AI Agents & Automation

Phronetic AI is a platform designed for building and deploying AI agents, particularly focusing on high-stakes environments like financial systems and national security. It emphasizes zero-trust architecture and air-gapped deployment for enhanced security. The platform offers specialized agents like ClipGen for video creation, Talkument for document interaction, and Codeshwar for AI development. Phronetic AI provides solutions tailored for the BFSI ecosystem, including banking, lending, financial services, insurance, and payments, with agents trained on domain-specific workflows and regulatory requirements. It also supports air-gapped environments for classified document processing and secure communications analysis, ensuring 100% offline operation.

Telewizard is a leading AI call center platform designed to fully automate customer interactions using advanced AI phone agents. It provides 24/7 automated support, ensuring businesses can handle customer inquiries around the clock without human intervention. The platform features email integration, allowing for a unified communication strategy, and advanced AI supervision to monitor and optimize agent performance. Telewizard focuses on delivering personalized interactions at an affordable cost, making it suitable for businesses of all sizes, from small enterprises to large corporations. It aims to enhance customer experience and operational efficiency by automating routine calls and providing consistent support.

Gemini Personal Intelligence offers personalized AI assistance by connecting with your Google apps such as Gmail, Photos, Search, and YouTube. This integration allows Gemini to analyze your context and chat history, providing more relevant and customized responses for tasks ranging from trip planning to project management. Users maintain control over which apps to connect and can manage their personalization settings at any time. The tool can research products, remember user interests for more helpful responses, recommend books based on reading history, and facilitate seamless conversations by considering past chats. It also helps discover new places by suggesting locations based on user preferences and past choices, making it ideal for planning personalized trips.

JobHire.AI is an AI-powered career assistant designed to streamline the job search process. It automates job applications, allowing users to apply to hundreds of jobs matching their criteria without manual effort. The platform includes an AI resume builder and cover letter generator to optimize applications, bypass ATS filters, and increase interview chances. Users can track their application activity through a built-in dashboard, saving significant time. JobHire.AI aims to make job searching more efficient and effective, offering features like resume matching and score checks to boost career growth.

Tensorforce is an open-source deep reinforcement learning framework built on TensorFlow, designed for both research and practical applications. It stands out for its modular, component-based design, allowing for highly configurable feature implementations. A key differentiator is the separation of the RL algorithm from the application, making algorithms agnostic to input and output structures. The entire reinforcement learning logic, including control flow, is implemented in TensorFlow, enabling portable computation graphs. It supports a wide range of features including various network layers, memory types, policy distributions, reward estimation, training objectives, and optimization algorithms. Tensorforce also offers extensive exploration techniques, preprocessing options, and regularization methods, making it a versatile tool for developing and training reinforcement learning agents.

TRFL (pronounced "truffle") is an open-source library developed by Google DeepMind, designed to simplify the implementation of Reinforcement Learning (RL) agents using TensorFlow. It offers a collection of essential building blocks and loss functions, such as Q-learning, that are crucial for developing and experimenting with various RL algorithms. The library integrates seamlessly with existing TensorFlow environments, allowing developers to leverage its powerful computational graph capabilities. TRFL does not list TensorFlow as a direct requirement, giving users flexibility to install specific CPU or GPU versions, along with TensorFlow Probability, separately. This modular approach makes it a valuable resource for researchers and practitioners in the field of AI and machine learning.

torchlayers is a PyTorch-based library designed to simplify the definition of neural network layers by providing automatic shape and dimensionality inference, similar to the Keras API. It eliminates the need for manual specification of input dimensions for many `torch.nn` modules, including convolutional, recurrent, transformer, attention, and linear layers. The library also includes additional building blocks found in state-of-the-art architectures, such as EfficientNet, PolyNet, Squeeze-And-Excitation, and StochasticDepth. Users can define custom modules with shape inference capabilities and benefit from useful defaults like "same" padding and automatic dropout rates. It supports zero overhead and torchscript, allowing seamless integration with existing PyTorch workflows.

tkDNN is a specialized Deep Neural Network library engineered for high-performance inference on NVIDIA Jetson Boards, including TK1, TX1, TX2, AGX Xavier, and Nano. Built upon cuDNN and TensorRT primitives, its core objective is to maximize inference speed on NVIDIA hardware. The library supports various deep learning tasks such as 2D/3D object detection, tracking, semantic segmentation, and monocular depth estimation. While it excels at inference, tkDNN does not support model training. It provides detailed FPS and mAP results for popular models like YOLOv3/v4 and MobileNetV2 SSD across different NVIDIA platforms, showcasing its optimization capabilities for embedded systems.

