Trending Projects

Baseline systems for the DuReader dataset, a Chinese machine reading comprehension dataset.

A text-to-video generation model that combines pixel-level and latent diffusion approaches.

ONNXMLTools enables conversion of machine learning models to the ONNX format, supporting Keras, Scikit-learn, and other frameworks.

A curated list of resources for building multi-modal GUI agents using large language models.

An open-source platform for creative visual effects and media generation using AI tools

A curated list of resources for image captioning and related areas, useful for developers working on AI projects.

A Java library that provides a high-level API to access computer vision and multimedia functionality from OpenCV, FFmpeg, and other libraries.

A set of tools to help developers inter-operate between different deep learning frameworks like Caffe, Keras, TensorFlow, and PyTorch.

An open-source project that allows developers to train their own O1 preview models for AI-powered coding assistance.

Open-source tools for prompt testing and experimentation with LLMs and vector databases.

A Python library that uses Tensorflow and convolutional neural networks to recognize character-based image captchas.

A Chrome extension that uses Meta's Segment Anything Model to extract and copy objects from images.

AingDesk is a simple and feature-rich AI assistant that supports knowledge bases, model APIs, sharing, search, and intelligent agents.

A JavaScript library for detecting nudity in images using HTML Canvas.

Fully open data curation for reasoning models for vibe coders building with AI tools.

A fractal graph-of-thought tool for AI agents, web links, notes, and code that enables rhizomatic mind-mapping and second brain workflows.

Open-source library for detecting 20,000+ classes using image-level supervision, useful for computer vision applications.

A reinforcement learning agent trained in a diffusion world model for AI research and development.

SAM is a PyTorch-based library that implements Sharpness-Aware Minimization, an optimization algorithm for training more robust deep learning models.

LAPACK is a comprehensive library for linear algebra computations including matrix factorizations.

A dataset of worldwide building footprints derived from satellite imagery for geospatial and computer vision applications.

This GitHub repository contains notes on the Deep Learning book, a valuable resource for developers interested in AI and machine learning.

A deep learning-powered library for detecting and recognizing Chinese license plates, including support for 12 different plate types.

A multi-threaded GOAP system for Unity game development, with support for AI-powered agents and behaviors.

An open-source e-book on building applications with large language models (LLMs), including prompt engineering, architecture design, and more.

A curated list of Tiny Object Detection papers and related resources for developers working with AI-powered computer vision.

A Python library for training and detecting objects using the YOLO3 deep learning algorithm.

A Python library for generating physically stable 3D toy brick models from text prompts.

An open-source library for research on learning disentangled representations.

An image super-resolution library that uses diffusion inversion to enable arbitrary-steps upscaling.

PALLAIDIUM is an AI-powered movie studio seamlessly integrated into the Blender Video Editor, enabling end-to-end production from script to screen.

Official implementation of a generative motion modeling framework for 3D human motions.

A high-quality lip sync tool using deep learning techniques like GFPGAN and Wav2Lip.

An AI chatbot for small and medium-sized teams, supporting popular AI models like Deepseek, OpenAI, and Claude.

A higher-level neural network library for microcontrollers and embedded systems.

A Jupyter Notebook repository for materials discovery, likely focused on AI and machine learning

Teach-Repeat-Replan is a complete and robust system for aggressive flight in complex environments using autonomous drones.

MyoSuite is a collection of environments/tasks for musculoskeletal models simulated with MuJoCo and wrapped in OpenAI gym.

DataDreamer is a Python library for generating synthetic data, fine-tuning and aligning large language models.

Open-source digital stylus using camera tracking and inertial measurements for vibe coders.

A bottom-up object detection algorithm that groups extreme and center points to detect objects.

Efficient implementations of Native Sparse Attention, a key component in large language models.

A plugin to enhance the data security and efficiency of ChatGPT, providing innovative features like auto-refresh, session preservation, and data sanitization.

Yao is an open-source engine for autonomous agents, enabling event-driven, proactive, and self-scheduling AI applications.

A fast, header-only C++ machine learning library for developers building AI-powered applications.

A Python library for generating 3D models from a single input image using cross-domain diffusion models.

A comprehensive collection of resources for researchers and developers in the Kolmogorov-Arnold Network field.

An open-source platform for building data-driven applications and AI-powered solutions with a focus on vibe coders.

A deep learning-based recommender system for developers working with AI tools and frameworks.

An open-source implementation of the 'Graph of Thoughts' technique for solving complex problems with large language models.