AI Agents & Automation

PULP-Dronet is an open-source, deep learning-powered visual navigation engine designed to enable autonomous navigation for pocket-size quadrotors. It allows nano-drones to explore environments and avoid dynamic obstacles without human intervention, external signals, or remote computation. The system comprises both software, based on the DroNet convolutional neural network, and hardware components, including a Parallel Ultra-Low-Power (PULP) GAP8 System-on-Chip (SoC) and an ultra-low power camera. The project has evolved through several versions, optimizing for reduced memory footprint, faster inference times, and lower power consumption, making it suitable for resource-constrained nano-UAVs. It also includes methodologies for dataset collection and automated deployment of DNNs.

RAGEN (Reasoning AGENT) is a flexible reinforcement learning framework designed for training reasoning agents, particularly Large Language Models (LLMs), in interactive and stochastic environments. It introduces StarPO (State-Thinking-Actions-Reward Policy Optimization), a unified RL framework that supports multi-turn, trajectory-level agent training with fine-grained control over reasoning processes, reward assignment, and prompt-rollout structures. RAGEN-2, the latest iteration, includes SNR-Adaptive Filtering to mitigate noisy gradient updates and reasoning collapse diagnostics to detect and monitor template collapse during training. The framework is compatible with Gym environments and offers 10 built-in environments for diverse testing. It's ideal for researchers and developers focused on advancing the capabilities and stability of LLM-based agents.

Replica Studios was an AI voice platform that provided tools for text-to-speech and audio editing, catering to various creative projects including gaming and film production. The platform aimed to offer a user-friendly interface with styling and interactive elements for voice creation. However, Replica Studios has officially announced its closure, stating that it has signed off and is no longer operational. The company expressed gratitude to its users for their support during its journey.

SpikingJelly is an open-source deep learning framework specifically designed for Spiking Neural Networks (SNNs), built upon the PyTorch ecosystem. It aims to simplify the development and research of SNN-based AI applications, offering an intuitive way to construct SNNs similar to building ANNs in PyTorch. Key features include fast and handy ANN-SNN conversion capabilities, CUDA/Triton-enhanced neurons for accelerated training, and support for various neuromorphic datasets. The framework also provides multi-step neuron backends (torch, cupy, triton) for flexible coding and debugging, alongside optimized training speed. SpikingJelly is actively maintained, with ongoing improvements and future plans including NIR support and memory optimization.

Chatbot Compare is a Hugging Face Space application designed for evaluating and comparing the outputs of various chatbot models. It provides a user-friendly interface where you can input a custom prompt and system prompt, then select up to four different AI models to generate responses simultaneously. The tool also allows for adjustment of settings like temperature, offering flexibility for experimentation. This side-by-side comparison capability makes it an invaluable resource for researchers, developers, and anyone interested in understanding the nuances and performance differences between various conversational AI systems.

Wan 2.2 5B is an AI-powered tool hosted on Hugging Face Spaces, designed for generating short videos. Users can create videos by simply providing a text description, with the option to upload an image to further guide the visual content of the scene. The application offers customization options for video length and resolution, along with a few advanced settings to fine-tune the output. This tool is ideal for content creators or individuals looking to quickly produce visual content from textual prompts, offering a straightforward approach to video creation.

Wan2.1 Fun 1.3B InP is an AI-powered application developed by Alibaba-PAI, available as a Hugging Face Space, that specializes in text-to-image generation. Users can input a descriptive text prompt, and the tool will process this input to create a corresponding visual representation. This allows for the quick and easy creation of images based on textual ideas, making it suitable for various creative or illustrative purposes. The application is designed to be user-friendly, providing a straightforward interface for generating images from descriptions.

Feeling Great is a mental wellness application designed to improve emotional well-being through cognitive behavioral techniques. It helps users transform negative thoughts and feelings into positive ones by leveraging a revolutionary AI-powered chatbot and an interactive learning program. The app is developed based on the groundbreaking work of Dr. David Burns, author of the best-selling book "Feeling Good" and co-host of the "Feeling Good podcast," utilizing his T.E.A.M. approach to cognitive behavioral therapy. Users can experience a dramatic reduction in feelings of depression, anxiety, and hopelessness, with claims of significant improvement in as little as two hours. The app is available for download on both iPhone and Android devices.