TinyChatEngine is an open-source library designed for efficient on-device inference of Large Language Models (LLMs) and Visual Language Models (VLMs). It allows users to run these advanced AI models directly on edge devices such as laptops, cars, and robots, ensuring instant responses and enhanced data privacy by keeping processing local. The engine leverages sophisticated LLM model compression techniques, including SmoothQuant and AWQ (Activation-aware Weight Quantization), to optimize performance for low-precision models. It boasts universal compatibility across x86, ARM, and CUDA platforms, featuring a from-scratch C/C++ implementation with no external library dependencies. TinyChatEngine is recognized for its high performance, achieving real-time inference on various devices, and is designed for ease of use, requiring only download, compilation, and deployment.

Loman AI offers a 24/7 AI phone answering solution specifically designed for restaurants. This voice AI agent can take pickup and delivery orders, manage reservations, answer frequently asked questions, and securely process credit card payments over the phone. It integrates seamlessly with popular POS and reservation systems like Toast, SpotOn, OpenTable, Clover, and Square. Loman AI aims to boost revenue by capturing missed calls, increase average ticket size through smart upsells, and reduce labor costs by offloading routine phone tasks from staff. The platform provides a command center to monitor live calls, transcripts, and orders, allowing restaurants to update menus and hours instantly.

AIGenerator.com offers a comprehensive suite of AI-powered tools designed for entrepreneurs and teams to plan, launch, and grow their businesses. It provides real-time knowledge of customers, competitors, and market trends to aid in smarter marketing decisions. Users can generate a full business plan, financial projections, marketing strategies, and over 100 types of content like ad copy, emails, and blog posts. The platform features an AI Business Consultant for guidance, content repurposing, and collaboration tools. It aims to streamline business planning and content creation, offering a structured approach tailored to unique business needs.

SeeAct is a system designed for generalist web agents, allowing them to autonomously execute tasks across various websites. It primarily utilizes large multimodal models (LMMs) such as GPT-4V(ision) to power its capabilities. The system features a robust code execution environment and a sophisticated grounding mechanism, ensuring effective and reliable interactions with web interfaces. SeeAct is particularly well-suited for researchers and developers who are focused on advancing the field of web automation and creating intelligent agents that can navigate and operate within complex online environments. Its focus on LMMs provides a cutting-edge approach to web agent development.

BingGPT is a desktop application designed to bring Microsoft's AI-powered Bing chat directly to your Windows, macOS, or Linux computer. This tool eliminates the need to install Microsoft Edge or rely on browser plugins, offering a standalone experience for interacting with the new Bing. Key features include the ability to export full conversations to Markdown, PNG, or PDF formats, and options to customize the application's appearance with different themes and font sizes. It also supports various keyboard shortcuts for efficient navigation and interaction, such as starting a new topic, switching tones, and quick replies. Users simply sign in with their Microsoft account to begin chatting, though a VPN might be required if Bing is not available in their region.

IntellibizzAI specializes in building intelligent identity systems for modern brands, leveraging AI precision with a human touch. The platform offers a comprehensive suite of services including brand positioning, premium website design, content intelligence, and visibility architecture. It caters to founders, creators, and boutique brands looking to enhance their online presence, convert visitors, and grow on social media. Key offerings range from identity system clarity and narrative development to high ROI visibility systems and AI visual narratives, all designed to deliver tangible results and sustained growth.

Vooyai is an AI-powered trip planner designed to help users discover new travel destinations and create personalized itineraries quickly. Users can provide their trip details to receive location recommendations or generate a bespoke itinerary if they already have a destination in mind. The platform aims to simplify trip planning, offering improved recommendation models that are accurate and tailored to individual needs. Vooyai Plus offers enhanced features such as up to 15 destination recommendations, itineraries for up to 15 days, and extra itinerary features like exporting, editing, and an improved map. Users can also earn free Vooyai Plus credits by inviting friends or booking accommodations, transportation, or activities through the platform.

MARLlib is a comprehensive, open-source library designed for Multi-agent Reinforcement Learning (MARL), leveraging Ray and its RLlib toolkit. It offers a unified platform for researchers and developers to create, train, and evaluate MARL algorithms across a wide array of tasks and environments. Key features include support for all task modes (cooperative, collaborative, competitive, mixed), a Gym-like interface for multi-agent environments, and flexible parameter-sharing strategies. MARLlib provides 18 pre-built algorithms with an intuitive API, making it accessible even for those new to MARL. Users can customize model architectures, policy sharing, and access over a thousand released experiments. It is compatible with Linux operating systems and offers step-by-step installation or Docker-based usage.

