AI Agents & Automation

The TinyFish Cookbook is a comprehensive, open-source repository featuring a growing collection of recipes, demos, and automations developed using the TinyFish web agent. It serves as an invaluable resource for developers looking to understand and implement web agent technology. The cookbook showcases various practical applications, from real-time deal aggregators and price comparison tools to AI-powered research assistants and scholarship finders. Each project within the repository is standalone, offering clear examples of how to leverage TinyFish's capabilities, including its four core endpoints for fast search, content fetching, multi-step browser automation, and fully managed cloud browser rentals. It highlights TinyFish's ability to turn any website into a programmable data source with natural language goals and built-in stealth features.

Purdue AI Racing is a program at Purdue University dedicated to fostering research and education in artificial intelligence. The initiative provides a platform for students and faculty to delve into various AI applications, particularly within the fields of engineering and robotics. It offers essential resources for the research and development of autonomous vehicle technology, contributing significantly to the university's broader mission of innovation in science and technology. The program aims to push the boundaries of AI knowledge and practical implementation through academic exploration and hands-on projects.

Uniem is an open-source project dedicated to developing and refining universal text embedding models, with a strong focus on the Chinese language. The project offers comprehensive code for training, fine-tuning, and evaluating these models, making it a valuable resource for researchers and developers. All models and associated datasets are made publicly available on the Hugging Face community, promoting accessibility and collaboration. Uniem supports fine-tuning for various models, including M3E, sentence_transformers, text2vec, and even GPT series models using SGPT methods and Prefix Tuning. It also features MTEB-zh, a standardized evaluation benchmark for Chinese embedding models, allowing for rigorous comparison across different models and tasks.

traceml is an open-source engine designed for comprehensive ML/Data tracking, visualization, explainability, drift detection, and dashboards, specifically integrated with Polyaxon. It enables machine learning engineers and data scientists to effectively monitor their experiments, visualize key metrics, understand model behavior, and detect data drift. The tool supports offline usage and offers integrations with popular deep learning and machine learning libraries such as Keras, PyTorch, TensorFlow, Fastai, PyTorch Lightning, and HuggingFace. Additionally, traceml provides robust artifact tracking for various chart types (Matplotlib, Bokeh, Altair, Plotly) and detailed DataFrame summaries for data profiling and quality checks.

Twitter Personality is a web application designed to analyze Twitter handles and generate personalized personality profiles using a Wordware AI Agent. This tool offers users unique insights into their online persona based on their Twitter activity. It utilizes cutting-edge AI technologies to process Twitter data and construct detailed profiles. The project is open-source, with its repository available on GitHub, allowing developers to explore the AI agent and prompts used in the application. Setting up the project involves cloning the repository, installing dependencies, and configuring various environment variables for database access, Wordware API keys, and other services like PostHog and Stripe, indicating potential for advanced features and analytics.

Stepsailor is an AI-powered platform designed to enhance customer education and streamline user interaction within software applications. It allows users to execute tasks using natural language commands, eliminating the need for complex menus. Stepsailor integrates an AI command bar into existing software, making it more intuitive and user-friendly. The platform is designed for easy integration and usability, offering various pricing tiers including a free option with 100 credits per month and paid plans with more credits and customization features like removing watermarks and custom styling. While currently on hold for a next-generation platform, its previous offerings focused on enabling businesses to build AI-powered products efficiently.

DAVI The Humanizers specializes in creating 'Digital Humans' for businesses, aiming to transform digital interactions into human-like relationships. Utilizing its proprietary DeepTech-labeled IA Retorik technology, DAVI develops digital employees capable of empathy and adapting to human emotional reactions. These Digital Humans can deliver various business expertises 24/7, without additional costs, addressing the need for increased productivity and revenue, especially in tight labor markets. The technology comprises RETORIK BODY ENGINE for human-like appearance, RETORIK STUDIO DIALOG for verbal logic and personalized responses, and RETORIK PERSONNALITY EMOTION for real-time emotional adaptation. DAVI offers solutions like WELCOM-INFOPOINT for digital reception, SALES ADVISOR for personalized sales, RECRUIT ROOM for optimized recruitment, and TRAINING ROOM for knowledge transfer.

ELI+ (Entrata Layered Intelligence) is an AI-powered platform designed to streamline property management operations. It provides specialized AI agents that automate key workflows such as leasing, rent collection, and renewals. The Leasing AI qualifies leads, answers prospect questions, and schedules tours via various communication channels. The Payments AI optimizes rent collection, while the Renewals AI proactively engages residents based on real-time data to maximize retention. ELI+ integrates natively with Entrata’s product suites, aiming to enhance conversion rates, resident satisfaction, and staff efficiency. It also includes ELI Essentials, offering generative AI, facilities app, and translation features to all Entrata customers.

bntr is an AI-powered virtual agent platform designed to automate and enhance customer interactions through both voice and chat AI solutions. The platform is engineered for easy setup, leveraging customer data to quickly train its AI models. It aims to provide comprehensive 24/7 customer support, helping businesses manage high volumes of inquiries efficiently. By deploying bntr, organizations can reduce call handling times, improve customer satisfaction, and ensure consistent service quality across all touchpoints. The tool is ideal for businesses looking to scale their customer service operations without significantly increasing their human resource overhead.