SwitchAI is an open-source Android application designed to simplify the management of AI digital assistants on your device. It offers a fresh and streamlined approach, allowing users to easily select, start, and manage their preferred AI assistants. With SwitchAI, you can seamlessly switch between installed digital assistant apps, choose an assistant each time you activate your device's digital assistant feature, or set a default. It also supports quick access via home screen widgets and Quick Settings tiles. The tool boasts broad compatibility with a growing list of popular AI assistant apps, replacing older solutions like Plugin-VoiceGPT, and is ideal for anyone looking to optimize their interaction with multiple AI assistants on Android.

web-gpu-doc-chat is an innovative web application that brings a powerful Vicuna-7B language model directly into your browser environment. Users can upload or provide any text and then engage in conversational AI, asking questions or providing prompts, with the model responding instantly. This eliminates the need for server-side processing, offering a private and efficient way to interact with an LLM for document understanding and discussion. It's ideal for those who want to leverage advanced AI capabilities without external dependencies or data transfer.

simple_GRPO is an open-source implementation of the GRPO algorithm, specifically designed for reproducing r1-like LLM thinking. It utilizes a core loss calculation formula referenced from Hugging Face's trl, but with a significantly simplified codebase. The tool aims to save GPU memory, enabling feasible and efficient training, and helps users quickly understand and experiment with Reinforcement Learning processes like GRPO. It supports features such as improved multi-answer generation, regrouping, penalty on KL, and parameter tuning, all within approximately 200 lines of code across two files. The reference model is decoupled, allowing it to run on separate GPUs, which prevents multiple copies from being created by torch’s multiprocessing and enables training of large models on less powerful hardware.

Stable Diffusion WebUI Forge is an open-source platform that enhances the capabilities of Stable Diffusion WebUI, focusing on improving development workflows, optimizing resource management, and accelerating inference speeds. Inspired by 'Minecraft Forge,' it aims to become the definitive 'Forge' for SD WebUI. The platform is currently based on SD-WebUI 1.10.1 and synchronizes with the original WebUI periodically. It offers features like GPU memory management, support for various LoRAs, preprocessors, ControlNets, and IP-Adapters. Forge also integrates Gradio 4 UIs and provides one-click installation packages for different CUDA/Pytorch versions, making it accessible for users to quickly set up and run the environment.

WhiStress Demo is an AI-powered tool available on Hugging Face that provides audio transcription with a unique feature: it highlights emphasized words. Users can easily interact with the tool by either uploading an audio file or recording their voice directly within the interface. The platform is designed to offer clear transcriptions, with a recommendation to speak clearly for optimal results. This tool is particularly useful for analyzing speech patterns and identifying key stress points in spoken language, making it valuable for various applications from linguistic analysis to speech therapy demonstrations.

WebArena is a self-hostable, open-source web environment designed for building and evaluating autonomous AI agents. It provides a realistic web environment, enabling researchers and developers to reproduce results from academic papers and conduct new experiments. The platform has been significantly enhanced by AgentLab, offering features like parallel experiments using BrowserGym, integration of popular web navigation benchmarks such as VisualWebArena, and a unified leaderboard for reporting results. It also includes improved handling of environment edge cases, making it a robust framework for developing and testing AI agents in complex web interactions. The repository provides detailed instructions for installation, environment setup, and end-to-end evaluation, including generating test data and launching evaluations with various reasoning agents.

ThinkGPT is a Python library designed to augment Large Language Models (LLMs) by implementing Chain of Thoughts techniques. It enables LLMs to think, reason, and act as generative agents, addressing common limitations such as restricted context windows. Key features include memory management for LLMs to recall past experiences, self-refinement capabilities to improve model-generated content, and knowledge compression techniques to fit extensive information within an LLM's context. The library also offers inference based on available data, natural language conditions for decision-making, and efficient context length management, all through an easy-to-use Pythonic API.

Three Sigma is an AI research tool designed to streamline document interaction and utilization. It significantly reduces reading time, claiming up to a 90% reduction, by answering questions directly from your documents. The platform supports various document formats, making it versatile for different types of content. Future integrations include GPT-4 for enhanced image understanding, further expanding its capabilities. This tool aims to simplify the process of extracting information and insights from extensive documentation, making it an efficient solution for research and information retrieval.

