Trending Projects

Simple, hackable offline speech-to-text tool using the VOSK-API, useful for vibe coders building AI apps.

A minimal yet professional single agent demo project showcasing the core execution pipeline and production-grade features of AI agents.

A comprehensive collection of research on knowledge graphs, covering various applications and techniques.

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

Caption-Anything is a versatile AI-powered tool for generating tailored image captions with diverse controls.

Practical course on using Large Language Models (LLMs) with tools like LangChain, HuggingFace, and PEFT.

This repository provides Jupyter Notebook examples to try out deep learning models online using Google Colab.

A fast and efficient implementation of the WaveNet model for speech synthesis in Python.

A curated list of resources for transfer learning and domain adaptation research and applications.

Microsoft.Recognizers.Text is a library for recognizing and resolving numbers, units, date/time in multiple languages.

Versatile audio super resolution tool that can upscale audio to 48kHz using AI.

Large-scale linear classification, regression, and ranking library for Python developers.

PyTorch implementation of the PointNet2/PointNet++ architecture for processing point cloud data.

A PyTorch-based implementation of the Faster R-CNN object detection algorithm.

An open-source tool for extending the capabilities of the Automatic1111 AI model training platform.

An open-source library for building generative multimodal AI models, with a focus on foundation models, in-context learning, and multimodal pretraining.

This is a Python implementation of the YOLO (You Only Look Once) object detection algorithm.

A Python tool that allows users to edit images generated by the Stable Diffusion AI model

A collection of prompts for using Large Language Models (LLMs) like ChatGPT to assist with various coding tasks.

A collection of awesome and classical papers on content-based image retrieval (CBIR) and visual search.

A collection of resources for few-shot learning (FSL) in Python, useful for vibe coders building AI-powered applications.

A C++ library for GPU computing patterns and behaviors, suitable for high-performance computing applications.

zetane/viewer is a Python-based 3D visualizer for ML models and internal tensors.

A Python library for interpretability and explainability of data and machine learning models.

A domain-specific language for expressing machine learning workloads, useful for vibe coders building with AI tools.

A repository hosting code for a state-of-the-art generative recommender system for AI-powered developer tools.

A compiler infrastructure for Multi-Level Intermediate Representation (MLIR) used in machine learning and other domains.

Flexible and AI-assisted Node.js crawler library for building web scrapers and crawlers.

A TypeScript-based workflow DevKit for building durable, reliable, and observable apps and AI agents.

A package for the sparse identification of nonlinear dynamical systems from data

Fast Transformers is a PyTorch library for efficient implementation of transformer models.

A free and open-source speech synthesizer for Russian and other languages, supporting various platforms.

A powerful video enhancement tool that uses AI to interpolate, upscale, decompress, and denoise videos on multiple platforms.

A Kotlin library that runs Stable Diffusion on Android devices with Snapdragon NPU acceleration.

A free, open-source browser extension to filter NSFW content using TypeScript and TensorFlow.js.

A curated collection of articles and resources on search, recommendation, and natural language processing.

An artificial intelligence-powered implementation of the classic Snake game.

This GitHub repository hosts the open-source organization ApacheCN, which focuses on AI, ML, and data science tools and resources.

NeuS is a Python library for neural surface reconstruction, a key component in 3D computer vision.

A project demonstrating GPU-accelerated AI solutions for Lidar and camera data processing.

A dataset of Linus Torvalds' rants classified by negativity using sentiment analysis.

Command line tool for forced alignment using the Kaldi speech recognition toolkit.

An MXNet implementation of Mask R-CNN, a deep learning object detection and segmentation algorithm.

A powerful vision-language pre-training method for tasks like image-text retrieval and captioning.

A platform for experimenting and researching the interaction of automated agents in simulated network environments.

A state-of-the-art conversational AI library using transfer learning and GPT-2 models.

This repository contains materials, slides, and notebooks for Andrew Ng's deeplearning.ai course on machine learning and AI.

A curated collection of top 200 deep learning GitHub repositories sorted by stars for AI developers.

Pixel2Mesh is a Python library for generating 3D mesh models from single RGB images.

A PyTorch implementation of a paper on artistic style transfer for videos.