Trending Projects

A machine learning compiler for GPUs, CPUs, and ML accelerators, useful for building AI-powered applications.

A reliable multi-agent orchestration framework for building complex distributed systems and applications.

A flexible and fast reinforcement learning library for building LLM-powered agents and reasoning systems.

A unified and scalable ML library for large-scale distributed training, model serving, and federated learning.

A collection of loss functions for medical image segmentation in Python.

A state-of-the-art LLM that converts natural language queries to SQL, enabling vibe coders to work more efficiently.

A GitHub repository for a developer discovery platform focused on 'vibe coders' (developers who build with AI tools).

Scalable neural forecasting algorithms for time-series data, with support for various deep learning models.

A JavaScript library that uses machine learning (neuroevolution) to learn how to play the Flappy Bird game.

A PoC for a technique to recover plaintext from pixelized screenshots.

Official TensorFlow implementation for a CVPR2020 paper on learning to cartoonize images.

A real-time state-of-the-art speech synthesis library for TensorFlow 2, supporting multiple languages.

A curated list of responsible machine learning resources for interpretable AI development.

Positron is a next-generation data science IDE that provides a comprehensive set of tools and features for vibe coders.

A differentiable architecture search library for convolutional and recurrent neural networks

A curated list of action recognition and related area resources for developers working with computer vision and video processing.

Efficient 3D human pose estimation in video using 2D keypoint trajectories.

Evolutionary Scale Modeling (ESM): Pretrained language models for proteins in Python.

Jupyter Notebook project to build large language models from scratch using Python, including GLM4, Llama3, and RWKV6.

A Chinese NLP library for tokenization, part-of-speech tagging, named entity recognition, and lexical analysis.

Official implementation of a paper on multimodal chain-of-thought reasoning in language models.

Deepchecks is an open-source solution for thorough testing of ML models and data from research to production.

A PDF toolbox for Anki that helps developers efficiently convert knowledge from various sources into flashcards.

A pre-trained ALBERT model for self-supervised learning of Chinese language representations.

A Python library for easy and robust visual localization using deep learning and feature matching.

A comprehensive collection of tutorials and resources for AI, deep learning, and machine learning in Python.

Simple PyTorch tutorial repository for learning deep learning from the basics to advanced topics.

A collection of example workflows for the ComfyUI AI tool, which allows developers to create custom AI models and applications.

Stay on top of trending topics on social media and the web with AI-powered topic discovery.

Tensor-Puzzles is a collection of PyTorch-based puzzles to help developers improve their machine learning skills.

A PyTorch implementation of the SuperGlue graph neural network for feature matching and pose estimation.

Snips NLU is a Python library for extracting meaning from text using natural language processing and machine learning.

A Jupyter Notebook project that helps developers label their own data and train custom AI models.

Learning embeddings for classification, retrieval and ranking.

A spreadsheet tool with AI capabilities for data analysis, engineering, and visualization.

Motion is a software motion detector, a useful tool for developers working on computer vision projects.

oneAPI Deep Neural Network Library (oneDNN) is a high-performance, open-source, and cross-platform math library for deep learning applications.

RAFT is a PyTorch library for training and evaluating visual transformers, a popular AI model for computer vision tasks.

A versatile AI assistant desktop app that can query and generate content across multiple AI models.

An open-source toolkit for speech processing, supporting enhancement, separation, and target speaker extraction.

A very low-bitrate speech codec for efficient audio compression, useful for various applications.

A lightweight C++ library for portable low-level GPU computation using WebGPU.

A Python library that solves the Traveling Salesman Problem using Self-Organizing Maps.

An end-to-end multimodal AI model that can understand and generate text, audio, vision, and video in real-time.

Deep neural networks for voice conversion (voice style transfer) in Tensorflow

Turn any glasses into AI-powered smart glasses with this open-source hardware project.

Open-source C++ library for fast, approximate nearest-neighbor search and clustering of vectors and objects

A library of reinforcement learning components and agents for AI and machine learning research.

A Python library for reinforcement learning tuning of large language model agents.

LightLLM is a high-performance, scalable Python-based framework for inference and serving of large language models.