Goddard - Discovery offers an intelligent research assistant called Inventia AI, designed to empower researchers by augmenting their capabilities. This platform helps users find and organize research articles, discover latent knowledge within their field, and identify collaboration opportunities. Beyond Inventia AI, Goddard - Discovery also provides services in Artificial Intelligence, Data Science, and Web & App Development. The team is committed to advancing research communities by integrating AI into research processes, enabling breakthroughs and elevating work to unprecedented levels. They are actively shaping the future of research by providing tools and services that enhance scientific investigation across diverse domains.

whatsapp-gpt is an open-source project that enables users to connect ChatGPT with WhatsApp. This setup requires running WhatsApp from a phone number using a Go library and controlling ChatGPT via a dedicated browser in a separate window. The project involves running two terminals, one for the Go application and another for a Python server, to facilitate this interaction. Additionally, a `multichat.py` script is available for users interested in observing two ChatGPT instances communicate with each other. While the initial setup might require some technical familiarity, the project's open-source nature and relatively sparse code make it accessible for those willing to delve into the implementation. It offers a unique way to integrate conversational AI directly into the WhatsApp messaging platform.

Featurestore.org serves as a comprehensive hub for all things related to feature stores in machine learning. It curates content, including blog posts and videos, to inform and educate professionals on the evolving landscape of feature stores and their surrounding data and AI environments. The platform fosters a global community of data science professionals, researchers, and engineers, facilitating the sharing of ideas and collaborative learning through monthly meetups with industry experts. It also hosts annual Feature Store Summits, providing a forum for in-depth discussions and insights into the latest advancements and best practices in the field. The site features detailed comparisons of various feature store solutions, including open-source, vendor, and in-house options, covering aspects like ingestion APIs, supported platforms, and training data handling.

FantasyGF is an innovative platform offering a unique AI girlfriend experience, allowing users to create and interact with personalized virtual companions. Users can customize their AI girlfriend's appearance and personality, engaging in uncensored chats, voice calls, and video interactions. The platform leverages advanced AI to learn from interactions, making the companion more attuned to user preferences over time. Beyond conversation, FantasyGF enables the generation of stunning AI-powered images and even supports AI sexting in a private and secure environment. It's designed for those seeking companionship, emotional connection, or playful interactions, providing an always-available partner for various forms of engagement.

VibeVoice-ComfyUI provides a comprehensive integration for Microsoft's VibeVoice text-to-speech model directly within ComfyUI workflows. This tool allows users to generate natural speech with single or multiple speakers, supporting up to four distinct voices in a conversation. Key features include optional voice cloning from audio samples, fine-tuning voices with custom LoRA adapters, and adjustable voice speed control. It also handles long texts seamlessly with automatic chunking and custom pause tags. The integration is self-contained, cross-platform, and supports various backends like CUDA, CPU, and Apple Silicon's MPS, offering flexible configuration for attention mechanisms, diffusion steps, and memory management, including 4-bit and 8-bit quantization for VRAM savings.

Vosk-server is an open-source speech recognition server designed for highly accurate offline transcription. It leverages the powerful Kaldi and Vosk-API libraries to deliver robust speech-to-text capabilities without requiring an internet connection. The server offers flexibility through its support for multiple communication protocols, including MQTT, gRPC, WebRTC, and Websocket, making it adaptable to various application environments. It can be deployed locally to provide speech recognition for smart home systems or PBX solutions like FreeSWITCH and Asterisk. Additionally, vosk-server can function as a backend for streaming speech recognition on the web, powering chatbots, websites, and telephony applications. Its focus on offline processing and high accuracy makes it a valuable tool for developers and organizations requiring reliable speech recognition in diverse settings.

ARX Robotics specializes in developing advanced autonomous systems manufactured in Europe, providing scalable and mission-ready solutions for defense, logistics, and enhancing operational resilience. Their product line includes Gereon RCS, Mithra OS, and Hector, each designed to address critical challenges such as combat readiness, resilience against centralized infrastructure failures, and modernizing legacy fleets. ARX Robotics aims to strengthen Europe's technological resilience and sovereignty by building software-defined systems that are deployable and integrate with existing command systems, offering decision superiority across various missions. They support industries from battlefields to complex logistics, with applications in reconnaissance, firepower, clearance, surveillance, evacuation, cargo & freight, and data relay.

