AI Agents & Automation

aignosi Brasil provides SIENTIA™, an innovative Industrial AIOps platform that enables companies to rapidly deploy and scale AI models in Operational Technology (OT) environments. The platform focuses on transforming data (DataOps) and model (MLOps) operations, helping businesses move AI proofs of concept (PoCs) into full production 10x faster. SIENTIA™ is already utilized by enterprise clients across various heavy-asset industries, handling millions of inferences per month with low latency. Beyond the platform, aignosi offers complementary services including AI Maturity Assessments, Analytical Transformation, and Analytical Core support to help clients create tailored AI solutions and optimize operational efficiency.

Megatron-LM is an NVIDIA-developed, GPU-optimized library designed for training large transformer models at scale. It comprises two main components: Megatron-LM, which offers pre-configured training scripts for research teams and quick experimentation, and Megatron Core, a composable library providing GPU-optimized building blocks for custom training frameworks. Megatron Core includes transformer building blocks, advanced parallelism strategies (TP, PP, DP, EP, CP), mixed precision support (FP16, BF16, FP8, FP4), and various model architectures. It's ideal for framework developers and ML engineers building custom training pipelines. The library also features Megatron Bridge for bidirectional Hugging Face ↔ Megatron checkpoint conversion, ensuring interoperability and production-ready recipes. It supports training models from 2B to 462B parameters across thousands of GPUs, achieving high Model FLOP Utilization (MFU).

Outside is a versatile tool designed to help individuals and teams organize, track, and share their work efficiently. It manages five distinct data types, with trips being one of them, providing a centralized platform for various organizational needs. This tool aims to simplify work management by consolidating different aspects into a single location, making it easier for both solo users and collaborative teams to stay on top of their projects and information. Its focus on managing multiple data types suggests a broad application for different organizational challenges.

Hubcap is a Go binary that wraps the entire Chrome DevTools Protocol (CDP) into 118 composable command-line commands, specifically designed for AI agents. It offers a powerful alternative to traditional browser automation methods by providing direct, low-level access to browser functionalities like network interception, performance profiling, and DOM manipulation. Each command outputs structured JSON, uses semantic exit codes, and works seamlessly with standard Unix tools, making it trivial for AI agents to invoke without SDKs or complex websocket management. This stateless design optimizes for Agentic Experience (AX), allowing agents to explore capabilities, debug, and monitor browser activities efficiently.

Shift-AI-models-to-real-world-products is an Open Source repository offering comprehensive guides and references for transitioning AI models from research and development into practical, real-world products and projects. It provides insights into various stages of AI product development, including machine learning project processes, team composition, product manager challenges, pre-sales solutions, data management, model training and deployment, and MLOps. The resource is particularly valuable for those looking to understand the engineering and productization aspects of AI, especially within B/G (Business/Government) markets and computer vision applications. It aims to bridge the gap between theoretical AI models and their successful implementation in commercial or governmental settings.

MultiAgentPPT is an intelligent presentation generation system that integrates A2A (Agent2Agent), MCP (Model Context Protocol), and ADK (Agent Development Kit) architectures. This system supports multi-agent collaboration and streaming concurrent mechanisms to produce high-quality, editable presentation content. It automates the process from theme input to complete presentation generation, including outline generation, topic splitting, parallel research by multiple agents, and summary generation. The tool offers real-time streaming of generated PPT content, enhancing user experience, and is designed for extensibility with new agents and functional modules. It also includes features like PPT quality checking, dynamic image rendering, and PPTX download capabilities.

AI Momentum Partners (AMP) is a technology services firm specializing in end-to-end AI strategy and execution. They guide businesses from initial AI roadmap development to real-world impact, focusing on accelerating growth, efficiency, and ROI. AMP offers tailored strategies and solutions, blending strategic rigor with hands-on execution. Their services cover experimentation, planning, implementation, and optimization of AI solutions, ensuring tangible AI-driven outcomes quickly. They differentiate themselves from traditional consulting firms and technical agencies by providing comprehensive support, ROI-driven strategies, custom AI solutions, and ongoing support with continuous improvement.

TencentPretrain is a powerful PyTorch-based framework designed for pre-training and fine-tuning AI models, supporting various data modalities including text and vision. Its modular architecture facilitates the use of existing pre-training models and provides clear interfaces for users to further develop and customize their own models. This makes it an ideal solution for researchers and developers looking to experiment with or deploy advanced AI models. The framework emphasizes flexibility and extensibility, allowing for adaptation to diverse research and application needs in the AI domain.

