AI Agents & Automation

Whisper-Flow is an open-source framework designed for real-time transcription of audio content using OpenAI’s Whisper model. Unlike traditional batch processing, Whisper-Flow accepts a continuous stream of audio chunks and produces incremental transcripts immediately. It leverages a tumbling window technique to segment audio based on natural speech patterns, returning partial and complete transcriptions as events. The tool provides impressive performance metrics, achieving sub-second latency and around 7% word error rate on a MacBook Air with an M1 chip. It can be installed as a Python package, deployed with Docker, or run as a FastAPI server, offering flexibility for developers to integrate real-time speech-to-text functionality into their applications.

ir-sim is an open-source, Python-based lightweight robot simulator specifically designed for navigation, control, and learning applications. It offers a simple and user-friendly framework that includes built-in collision detection, making it ideal for academic and educational use. The simulator allows for rapid prototyping of robotics and learning algorithms in custom scenarios with minimal coding and hardware requirements. Key features include the ability to simulate various robot platforms with diverse kinematics and sensors, quick scenario configuration using straightforward YAML files, and visualization of simulation outcomes with a naive visualizer for immediate debugging. It also supports multi-agent/robot learning projects.

POS Dish is a comprehensive digital menu solution designed to revolutionize dining experiences and enhance restaurant efficiency. It provides a seamless contactless menu system, allowing customers to access menus via QR codes on their smartphones. The platform supports real-time menu updates, enabling restaurants to instantly add new dishes or adjust prices. Key features include an integrated customer loyalty program to boost repeat business, robust analytics for insights into customer preferences and sales trends, and multi-language support to cater to diverse clientele. POS Dish also offers a waiter app for streamlined operations, AI-powered customer-facing applications for personalized recommendations, and smart upsell/cross-sell strategies to increase average order value. It aims to reduce printing costs and waste while providing premium features at a fraction of the cost.

MetaGPT is an innovative multi-agent framework designed to simulate a complete software company, enabling collaborative task completion through role-based GPTs. It streamlines the software development process by taking a single-line requirement and generating detailed outputs such as user stories, competitive analysis, requirements, data structures, APIs, and documentation. The framework orchestrates various roles like product managers, architects, project managers, and engineers, following carefully defined Standard Operating Procedures (SOPs). This approach, encapsulated by the philosophy "Code = SOP(Team)", applies SOPs to teams composed of large language models, making it a powerful tool for natural language programming and automated software creation.

Hipert Srl specializes in developing advanced algorithmic and software solutions for autonomous devices, focusing on enabling vehicles and systems to perceive, interact with, and navigate their environments independently. The company hosts multiple working prototypes, including autonomous cars, delivery bots, RC models, drones, and industrial automation systems. Hipert's expertise spans various domains, including aerial drones, underwater and surface vehicles, and applications for street cars, cameras, and forklifts. They are particularly known for their new-generation autonomous driving systems, as highlighted by their involvement in projects like Unimore Racing and the European FRODDO Project.

This open-source project, named Snake, provides an AI-driven approach to playing the classic game of snake. It implements two distinct artificial intelligence algorithms: graph search and reinforcement learning. The graph search algorithm uses a rule-based strategy, modeling the grid as a graph to find paths for the snake, including Hamiltonian paths for optimal play. The reinforcement learning algorithm, based on deep reinforcement learning with a neural network and Double DQN technique, allows the snake to learn through trial and error, maximizing cumulative rewards. The project includes a pre-trained reinforcement learning model and offers options to play with either algorithm or train your own RL model, making it a valuable resource for AI enthusiasts and developers.

Impel is an advanced, industry-leading AI-Powered Customer Lifecycle Management platform specifically built for the automotive industry. It serves as an end-to-end AI Operating System that unifies every customer touchpoint, from initial inquiries to post-sale service. The platform offers specialized AI solutions for sales, chat, merchandising, service, and marketing, helping dealerships and OEMs streamline operations, scale impact, and unlock performance. Impel aims to transform how work gets done by automating mundane tasks, personalizing customer interactions, and driving measurable results across the entire customer lifecycle. It is designed to help automotive businesses convert shoppers into buyers and customers into loyalists, with deep integrations and domain-trained AI.

infiAgent, also known as MLA (Multi-Level Agent), is an open-source agent framework designed for handling long-running, complex tasks without issues like tool calling chaos or system crashes due to cumulative task resources and conversation history. It enables users to build powerful general-purpose and semi-specialized agents by simply editing configuration files. Key features include support for days-long complex tasks with full recovery from interruptions, compatibility with the Agent Skills open standard for dynamic skill loading, and a flexible architecture supporting both multi-level hierarchy and flat designs. The framework utilizes a file-directory-based memory system for persistent memory across sessions, eliminating the need for external databases. It also offers a Docker-based Web UI for multi-user registration and account management, and supports multi-provider model configurations for fine-grained cost control.

