AI Agents & Automation

RL-Factory is an open-source framework designed for efficient reinforcement learning (RL) post-training in Agentic Learning. It significantly simplifies the process by decoupling the environment from RL post-training, allowing users to train agents with only a tool configuration and a reward function. A key differentiator is its support for asynchronous tool-calling, which makes RL post-training up to 2x faster than existing frameworks. The platform natively supports one-click DeepSearch training, multi-turn tool-calling, model judge reward mechanisms, and training for various models, including Qwen3. Future updates aim to introduce a WebUI for data processing, environment definition, and project management, alongside support for more models and multimodal agentic learning.

DeepCTR-Torch is a comprehensive, open-source Python package designed for building and experimenting with deep learning-based Click-Through Rate (CTR) models, leveraging the PyTorch framework. It offers a modular and extensible architecture, allowing users to easily implement and customize a wide range of CTR models, including popular architectures like DeepFM, xDeepFM, and Wide & Deep. The package includes numerous core component layers, enabling data scientists and researchers to construct their own custom models efficiently. With its user-friendly API, DeepCTR-Torch simplifies the process of training and predicting with complex models using standard `model.fit()` and `model.predict()` functions, making it an invaluable tool for recommendation systems and advertising applications.

PokeAI offers an engaging platform for users to dive into AI-driven conversations with virtual humans. Each virtual human is designed with unique personalities and interests, providing a tailored and immersive conversational experience. The platform emphasizes endless conversation possibilities, ensuring interactions are never dull or repetitive. While the app is free to use, it also provides premium features through paid plans. PokeAI is currently available for Android and iOS devices, with a strong focus on user privacy and safety for all conversations.

n8n-docs serves as the official documentation repository for n8n, a fair-code licensed automation tool. It offers comprehensive resources for both the free community edition and powerful enterprise options, guiding users on how to effectively connect various applications and build automated workflows. The documentation specifically highlights how to integrate and build AI functionality into these workflows, making it a valuable resource for developers and technical users looking to leverage n8n's capabilities. It includes detailed guides on setting up local previews, troubleshooting common issues, and contributing to the documentation itself, ensuring a smooth experience for both new and experienced users.

MyIP is a comprehensive, open-source IP Toolbox designed for detailed network analysis and diagnostics. It enables users to easily view their local and public IP addresses, perform IP geolocation lookups, and conduct essential network tests such as DNS leak detection and WebRTC connection examination. The tool also includes speed tests, ping tests, and MTR tests to assess network performance and connectivity. Additionally, MyIP offers website availability checks, WHOIS searches for domain and IP information, MAC lookups, and browser fingerprint analysis. It supports multiple languages, dark mode, a minimalist mobile-optimized mode, and PWA installation, making it a versatile solution for network professionals and users concerned with their online privacy and connectivity.

ROSA (Robot Operating System Agent) is an AI Agent developed by NASA JPL, designed to facilitate interaction with ROS1- and ROS2-based robotics systems through natural language queries. Built on the Langchain framework, ROSA empowers robot developers to inspect, diagnose, understand, and operate robots more efficiently. It supports custom agent creation, allowing for adaptation to various robots and environments, and offers features like identifying topics with publishers but no subscribers. The tool includes a TurtleSim demo for controlling a simulated robot and is actively developing an IsaacSim extension for direct integration and control within the simulation environment.

Mage-AI is an open-source platform designed for building, running, and managing data pipelines efficiently. It offers a self-hosted development environment that enables teams to create production-grade data pipelines using Python, SQL, or R in a modular, notebook-style UI. Key capabilities include automating ETL tasks, orchestrating data transformations, and connecting to various data sources like databases, APIs, and cloud storage with prebuilt connectors. The tool supports visual debugging with logs and step-by-step execution, and allows for manual or scheduled job execution. For advanced needs, Mage Pro offers enterprise orchestration, collaboration, AI-powered workflows, and robust features like multi-environment orchestration and real-time monitoring.

UAV_Obstacle_Avoiding_DRL is a comprehensive open-source project focused on developing deep reinforcement learning algorithms for autonomous obstacle avoidance in Unmanned Aerial Vehicles (UAVs). It addresses both static and dynamic environments, offering multiple approaches for each. For static environments, the project explores Multi-Agent Reinforcement Learning (MADDPG, DDPG, TD3) combined with artificial potential field algorithms. In dynamic settings, it utilizes disturbed flow field algorithms alongside single-agent reinforcement learning (PPO+GAE, TD3, DDPG, SAC). The project also includes implementations of traditional path planning methods like A* search, RRT, Ant Colony Algorithm, and D* algorithm for comparison, highlighting the superior performance of reinforcement learning approaches. It provides both MATLAB and Python implementations for various algorithms, making it a valuable resource for researchers and developers in UAV navigation.

