AI Agents & Automation

Ghostwriter, powered by Replit AI, is an advanced coding assistant designed to transform natural language prompts into fully functional applications and websites. It aims to automate the repetitive aspects of coding, enabling users to concentrate on innovation. The tool acts like an on-demand team of software engineers, capable of building a wide range of software from business apps and AI chatbots to games and online shops, all through a simple chat interface. Ghostwriter can quickly generate working prototypes, fix bugs, and even build apps from screenshots, making it accessible for both technical and non-technical creators. It offers a comprehensive environment for building, deploying, and sharing software without the need for extensive coding knowledge.

AI Chat: Talk with character, also known as Talky AI, is an iOS mobile application designed to empower users with the ability to create and engage with highly customized AI companions. The app offers extensive character creation tools, allowing for limitless design possibilities and deep personalization. Users can craft unique AI personalities that reflect their creativity, serving as distinctive conversational partners. This platform redefines AI connection by focusing on personalized interaction, providing an engaging and tailored experience for anyone looking to interact with bespoke AI characters.

AI Personal Trainer is a comprehensive fitness application that leverages artificial intelligence to generate highly personalized workout programs and nutrition plans. Unlike generic templates, this tool crafts smart training routines tailored to individual goals, current fitness levels, and schedules. Key features include AI-generated workout programs spanning 4–24 weeks, personalized nutrition and meal planning with smart calorie and macro targets, and AI-powered body fat percentage analysis. The app also offers progress tracking with weekly insights and adaptive plans that evolve as users improve, ensuring continuous and effective fitness journeys. It is built specifically for Android users, allowing for training at home or in the gym.

Zapia AI is a personal AI assistant designed for WhatsApp users, particularly in Latin America, to streamline daily tasks and save money. It offers features like AI shopping assistance to compare prices, routine organization, and WhatsApp message management. Users can interact with Zapia through voice notes to manage schedules, book meetings, reply to messages, and resolve tasks. The tool emphasizes user control, executing actions only with authorization. Zapia Max provides advanced capabilities such as price tracking, stock checks, and Gmail organization, aiming to automate various manual tasks.

Kornia is a differentiable computer vision library built on PyTorch, designed for spatial AI applications. It offers a comprehensive suite of differentiable image processing and geometric vision algorithms, allowing users to leverage powerful batch transformations, auto-differentiation, and GPU acceleration. Key features include a wide range of image processing operators like filters, transformations, and enhancements, as well as advanced augmentation pipelines for training AI models. Kornia also provides access to pre-trained AI models for tasks such as face detection, feature matching, segmentation, and classification. The library is expanding its focus towards end-to-end vision models, with a particular emphasis on integrating state-of-the-art Vision Language Models (VLM) and Vision Language Agents (VLA). It supports multi-framework usage, including TensorFlow, JAX, and NumPy, making it a versatile tool for developers and researchers in the AI and computer vision fields.

Simposcan Scanner App PDF OCR is a mobile application designed to turn your smartphone into a powerful scanning device. It enables users to easily scan and organize various types of documents, including receipts and pictures, directly from their mobile device. The app supports conversion of scanned items into multiple formats such as PDF, JPG, CSV, and FAX, offering flexibility for different needs. Users can also conveniently share their digitized files through popular messaging applications or other sharing methods. This tool aims to simplify document management and sharing for individuals and small businesses.

Bender is an open-source abstraction layer built over MetalPerformanceShaders, designed to simplify the development and execution of neural networks on iOS devices. It addresses the growing need to run AI models directly on mobile devices, even if the training was done elsewhere. Bender provides an intuitive way to define and run neural networks using common layers like Convolution, Pooling, and FullyConnected. A key feature is its ability to load models trained in other frameworks, such as TensorFlow, by translating them into Bender layers. This eliminates the need to include TensorFlow's static library or rely solely on CPU execution, enabling GPU-accelerated inference on iOS. It aims to make on-device AI more accessible and performant for developers.

kokoro-tts is an open-source command-line interface (CLI) text-to-speech tool built on the Kokoro model, designed to convert text into natural-sounding speech. It offers extensive language and voice support, including the ability to blend multiple voices with customizable weights for unique audio outputs. The tool can process various input formats such as TXT, EPUB books, and PDF documents, automatically extracting chapters for organized output. Users can stream audio directly, adjust speech speed, and save output in WAV or MP3 formats. It also supports GPU acceleration for faster processing and provides detailed debug output for troubleshooting, making it a versatile solution for generating audio content from diverse text sources.