Lolo — AI Food&Calorie Tracker is an AI-powered solution designed to simplify the process of monitoring nutrition and managing calorie intake. Users can effortlessly log their food consumption through plain text or voice commands, making data entry quick and convenient. The tool leverages artificial intelligence to analyze dietary information, providing insights that help individuals maintain a balanced diet and achieve their health goals. It aims to streamline food tracking, making it accessible and efficient for anyone looking to better understand and control their nutritional habits.

MM-EUREKA is a cutting-edge project exploring the frontiers of multimodal reasoning through rule-based reinforcement learning. It introduces powerful models such as MM-Eureka-Qwen-7B and MM-Eureka-Qwen-32B, which significantly advance performance in multidisciplinary K12 and mathematical reasoning tasks. The project has iterated on model architecture, algorithms, and data, moving from InternVL to the more robust Qwen2.5-VL base models. Key improvements include enhanced online filtering, adaptive online rollout adjustment (ADORA), and novel RL algorithms like Clipped Policy Gradient Optimization with Policy Drift (CPGD). MM-EUREKA also open-sources a comprehensive pipeline, including self-collected MMK12 datasets, to foster further research and development in multimodal AI.

DeepGamingAI_FIFA is an open-source project that provides a deep learning-based AI bot specifically designed to play the football simulation game FIFA 18 on the Windows platform. This tool offers a unique opportunity for developers and AI enthusiasts to explore and experiment with artificial intelligence in a complex gaming environment. It demonstrates how deep learning techniques can be applied to automate gameplay, providing insights into building AI for simulations. The project includes various components for training and playing, making it a valuable resource for understanding AI in gaming.

ms-swift is a comprehensive, open-source framework developed by the ModelScope community, designed for fine-tuning and deploying large language models (LLMs) and multimodal large models (MLLMs). It supports over 600 text-only LLMs and 400 MLLMs, offering full-pipeline capabilities from training to inference, evaluation, quantization, and deployment. The framework integrates advanced training technologies, including Megatron parallelism (TP, PP, CP, EP) for acceleration and a rich family of GRPO reinforcement learning algorithms. ms-swift also supports various fine-tuning methods like LoRA, QLoRA, and DoRA, and provides memory optimization techniques such as Flash-Attention 2/3. It offers a Web-UI interface for simplified training, inference, evaluation, and quantization workflows, making it accessible for a wide range of users.

Game-Bot is an open-source project designed to teach artificial intelligence how to play video games by observing human interaction. The system works by recording a user's keyboard and mouse movements during gameplay, creating a dataset that is then used to train a deep learning model. Once trained, the AI can replicate the human player's actions and play the game autonomously. This tool provides a foundational framework for AI-driven game automation and research, leveraging deep learning techniques with neural networks. It is tested with Python 3.6.0 and requires specific module installations, making it suitable for developers and researchers interested in AI and gaming.

Ensemble-Pytorch is an open-source, unified ensemble framework designed for PyTorch to enhance the performance and robustness of deep learning models. It allows users to easily integrate various ensemble strategies, such as Voting, Bagging, Gradient Boosting, and Snapshot Ensemble, into their existing PyTorch workflows. The framework supports both classification and regression problems and provides a straightforward API for defining, optimizing, training, and evaluating ensembles. It is part of the PyTorch ecosystem, ensuring good maintenance and compatibility. With Ensemble-Pytorch, developers can leverage advanced ensemble techniques to achieve more reliable and accurate AI models.

inltk (Natural Language Toolkit for Indic Languages) is an open-source library designed to provide comprehensive support for various NLP tasks in Indic languages. It offers pre-trained language models and functionalities for data augmentation, textual similarity, sentence embeddings, word embeddings, tokenization, and text generation across 13 Indic languages. The library has demonstrated significant performance improvements, outperforming previously reported results for text classification on publicly available datasets. Furthermore, it enables achieving high performance with substantially reduced training data when utilizing its pre-trained models and data augmentation features. inltk is widely adopted, with over 40,000 downloads and a strong community presence on GitHub.

The Azure MLOps (v2) solution accelerator offers enterprise-ready templates designed to streamline the deployment of machine learning models on the Azure Platform. This project serves as a foundational starting point for MLOps implementation within Azure, emphasizing repeatable, automated, and collaborative workflows. It empowers teams of ML professionals to efficiently get their machine learning models into production. The accelerator focuses on simplicity, modularity, repeatability, security, collaboration, and enterprise readiness, utilizing a template-based approach to enhance operational efficiency across the data science lifecycle. It supports both Azure DevOps and GitHub-based deployments, providing architectural patterns and quickstart guides for various project scenarios.