Trending Projects

A conversational speech generation model for developers building AI-powered applications.

A high-performance multi-object tracking library for real-time computer vision applications.

Deep learning library for fast and easy model building

Bullet Physics SDK is a real-time collision detection and multi-physics simulation library for VR, games, robotics and more.

Zero-shot identity-preserving text generation in seconds for vibe coders.

Translation of deep learning research papers, including classification and detection papers.

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

A comprehensive collection of resources and tutorials for building AI infrastructure and systems.

LocalGPT enables private document interaction with GPT models on your device.

A set of Jupyter Notebooks that combine Grounding DINO, Segment Anything, and Stable Diffusion for automatic detection, segmentation, and generation of anything in images.

A high-performance latent diffusion model for generating high-resolution images.

An official PyTorch implementation of the StarGAN image-to-image translation model from CVPR 2018.

This repository provides an AI-powered toolkit for developing applications with the Rockchip RKNN inference engine.

A framework for building resilient language agents as graphs using TypeScript and AI tools.

A PyTorch implementation of Stable Diffusion, a powerful AI-powered text-to-image generation model.

A machine learning toolkit for time series analysis and classification in Python.

Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, and other optimization algorithms for Python

A machine learning package built to make AI-powered development more accessible for developers.

A lightweight and generalist NER model for extracting entities from text, with support for prompt-tuning.

A Python-based assistant for reverse engineering and exploring the 1999 time period.

An official implementation of DanceGRPO, a visual generation model that leverages GRPO techniques.

A single-file C implementation of Llama 2 for efficient large language model inference

Open-source IM server that supports ChatGPT and other AI chatbots for building messaging apps and platforms.

Access OpenAI models programmatically through your ChatGPT subscription.

FoundationPose is a unified 6D pose estimation and tracking framework for novel objects, useful for computer vision applications.

A minimal TypeScript plugin that allows developers using the Claude AI assistant to receive phone calls.

A CLI text-to-speech tool using the Kokoro model, supporting multiple languages and input formats.

Deep learning library in JavaScript that allows training convolutional neural networks in the browser

Ultra-efficient large language models (LLMs) for end devices, enabling fast on-device reasoning and inference.

A library of tile primitives for building speedy CUDA kernels, useful for vibe coders working on AI tools.

PyTorch implementation of CycleGAN and pix2pix for image-to-image translation

A deep reinforcement learning library for the Keras deep learning framework, enabling AI-powered applications.

A library for creating lip-synced videos using Stable Diffusion, focused on research and virtual avatars.

A PyTorch implementation of BigGAN with pretrained weights and conversion scripts for generative AI models.

Simple Pytorch implementation of OpenAI's GPT-2 language model for text generation.

A library of deep learning models and datasets to make deep learning more accessible and accelerate ML research.

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

A Python wrapper for the MuJoCo physics engine, enabling detailed rigid body simulations with contacts.

A fast and efficient ONNX model inference and training library for Rust developers working with AI.

Dramatron is a Jupyter Notebook tool that uses large language models to generate coherent scripts and screenplays.

An official implementation of the Swin Transformer, a hierarchical vision transformer for image classification and segmentation.

Python bindings for the llama.cpp library, enabling developers to use LLMs in their Python projects.

Unofficial API wrapper for Perplexity.ai with a web interface for generating Perplexity AI accounts

A curated list of awesome papers and code for optimizing LLM/VLM inference performance

Repository of code samples for the book 'Neural Networks and Deep Learning' focused on machine learning.

Open-source observability tool for GenAI and LLM applications, based on OpenTelemetry

docTR is a high-performing and accessible library for OCR-related tasks powered by deep learning.

This is a PyTorch implementation of Cross-lingual Language Model Pretraining, a research project focused on multilingual NLP.

A trainable PyTorch reproduction of the AlphaFold 3 protein structure prediction model.

DeepSeek-Math-V2 is a Python library for AI-powered math analysis and computation.