PyMARL is a Python-based, open-source framework developed by WhiRL for deep multi-agent reinforcement learning. It provides implementations of several prominent algorithms, including QMIX for monotonic value function factorisation, COMA for counterfactual multi-agent policy gradients, VDN for value-decomposition networks, IQL for independent Q-learning, and QTRAN for learning to factorize with transformation. The framework is built using PyTorch and integrates with SMAC (StarCraft Multi-Agent Challenge) as its environment, specifically using SC2.4.6.2.69232 for the results in the SMAC paper. PyMARL supports saving and loading trained models, as well as watching StarCraft II replays, making it a comprehensive tool for researchers and developers in the multi-agent RL domain.

boos-helper is an open-source browser extension designed to enhance the job application experience on platforms like Boss Zhipin. It streamlines the process by optimizing the user interface, removing advertisements, and enabling batch resume delivery. The tool offers advanced filtering options, including salary, company name, job title, and applicant count, along with location-based filtering using Gaode API for driving/walking distance and time. A key feature is its GPT-powered automatic greetings and replies, supporting multiple AI models for personalized communication. Additionally, it includes multi-account management and aims to provide features like a dark mode, adaptive UI for mobile, and a blacklist for companies.

Phoenix Technologies AG, operating as PHOENIQS, is a Swiss-based AI and cloud service provider focused on delivering sovereign, high-performance computing solutions for enterprises. PHOENIQS emphasizes data control, security, and strategic independence, ensuring organizations have full command over their digital infrastructure. Their offerings include PHOENIQS Cloud Services for AI-ready infrastructure, PHOENIQS Model Service for accessing multi-tenant FP16-quality open-source models without logging traffic, and the PHOENIQS AI Platform for deploying governed AI applications within Swiss jurisdiction. The company guarantees robust data protection and privacy, adhering to the highest standards of security and reliability.

artyom.js is a robust and constantly updated open-source JavaScript library that wraps the webkitSpeechRecognition and speechSynthesis APIs. It enables developers to integrate voice control, voice commands, speech recognition, and speech synthesis into their web applications. Key features include quick recognition of voice commands, easy addition of dynamic commands, smart commands with wildcards and regular expressions, and the ability to convert voice to text. The library supports synthesizing large blocks of text and works on both desktop browsers and mobile devices. It offers support for multiple languages and provides options for continuous listening, soundex algorithm for accuracy, and a remote command processor. Developers can create custom voice assistants similar to Siri, Google Now, or Cortana within their websites.

MetaMevs provides a comprehensive suite of automated MEV bots engineered to help users capture on-chain profits from DEX transactions. The platform eliminates the need for coding, making advanced trading strategies accessible to a wider audience. Key offerings include the Sandwich Mevbot for reliable smart contract execution, an HFT Futures and Spot Bot for high-frequency trading on platforms like Binance and KuCoin, and a Flashloan Arbitrage Bot that leverages AI and smart contract strategies to profit from price differences in DeFi. Additionally, the MetaMev Sniper bot uses AI, similar to GPT-4, to identify and snipe verified tokens on launchpads and social media. MetaMevs emphasizes cutting-edge technology, unmatched performance with millisecond execution, easy integration, and robust security features, all within customizable solutions.

PyHealth is a comprehensive, open-source deep learning Python toolkit designed to support clinical predictive modeling for both ML researchers and medical practitioners. It aims to make healthcare AI applications easier to develop, test, and deploy, offering flexibility and customizability. Key features include a modular 5-stage pipeline, a healthcare-first approach with support for medical codes and clinical datasets like MIMIC and eICU, and over 33 pre-built models with production-ready trainers and metrics. The toolkit supports more than 10 healthcare tasks and datasets, providing fast data processing for quick experimentation. PyHealth also includes independent modules for medical code mapping (pyhealth.medcode) and medical code tokenization (pyhealth.tokenizer), enhancing its utility for complex healthcare data.

Applying_EANNs is a 2D Unity simulation designed to showcase how cars can learn to navigate various courses. The cars are controlled by a feedforward neural network, whose weights are optimized using a modified genetic algorithm. This project provides a practical demonstration of evolutionary artificial neural networks in a simulated environment. Users can tinker with simulation parameters in the Unity Editor or run the built executable with default settings. The neural network architecture includes an input layer, two hidden layers, and an output layer, with its training managed by a customizable genetic algorithm. The user interface displays real-time data for the best performing car, including neural network output, evaluation value, and a generation counter, along with a visual representation of the neural network's weights.

Reachy Mini Minder is a voice-first care companion specifically designed for the Reachy Mini robot. This application enables users to interact with their robot naturally through speech to record important health information, such as medication doses and headache details. The companion saves this information and displays it on a live dashboard, offering a convenient way to track health data. Hosted on Hugging Face Spaces, Reachy Mini Minder aims to provide accessible and intuitive assistance for caregiving, leveraging AI to simplify health logging and monitoring.