Mobileye is a leader in the evolution of automobility, specializing in advanced driver-assistance systems (ADAS) and autonomous driving (AV) technologies. The company utilizes world-renowned expertise in artificial intelligence, computer vision, machine learning, mapping, and data analysis to develop its solutions. Mobileye's modular product portfolio scales from current ADAS offerings like Mobileye ADAS and Mobileye SuperVision™ to future AV programs such as Mobileye Chauffeur™ and Mobileye Drive™. Their Compound AI System integrates cutting-edge AI with engineered precision to deliver explainable and safe automated driving decisions, built on a purpose-built SoC family and a mathematical safety model. Mobileye aims to bring safe and scalable self-driving technology to the mass market.

alloy-voice-assistant is an open-source project available on GitHub designed for developers to create and experiment with AI voice assistants. The project provides a foundational framework for building a sample AI assistant, requiring both an OPENAI_API_KEY and a GOOGLE_API_KEY for its functionality. Users can store these keys in a .env file or set them as environment variables. The repository includes clear instructions for setting up a virtual environment, installing necessary packages, and running the assistant, with specific guidance for Apple Silicon users. This tool is ideal for those looking to understand the mechanics of AI voice assistants and build custom applications.

Daft is a high-performance data engine specifically designed for AI and multimodal workloads, enabling the processing of images, audio, video, and structured data at any scale. It features native multimodal processing, allowing users to handle various data types within a single framework. The tool also includes built-in AI operations, facilitating tasks like LLM prompts, embedding generation, and data classification using models such as OpenAI, Transformers, or custom solutions. Built with Python at its core and Rust under the hood, Daft offers blazing performance without the complexity of JVM. It supports seamless scaling from local environments to distributed clusters on Ray and Kubernetes, and provides universal connectivity to data sources like S3, GCS, Iceberg, Delta Lake, Hugging Face, and Unity Catalog. Daft ensures out-of-box reliability through intelligent memory management and sensible defaults.

Senso acts as the context layer for AI agents, enabling organizations to compile raw documents, websites, and internal knowledge into a verified, grounded, and synchronized knowledge base. This ensures that AI agents provide accurate responses based on the organization's ground truth, preventing hallucinations and misrepresentation. The platform addresses the challenge of AI agents accessing disparate information by ingesting, compiling, and allowing any agent to query or generate content from the verified knowledge. Senso also offers scoring and governance features to align agentic channels with ground truth, providing visibility into mentions, citations, accuracy, and compliance across various AI models like ChatGPT, Perplexity, and Gemini. It is designed to power call center, compliance, and support agents from a single source of truth.

DiffusionKit is an open-source project designed for on-device image generation using diffusion models on Apple Silicon. It offers both Python and Swift packages, facilitating the conversion of PyTorch models to the Core ML format and enabling efficient inference with MLX. Developers can leverage DiffusionKit to run models like Stable Diffusion 3 and FLUX.1-dev directly on Apple devices, optimizing performance and reducing reliance on cloud resources. The tool supports various functionalities including text-to-image generation, image-to-image transformations, and fine-grained control over generation parameters such as seed, height, and width. Its architecture is built to support both Core ML and MLX backends, providing flexibility for integration into different application environments.

GPTAutoBot, operating under the name "PG赏金女王" (PG Bounty Queen), is an online platform primarily focused on PG electronic games. It offers an online simulator for the popular game "Bounty Queen," allowing users to experience high-quality entertainment content via mobile or PC. The platform provides convenient login services and incentivizes new users with彩金奖励 (cash rewards). Additionally, it features daily updated entertainment activities, including interactive tasks, lucky draws, and limited-time events. The platform emphasizes a smooth and secure APP download experience and aims to provide an immersive entertainment experience through its simulator interactions. It also mentions a commitment to optimizing content and services to meet diverse user needs.

Deeplearning4j is a comprehensive ecosystem designed for deploying and training deep learning models within the Java Virtual Machine (JVM) environment. It offers a high-level API for building MultiLayerNetworks and ComputationGraphs, supporting various layers including custom ones. A key feature is its ability to import models from popular frameworks like Keras, TensorFlow, ONNX, and PyTorch. The suite includes ND4J, a general-purpose linear algebra library with over 500 operations, and SameDiff, an automatic differentiation/deep learning framework similar to TensorFlow's graph mode. DataVec provides ETL capabilities for machine learning data, handling diverse formats and sources. The underlying C++ library, LibND4J, ensures high performance with CPU and GPU acceleration. Deeplearning4j supports Windows, Linux, and macOS, with broad hardware compatibility.

Moneypenny USA offers a comprehensive customer communication service, blending the expertise of human agents with advanced AI technology to provide 24/7 support across voice and text channels. The platform helps businesses manage customer interactions, qualify leads, and scale operations efficiently. Key features include a human-sounding AI Receptionist for automated call handling, KnowledgeBase for instant information retrieval, and MessageMaker for auto-drafting call summaries. Moneypenny also provides outsourced switchboard services, managed live chat, and multichannel customer service, ensuring consistent and emotionally intelligent responses. It serves a wide range of industries, helping businesses enhance customer experience and improve marketing performance.