SoTA-Point-Cloud is a GitHub repository offering an extensive survey of deep learning techniques applied to 3D point clouds. Published in IEEE TPAMI 2020, this resource covers major tasks such as 3D shape classification, 3D object detection, and 3D point cloud segmentation. It provides comparative results on numerous publicly available datasets, including ModelNet, KITTI, and Semantic3D. The repository also offers insightful observations and outlines future research directions, making it an invaluable resource for researchers and practitioners in the field of 3D computer vision. The maintainers regularly update the page with new results and suggestions.

RagaAI Inc. delivers production-grade AI Agent Suites specifically designed for critical sectors like Healthcare, Lifesciences, and Aerospace. The platform is engineered to provide maximum reliability, leveraging its proprietary Prism and Catalyst technologies. These AI Agent Suites are purpose-built to address complex challenges, offering solutions for areas such as Radiology, Allergy, and Clinical Trials. RagaAI emphasizes proven ROI and enterprise-grade reliability, aiming to empower healthcare leaders and other industry professionals with advanced AI capabilities. The tool focuses on reducing operational inefficiencies, as evidenced by claims of a 46.5% reduction in claim denials and 3x faster radiology review.

VRP-RL is an open-source project that leverages reinforcement learning to tackle complex combinatorial optimization problems such as the Vehicle Routing Problem (VRP) and the Traveling Salesman Problem (TSP). Developed by OptMLGroup, this tool provides a robust framework for researchers and developers to implement, train, and evaluate reinforcement learning models for route optimization. It is built using TensorFlow and includes all necessary dependencies like NumPy and tqdm. Users can easily run the code for both training and inference, with options to specify GPU usage, model directories, and inference types (batch or single mode). The project also logs all results, making it suitable for experimental research and performance analysis in the field of operational research and artificial intelligence.

Eyeballer is a convolutional neural network designed by Bishop Fox for analyzing penetration testing screenshots. It helps security professionals identify "interesting" targets from a vast collection of web-based hosts, particularly useful in large-scope network penetration tests. Users can employ their favorite screenshotting tools like EyeWitness or GoWitness, then process the outputs through Eyeballer to categorize them. The tool labels screenshots into categories such as "Old-Looking Sites" (indicating potential vulnerabilities), "Login Pages" (suggesting further functionality and credential enumeration opportunities), "Webapp" (signifying a larger attack surface), "Custom 404's" (to filter out uninteresting pages), and "Parked Domains" (to remove invalid attack surfaces from scope). Eyeballer provides results in both human-readable HTML and machine-readable CSV formats, offering performance metrics like Overall Binary Accuracy and All-or-Nothing Accuracy.

Sonara is an AI-powered platform designed to streamline and automate the job search process for individuals. It gets to know your skills and preferences, then continuously scans millions of job openings to find the best matches. The tool then automatically applies to these relevant positions, effectively multiplying the number of applications submitted with minimal effort from the user. Sonara aims to reclaim valuable hours for job seekers by handling the tedious grunt work of applications, allowing users to wake up to a curated list of new roles and significantly increase their application volume until they are hired.

PyTriton is a Flask/FastAPI-like framework designed to streamline the use of NVIDIA's Triton Inference Server within Python environments. It allows developers to serve machine learning models with ease, supporting direct deployment from Python. Key features include native Python support for exposing any Python function as an HTTP/gRPC API, framework-agnostic operation compatible with PyTorch, TensorFlow, or JAX, and performance optimizations like dynamic batching, response caching, and model pipelining. The tool also provides decorators for handling batching and pre-processing, high-level model clients for HTTP/gRPC requests, and alpha support for streaming partial responses.

RQ-VAE-Recommender offers a PyTorch implementation of a generative retrieval model, specifically designed for recommender systems. The model operates in two stages: first, it maps items in a corpus to a tuple of semantic IDs by training an RQ-VAE. Second, it tokenizes sequences of these semantic IDs using a frozen RQ-VAE and then trains a transformer-based model to predict the next IDs in the sequence. This approach is based on the research presented in "Recommender Systems with Generative Retrieval." It supports various datasets, including Amazon Reviews (Beauty, Sports, Toys), MovieLens 1M, and MovieLens 32M, and provides both RQ-VAE and decoder-only retrieval model training scripts. Pre-trained checkpoints are available on Hugging Face for Amazon Beauty.