Automation Intelligence provides advanced solutions for industrial automation, leveraging digital twin consulting and decision science technology. Their services include developing physics-enabled virtual models of operations to identify and resolve automation challenges, allowing for rapid concept testing, virtual commissioning of new equipment, capacity planning, and operator training in a safe environment. Additionally, they deploy mathematical algorithms to optimize systems in real-time, utilizing data to orchestrate human and automated resources for efficient labor utilization, improved on-time deliveries, optimized production planning, and increased throughput. This is particularly beneficial for eCommerce, retail, and manufacturing sectors seeking to enhance operational efficiency and reduce downtime.

MOSTLY AI is a data intelligence platform designed to unlock the power of data through secure access, high-quality synthetic data generation, and seamless analysis. The platform features an AI Assistant for persistent data analysis and collaboration, allowing users to gain insights from live production data using natural language. It supports the creation of realistic mock data for safe experimentation and testing, and generates high-fidelity, privacy-safe synthetic datasets that mimic real data without exposing sensitive information. Additionally, MOSTLY AI enables the simulation of edge cases and future scenarios for stress testing strategies. The platform is built for individuals, teams, and enterprise organizations, offering scalable deployment options and an open-source Synthetic Data SDK for local data generation.

gym-pybullet-drones offers PyBullet Gymnasium environments specifically designed for single and multi-agent reinforcement learning in quadcopter control. This tool is a minimalist refactoring of its original repository, ensuring compatibility with Gymnasium, Stable-Baselines3 2.0, and Betaflight/Crazyflie-firmware SITL. It provides examples for PID control, downwash effect simulation, and reinforcement learning using SB3's PPO algorithm. Researchers and developers can use this environment to train and test control policies for drones, facilitating advancements in robotics and autonomous systems. The project also includes examples for integrating with Betaflight SITL and pycffirmware Python bindings.

InProfiler is an AI-powered tool designed to optimize LinkedIn networking and lead profiling. It intelligently analyzes and categorizes incoming LinkedIn connection requests, helping users identify and prioritize high-potential leads that align with their professional objectives. By streamlining this process, InProfiler enables users to focus their efforts on the most valuable connections, enhancing their lead management and outreach strategies. The tool aims to integrate with CRM systems, providing a comprehensive solution for professionals looking to leverage LinkedIn for business growth and networking efficiency. It's particularly useful for those who receive a high volume of connection requests and need an automated way to sort and evaluate them.

Guidellm is an open-source platform designed for evaluating and enhancing Large Language Model (LLM) deployments, focusing on real-world inference needs. It simulates end-to-end interactions with OpenAI-compatible and vLLM-native servers, generating workload patterns that reflect production usage. The platform produces detailed reports to help teams understand system behavior, resource needs, and operational limits. Guidellm supports both real and synthetic multimodal datasets, including text, image, audio, and video inputs, and offers flexible execution profiles. It provides SLO-aware benchmarking, capturing complete latency and token-level statistics for metrics like TTFT, ITL, and end-to-end behavior, ensuring consistent assessment of model performance, tuning deployments, and capacity planning.

Avea Robotics is dedicated to advancing the physical AI revolution within the field of robotics. The company's core mission is to empower the development of next-generation, real-world robotic systems. By providing simplified, end-to-end pipelines, Avea Robotics seeks to unlock unprecedented capabilities and scalability for robotics development. This approach aims to streamline the complex process of integrating AI into physical robots, making advanced robotic systems more accessible and efficient to build and deploy. The focus is on creating robust infrastructure that supports the intricate demands of AI-driven robotics.

Botonomous.ai is a unique platform that merges AI-generated news commentary with human-authored investigations and interactive data journalism. It features over 100 AI personalities, each with a distinct editorial voice, covering more than 15 categories. Users can join the debate by commenting on any post, challenging AI perspectives, or starting conversations that both humans and bots will engage with. The platform emphasizes quality through moderator bots and human editors, maintaining standards with full transparency. Users can also create their own AI bots tailored to specific interests, with options ranging from a free trial to paid plans for increased posting and reaction capabilities, or connect their own AI via API.