Sonata is the official project repository for "Sonata: Self-Supervised Learning of Reliable Point Representations," a CVPR'25 Highlight paper. This open-source tool provides self-supervised pre-trained Point Transformer V3 models specifically designed for various 3D point cloud downstream tasks. Users can leverage Sonata for quick inference and visualization, with easy-to-use installation options for both standalone and package modes. The repository includes pre-trained models, inference code, and visualization demos, making it accessible for researchers and developers. It supports custom data integration and offers a flexible data transformation pipeline, along with options for loading models from Huggingface or local paths, even accommodating environments without FlashAttention.

Vultisig's Plugin Marketplace is a decentralized platform designed for building, deploying, and monetizing automation tools within the crypto space. Leveraging Vultisig’s Multi-Party Computation (MPC) infrastructure, it allows for secure crypto automation without compromising custody. Developers can create plugins that propose transactions, with a verifier enforcing user-defined rules before signing, ensuring robust security. The marketplace supports automation across multiple chains and provides a platform for developers to distribute their plugins and earn fees on every install. This infrastructure eliminates single points of failure through threshold signatures, making it ideal for secure and efficient DeFi operations.

MagicTrips is an AI-powered itinerary generator designed to simplify travel planning. Users input their desired destination and trip criteria, and the tool instantly creates custom travel itineraries. It aims to provide personalized recommendations and streamline the process of organizing vacations. The platform emphasizes ease of use, allowing users to generate detailed plans quickly. MagicTrips is currently offered for free, making it an accessible option for anyone looking to plan their next trip efficiently.

Synaptic is an open-source JavaScript neural network library designed for both Node.js environments and web browsers. Its core strength lies in its architecture-free algorithm, which allows developers to construct and train virtually any type of first-order or second-order neural network. The library comes equipped with several built-in architectures, including multilayer perceptrons, multilayer long-short term memory networks (LSTM), liquid state machines, and Hopfield networks. Additionally, it features a versatile trainer capable of training any given network, complete with built-in tasks for testing and comparing architectural performance, such as solving XOR problems or completing Distracted Sequence Recall tasks. This makes Synaptic a powerful tool for developers looking to implement and experiment with neural networks in their JavaScript projects.

Paddle3D is an open-source, end-to-end deep learning 3D perception toolkit developed by PaddlePaddle. It provides a flexible framework for handling various 3D data formats and supports integration with PaddleDetection and PaddleSeg for 2D vision capabilities. The toolkit features a rich model library covering mainstream 3D perception algorithms across monocular, point cloud, and multi-camera modalities, including detection and segmentation tasks. It offers full-process support from data processing and model building to training, optimization, and deployment, with compatibility for major 3D datasets like KITTI, nuScenes, and Waymo. Paddle3D is optimized for performance on various autonomous driving chips and seamlessly integrates with the Apollo autonomous driving platform.

Flourish Science is an AI-driven mental wellness application designed to promote well-being, motivation, and personal growth. Developed by psychologists, it features Sunnie, an AI wellness buddy available 24/7 to help users manage stress and anxiety, improve focus, and build healthy habits. The app incorporates evidence-based techniques from positive psychology, mindfulness, CBT, and DBT, transforming them into personalized, in-the-moment exercises. Key features include a focus timer, interactive journal, positive affirmations, relaxation exercises, and a smart habit tracker with gamified experiences. Flourish also provides meaningful insights through session notes, emotion charts, and weekly/monthly reports, fostering a supportive community for users.

Starter Template offers a foundational structure for initiating new projects within the CrewAI framework, designed to simplify the setup and development process. It provides fully functional CrewAI applications that serve as practical examples for building real-world AI agent orchestration solutions. This resource is part of a broader collection of examples, demonstrating end-to-end implementations and best practices for leveraging CrewAI's capabilities. Developers can utilize these templates to quickly prototype, learn, and deploy complex AI agent systems, accelerating their development cycles and ensuring adherence to effective architectural patterns within the CrewAI ecosystem.

Exabits.ai serves as the backbone of AI infrastructure, providing a comprehensive network of GPUs designed to accelerate AI development and innovation. Their offerings span from consumer-grade GPUs to high-end NVIDIA models like GB200s, H100s, H200s, and RTX5090s. Exabits is dedicated to refining raw GPU assets from leading manufacturers to deliver the most cost-effective compute solutions available. The platform is obsessed with innovating performance, ensuring that users have access to powerful and sustainable computing infrastructure for their AI applications and web3.0 initiatives. This focus on diverse GPU availability and performance optimization makes Exabits a key player in supporting advanced AI workloads.