RnPsoft is a pioneering technology company dedicated to building tomorrow’s solutions today. They are at the forefront of the technology world, delivering top-tier software and applications that redefine how businesses and individuals operate. RnPsoft offers a comprehensive suite of services including MI/A.I solutions, app development, software development, blockchain solutions, and real-time solutions. Their team of expert developers and engineers are committed to turning client visions into reality, whether it's robust software to streamline business processes or intuitive applications to engage customers. They also provide educational services and focus on empowering visions through innovative and tailored solutions.

langdetect is a Python library that serves as a direct port of Google's language-detection library, enabling developers to easily identify the language of text. It supports a wide array of 55 languages, including common ones like English, Spanish, French, and German, as well as many others. The library is compatible with Python versions 2.7 and 3.4+. While the language detection algorithm is non-deterministic for short or ambiguous texts, consistent results can be enforced by seeding the DetectorFactory. Users can also add new language profiles by generating them from Wikipedia abstract database files or plain text using a provided Java tool.

Inverse-Reinforcement-Learning is an open-source project providing implementations of various inverse reinforcement learning (IRL) algorithms. Developed as part of COMP3710, it was supervised by Dr Mayank Daswani and Dr Marcus Hutter. The project includes linear programming IRL (Ng & Russell, 2000), maximum entropy IRL (Ziebart et al., 2008), and deep maximum entropy IRL (Wulfmeier et al., 2015). Additionally, it features implementations of MDP domains like Gridworld (Sutton, 1998) and Objectworld (Levine et al., 2011). The repository also provides a final report detailing the implemented algorithms and offers module documentation for functions and classes.

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.

Agentic Employment is a tool hosted on Hugging Face Spaces by ruv, designed to streamline AI agents. The primary goal of this application is to enhance the performance and efficiency of AI agents across various applications. While the current live website content indicates a runtime error, suggesting it may not be fully operational or accessible at the moment, its stated purpose is to optimize agentic workflows. It is categorized under AI Agents & Automation, specifically within AI Frameworks & Infra, indicating its focus on foundational aspects of AI agent development and deployment. The tool is intended to be free to use, making it accessible for developers and researchers interested in agentic AI.

Unbody Lab is dedicated to questioning, exploring, experimenting, and building adaptive thinking tools. It challenges the traditional software paradigm where products are rigid and users adapt to them. Unbody envisions AI as a means to unlock latent human potential, surfacing what's already present but hard to access, such as patterns, blind spots, and capacity to act. The platform aims to create a cognitive exoskeleton that extends memory, sharpens attention, and fosters clarity. It prioritizes returning time to users rather than capturing it, and builds tools that adapt to the human, learning rhythms and respecting limits. Unbody also emphasizes calibrated friction, ensuring tools support intentions without competing for attention, and values craft as care, absorbing complexity so users don't have to.

Singulr AI delivers enterprise AI governance through its unified control plane, offering complete visibility, security, and compliance. The platform helps organizations discover, secure, and optimize AI adoption at scale by addressing challenges like shadow AI, data leakage, and compliance risks. Key features include AI Risk Intelligence powered by Singulr Pulse, application-aware AI red teaming, and enhanced runtime protection. It enables cross-functional collaboration for security, IT, privacy, and compliance teams, ensuring secure innovation without creating bottlenecks and accelerating AI adoption while maintaining control.

Cartoony is an iOS mobile application designed to leverage artificial intelligence for transforming selfies and photos into a variety of artistic styles, including anime, cartoons, and unique avatars. This tool offers users an instant and effortless method to generate distinctive digital art. It is ideal for individuals looking to personalize their profile pictures or create stylized images inspired by diverse artistic aesthetics. While the specific features of Cartoony are not detailed on the provided website, the overarching company, Gigantic Apps, focuses on creating user-friendly and high-quality educational and lifestyle applications, suggesting a similar approach for Cartoony.

Teachable Machine Community is an open-source repository offering example code snippets and machine learning code for Teachable Machine. Teachable Machine is a web-based tool designed to make machine learning model creation fast, easy, and accessible for everyone, including educators, artists, students, and innovators. Users can train a computer to recognize images, sounds, and poses without needing prior machine learning knowledge or coding. The repository includes a libraries section with machine learning code utilizing Tensorflow.js for in-browser model training and execution, along with API helper libraries for integrating exported models into projects. It also features a snippets section with code and instructions for using Teachable Machine models in languages like Javascript, Java, and Python.