Trankit is a light-weight, transformer-based Python toolkit designed for multilingual Natural Language Processing (NLP). It offers a trainable pipeline for fundamental NLP tasks across more than 100 languages, and includes 90 downloadable pretrained pipelines for 56 languages. Trankit outperforms other state-of-the-art multilingual toolkits like Stanza in various tasks, including sentence segmentation and dependency parsing, while maintaining efficiency in memory usage and speed. Key features include an Auto Mode for automatic language detection, a command-line interface for ease of use, and support for tasks such as tokenization, part-of-speech tagging, morphological feature tagging, dependency parsing, and named entity recognition. It also allows users to build and share customized pipelines.

WideLabs specializes in delivering sovereign AI infrastructure tailored for businesses. The platform provides robust GPU cloud services, enabling companies to run demanding AI workloads efficiently. Beyond infrastructure, WideLabs also develops and integrates proprietary AI models, offering advanced capabilities for various business needs. Their end-to-end solutions ensure comprehensive support from deployment to ongoing management, addressing complex challenges in generative AI, computer vision, and predictive algorithms. WideLabs aims to create a significant impact on individuals, institutions, and companies by leveraging cutting-edge AI technologies.

🔬🧠GPT4O🖼️🎥 is a versatile AI chatbot available on Hugging Face that leverages GPT-4 to process and analyze various forms of input, including text, audio, images, and video files. Users can upload these different modalities and receive detailed responses, summaries, and analyses. Beyond its multimodal AI capabilities, the tool also integrates a feature for searching scholarly articles on ArXiv, making it useful for research and information retrieval. This application is designed to provide comprehensive insights across diverse data types.

Unsloth is an open-source platform designed for training and running a wide array of open models, including Gemma 4, Qwen3.5, DeepSeek, and gpt-oss, directly on local machines. It offers a user-friendly web UI, Unsloth Studio, for easy interaction, alongside a code-based version, Unsloth Core. The tool boasts significant performance improvements, enabling up to 2x faster training with up to 70% less VRAM, without compromising accuracy. It supports various model types including text, audio, embedding, and vision models, and provides features like model inference, export, tool calling, and code execution. Unsloth also includes advanced training capabilities such as reinforcement learning, custom Triton kernels, and data recipes for dataset creation from diverse file types.

UltraRAG is a lightweight RAG development framework based on the Model Context Protocol (MCP) architecture, designed for both research exploration and industrial prototyping. It standardizes core RAG components like Retriever and Generation as independent MCP Servers, allowing for precise orchestration of complex control structures such as conditional branches and loops through simple YAML configuration. The platform features a visual RAG Integrated Development Environment (IDE) with a Pipeline Builder that supports bidirectional real-time synchronization between canvas construction and code editing. This enables granular online adjustments of pipeline parameters and prompts, along with an Intelligent AI Assistant for structural design, parameter tuning, and prompt generation. UltraRAG aims to lower the barrier to entry for building RAG systems and accelerate deployment, offering one-click conversion of logic flows into interactive dialogue systems and integrated knowledge base management.

StoryChat.app is an AI conversational platform designed for users to engage with AI characters and develop their own unique AI personalities. The platform facilitates the creation and sharing of interactive stories, fostering a global community around AI-driven narratives. It provides a space for creative expression, allowing individuals to bring their imaginative concepts to life through AI. Users can explore a variety of AI characters, engage in dynamic conversations, and contribute to a growing library of shared stories. The tool focuses on accessibility and user-generated content within the realm of AI interaction.

ioPartners offers a platform where users can connect with 3D customizable AI partners. The service focuses on providing virtual AI companions that users can chat with, personalize, and interact with in various scenarios. This tool allows for a unique approach to AI companionship, enabling users to tailor their virtual partners to their preferences. The emphasis is on creating engaging and interactive experiences through customizable AI entities, fostering unique stories and conversations.

Everlyn AI is a platform designed to facilitate the creation of personalized AI tutors. Users can define specific learning objectives to generate AI tutors tailored to individual student needs. This makes it a valuable resource for teachers, parents, and tutors looking to enhance educational experiences. The platform supports automated assessment and feedback mechanisms, which can significantly streamline the grading process. Additionally, Everlyn AI promotes interactive learning through features like quizzes and tests, aiming to boost student engagement and comprehension. Its focus on customization and automated support makes it a versatile tool for various educational settings.