KyleGPT is an iOS mobile application designed for secure and private direct messaging with a simulated AI companion named Kyle. The app emphasizes a personal and private communication channel, offering end-to-end encrypted conversations within a sleek, modern chat interface. It aims to provide a futuristic chat environment where users can interact exclusively with this specific AI. The tool focuses on delivering a unique one-on-one AI interaction experience, distinguishing itself through its dedicated AI companion and commitment to user privacy and security.

Quo, formerly known as OpenPhone, provides an AI-powered business phone system designed for startups and small businesses. It consolidates calls, texts, and contacts into a single shared workspace, enhancing team alignment and customer response times. A key feature is Sona, Quo’s AI voice agent, which offers 24/7 call answering, captures details, transfers calls, and ensures no customer interaction is missed. The system supports various devices including mobile (iOS and Android) and desktop, using an internet connection for calls and messages. Quo also offers features like voicemail transcription, phone menus (IVR), local and vanity numbers, virtual SMS numbers, and analytics for tracking performance. It aims to provide a reliable and efficient communication solution that scales with business needs.

Doom is a unique AI Agents & Automation tool hosted on Hugging Face Spaces, offering users the classic Doom game experience directly within their web browser. This eliminates the need for any downloads, allowing for instant access to the original gameplay, complete with all its challenges and excitement. While primarily a game, its hosting on Hugging Face Spaces positions it within a platform known for AI applications and machine learning demos. The tool provides a straightforward way to engage with a piece of gaming history without complex setup, making it accessible to a wide audience. It leverages the web-based capabilities of Hugging Face Spaces to deliver a seamless and immediate gaming experience.

tape (Tasks Assessing Protein Embeddings) is an open-source project from the Song Lab at UC Berkeley, designed to benchmark and assess protein embeddings across various domains of protein biology. It offers a comprehensive suite of resources including a pretraining corpus, five supervised downstream tasks, pretrained language model weights, and benchmarking code. The tool has been updated to use PyTorch, providing an API for loading pretrained models like BERT, UniRep, and trRosetta. Users can embed proteins from FASTA files, train language models, and evaluate both language and downstream models. While the training code is provided, the developers recommend using frameworks like PyTorch Lightning or Fairseq for future compatibility and ease of use, focusing their efforts on maintaining model availability.

Dataherald is an open-source natural language-to-SQL engine designed for enterprise-level question answering over relational data. It enables users to set up an API from their database, allowing them to answer questions in plain English without needing to write SQL. This tool is ideal for business users who need to gain insights from data warehouses without relying on data analysts, for integrating Q+A capabilities from production databases into SaaS applications, and for creating ChatGPT plugins from proprietary data. The platform includes an engine for core NL-to-SQL functionality, an enterprise layer for authentication and business logic, an admin console for GUI-based configuration, and a Slackbot for interactive querying.

ONVY HealthTech offers an AI Health Intelligence Layer designed for companies to optimize health and wellness experiences. It integrates data from over 500 health and wellness sources, including wearables, health apps, and lab results, into a unified, compliant platform. The tool provides AI-powered health coaching modules for areas like sleep, nutrition, and recovery, delivering personalized insights and guidance. Additionally, ONVY includes business intelligence dashboards for tracking key metrics, engagement, and health outcomes, leveraging a collective intelligence layer for advanced analytics and population-level insights. It supports various deployment models, including API, SDK, white-label apps, and fully custom solutions, making it adaptable for diverse industries from fitness to telehealth and corporate wellness.

TinyEngine is the official implementation of a memory-efficient and high-performance neural network library specifically designed for Microcontrollers. As a core component of MCUNet, a system-algorithm co-design framework, TinyEngine works in conjunction with TinyNAS to facilitate tiny deep learning on IoT devices with extremely tight memory budgets. It significantly outperforms existing inference libraries like TF-Lite Micro, CMSIS-NN, and X-CUBE-AI by improving inference speed by 1.1-18.6x and reducing peak memory by 1.3-3.6x. Key optimization techniques include in-place depth-wise convolution, patch-based inference, operator fusion, SIMD programming, and various loop optimizations to enhance performance and minimize memory footprint.