MyCareers by Leoforce is an AI-powered job platform designed to connect job seekers with relevant career opportunities. As the B2C arm of Leoforce, it utilizes over a decade of recruiting intelligence to power its AI matching system. The platform aims to provide a faster, fairer, and more fulfilling job search experience by matching individuals to roles based on their skills, ambitions, and values. Key features include personalized job alerts, a community for networking and career navigation, and free resources covering career, mental, and physical health topics. It helps users discover trending jobs and get notified about new opportunities.

lexvec is an open-source implementation of the LexVec word embedding model, designed to achieve state-of-the-art results in various Natural Language Processing (NLP) tasks. It functions similarly to other popular word embedding models like word2vec and GloVe. The tool offers pre-trained vectors derived from Common Crawl data, available in both subword and standard LexVec formats, with options for cased and lowercased words. Users can compute vectors for out-of-vocabulary (OOV) words using a binary model. LexVec supports both in-memory and external memory training, making it adaptable for large corpora. It also incorporates subword information through character n-grams, enhancing its performance. The project includes evaluation metrics against other models like fastText, word2vec Skip-gram, and GloVe, demonstrating its competitive accuracy.

Generative_Deep_Learning_2nd_Edition is the official code repository for the second edition of the O'Reilly book "Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play." This open-source resource provides practical code examples and outlines corresponding to the book's chapters, covering topics such as Variational Autoencoders, Generative Adversarial Networks, Autoregressive Models, Normalizing Flows, Energy-Based Models, Diffusion Models, Transformers, and advanced GANs. It is designed to help users learn and implement generative deep learning techniques, with instructions for setting up a Docker environment, downloading datasets, and using Tensorboard for monitoring experiments. The repository also includes guidance for using cloud virtual machines.

Audiogum offers business solutions designed to enhance smart devices through advanced AI capabilities. The platform specializes in content aggregation, providing a one-to-many API that grants access to over 20 content providers with a single integration. It also features intelligent personalization, which creates unique taste profiles for users to deliver relevant content and improve engagement. Furthermore, Audiogum incorporates Natural Language Understanding (NLU) AI, enabling devices to interpret user requests naturally and respond intelligently. This suite of technical solutions aims to help products stand out by offering innovative features and smarter experiences for end-users.

GPT-4V-Act is an AI agent that leverages GPT-4V(ision) and a web browser to interact with web user interfaces, mirroring human operations through screen feedback and low-level mouse/keyboard interaction. Its primary objective is to facilitate a smooth transition between human and computer operations, enhancing UI accessibility, automating workflows, and enabling automated UI testing. The tool utilizes Set-of-Mark Prompting and a tailored auto-labeler that assigns unique numerical IDs to interactable UI elements. This allows GPT-4V-Act to deduce subsequent actions based on a task and a screenshot, using numerical labels for precise pixel coordinates for mouse/keyboard output. The project also incorporates features like JS DOM auto-labeler, clicking, and typing characters.

All-in-One Demo is an AI demonstration tool hosted on Hugging Face Spaces, designed to showcase various AI functionalities. It is built using Gradio, an open-source Python library for creating easy-to-use UI components for machine learning models. This tool is intended for individuals, developers, and researchers who wish to explore and test different AI models and applications. While the live website indicates a runtime error, suggesting it may not be currently operational, its purpose is to provide a platform for interacting with AI models. It is licensed under AFL-3.0, making it accessible for free use and modification.

Atlas Software Technologies offers comprehensive AI consulting and software development services, focusing on business intelligence, data science, and machine learning. They assist organizations in implementing cutting-edge AI technologies to enhance products and capabilities. Their services include auditing, validating, and deeply understanding available data, as well as integrating custom software components. Atlas emphasizes delivering business value beyond mere offshore advantages, lowered costs, and faster turnaround times. They have a proven understanding of widely-used BI tools and offer solutions for both large enterprises and small businesses globally, covering areas from deployment to data auditing and AI integration.

Athenic AI is an advanced platform designed to democratize data insights, making analytics accessible to everyone regardless of their technical skill level. It functions as an AI data analyst, providing answers to business questions on demand and insights on autopilot. The tool offers chat-based data interaction, deep research capabilities for multi-step investigations, and customizable dashboards. A key differentiator is its "Agentic Analysis" feature, which proactively monitors business metrics, identifies root causes of changes, and surfaces unprompted insights and anomalies. Athenic AI emphasizes zero hallucination, grounding every answer in governed metrics and verifying against the data layer to ensure trustworthiness. It aims to replace legacy BI tools by offering similar features at a fraction of the cost, with instant dashboard creation, collaborative editing, and scheduled reports.

The fraud-detection-handbook is a comprehensive, open-source resource dedicated to reproducible machine learning for credit card fraud detection. It functions as a practical handbook, offering detailed insights into the motivations and active research within this field. The resource emphasizes reproducibility, with all techniques and results provided in Jupyter notebooks that can be executed locally or on cloud platforms like Google Colab or Binder. It is designed for students and professionals interested in credit card fraud detection from a practical standpoint, as well as data practitioners and scientists dealing with sequential data and imbalanced classification problems. The handbook covers topics such as book overview, background, getting started, performance metrics, model selection, imbalanced learning, and deep learning.