractor retrofit kit specifically designed for brownfield container ports. This solution enables terminal operators to convert their existing fleets into autonomous vehicles, ensuring efficient, flexible, and safe container transport without disrupting current infrastructure. Key benefits include boosting port productivity through 24/7 continuous operation, removing horizontal transport bottlenecks, and increasing daily move capacity. The system supports continuous operation in mixed traffic with remote human oversight, ensuring undisrupted port activities. It offers a fast ROI, minimizing upfront replacement costs and allowing quick deployment and scalability for a return on investment in under two years. DriveU.auto also offers additional products like a superior connectivity platform for autonomous vehicle remote operation and teleassist, and teleoperation solutions for defense applications.

Vocode offers an open-source voice AI platform designed for building, deploying, and scaling hyperrealistic voice agents. Its core component, Vocode Core, provides the necessary integrations, orchestration, and abstractions to develop voice applications on top of various AI stacks. Additionally, the Vocode API offers an enterprise-grade solution for managing AI agents on phone calls, built upon Vocode Core. The platform includes Python and Node SDKs to facilitate development, making it a versatile tool for creating advanced voice-based LLM agents. It emphasizes modularity and open-source principles, allowing developers to customize and extend its capabilities.

Motional is a joint venture between Hyundai Motor Group and Aptiv, dedicated to revolutionizing driverless technology. The company develops and deploys safe, reliable, and accessible autonomous vehicles for integration into mobility networks. Motional's technology is designed for autonomous ride-hail and delivery services, focusing on creating an enjoyable experience for passengers. Their vehicles are engineered to be expert drivers, prioritizing safety by eliminating human factors like drowsiness or distraction. Motional has a strong commitment to safety and industry-leading partnerships, with robotaxis already available on the Uber App in Las Vegas.