Email Bind provides a unique service that allows users to interact with powerful AI models like ChatGPT (GPT-3.5/4) and Google Bard directly through email. Users can initiate conversations by sending an email to gpt@emailbind.com or bard@emailbind.com after a simple email verification process. The service supports multi-turn conversations, with the Bard model offering internet connectivity for up-to-date information and Chinese language support. While a free trial mode is available, advanced features such as prompt templates, GPT-4 model access, and custom token/temperature settings can be unlocked by downloading the 'Email Bind' App on iPhone, with an option to upgrade to a Pro version for full functionality.

imgProof, branded as Gard, is an AI-powered image spell checker and design proofing software designed to prevent typos and grammatical errors from reaching clients in ads, infographics, packaging, and other visual designs. It offers automated image proofing by scanning new designs from watch folders, context-aware grammar checking that understands design context, and visual proofreading with highlighted errors and suggested corrections. The tool supports batch processing for high-volume workflows, making it ideal for agencies. Gard is highly accurate, leveraging state-of-the-art AI models, and supports over 50 languages. It processes standard image formats like JPEG, PNG, and WebP, and offers a free trial.

RobustMQ is a unified messaging engine built with Rust, designed as a communication infrastructure for the AI era. It operates as a single binary, one broker, and one storage layer, eliminating external dependencies and allowing deployment from edge devices to cloud clusters. It natively supports MQTT, Kafka, NATS, AMQP, and its own mq9 protocol on a shared storage layer, meaning a message written once can be consumed by any protocol. The mq9 protocol is specifically designed for AI Agent asynchronous communication, offering features like agent mailboxes with persistent store-first delivery, priority levels, and public mailbox discovery. RobustMQ emphasizes minimal operations, multi-tenancy, and ultra-low-latency dispatch, making it suitable for diverse messaging needs from IoT to streaming data pipelines.

TensorLayer is a powerful, open-source deep learning and reinforcement learning library built for scientists and engineers. It offers an extensive collection of customizable neural layers, enabling rapid development of advanced AI models. Inspired by PyTorch, TensorLayer provides transparent and flexible APIs, making it easier to build and train complex AI models compared to other TensorFlow wrappers. It supports multiple backends including TensorFlow, PyTorch, MindSpore, PaddlePaddle, OneFlow, and Jittor, allowing deployment on various hardware like Nvidia-GPU and Huawei-Ascend. The library is recognized for its simplicity, flexibility, and high performance, with comprehensive documentation and a large community.

AI ChatFun is an iOS mobile app designed to provide users with an AI companion for emotional connection and role-playing. It allows users to engage in thrilling role-play games and offers unrestricted picture and voice exchanges with chosen AI characters. This app serves as a virtual AI girlfriend, helping users combat loneliness and explore imaginative interactions. The focus is on creating a personalized and interactive experience through AI-driven conversations and multimedia exchanges, fostering a sense of companionship and fun.

sherpa is an open-source speech-to-text inference framework built with PyTorch, designed for deploying pre-trained models to transcribe speech. It specializes in end-to-end models, particularly transducer- and CTC-based architectures, offering high-performance speech recognition capabilities. Developers can integrate sherpa into their projects using either C++ or Python APIs, making it versatile for various development environments. The framework is ideal for those looking to implement custom speech-to-text solutions, leverage advanced AI models for audio processing, or contribute to the open-source AI community. Its focus on inference means it's optimized for efficient deployment of trained models.

Kedro is an open-source Python framework designed for building production-ready data engineering and data science pipelines. It emphasizes software engineering best practices to ensure pipelines are reproducible, maintainable, and modular. Key features include a project template based on Cookiecutter Data Science, a Data Catalog for connecting to various data sources and versioning, and pipeline abstraction for automatic dependency resolution and visualization with Kedro-Viz. Kedro also supports coding standards like test-driven development with pytest and flexible deployment strategies, including integration with Argo, Prefect, Kubeflow, AWS Batch, and Databricks. It aims to address the shortcomings of one-off scripts and Jupyter notebooks by promoting team collaboration and efficiency through modular, reusable analytics code.

LiveC is an AI companion designed to offer emotional support, intelligent assistance, and personalized conversations. Users can create a personalized AI girlfriend or companion who understands and grows with them. Key features include 24/7 compassionate AI emotional support with empathetic conversations, real-time emotional responses, and personalized coping strategies. The platform also includes mood tracking with daily check-ins, emotional pattern analysis, and progress visualization. Guided exercises like meditation, mindfulness, and stress relief techniques are available, alongside a growth journey tracker for personal milestones and custom wellness goals.

Talkie AI is a platform designed for creating and interacting with AI characters, offering a unique experience for multimodal dreams. Users can engage in AI free chat and AI character chat, exploring a new way to interact with artificial intelligence. The platform provides AI companions for various interactive narratives, allowing for personalized conversations. It caters to users interested in roleplay AI, including the ability to chat with AI characters designed as AI boyfriends and AI girlfriends, providing a soulful AI experience. Talkie AI aims to be more than just an AI companion, fostering creative and engaging interactions.