Trending Projects

PointNet is a deep learning model for 3D classification and segmentation on point cloud data.

A high-performance machine learning library for CUDA-enabled GPUs, accelerating data science workflows.

A deep learning-based library for person re-identification in PyTorch.

DiffSinger is a singing voice synthesis system using a shallow diffusion mechanism, enabling efficient TTS and SVS.

PyTorch implementation of PointNet and PointNet++ for 3D point cloud classification and segmentation.

An open platform for building and deploying language agents powered by large language models.

A fast C++/CUDA neural network framework for high-performance deep learning and rendering.

Easily convert large sets of image URLs into a dataset for AI/ML training and experimentation.

A fast, multimodal LLM for real-time voice applications and AI-powered speech tools.

Materials for the Hugging Face Diffusion Models Course, a resource for learning about diffusion models in AI.

Easiest way to build multi-agent LLM applications for vibe coders using Python and LangChain.

An open-source cookbook for getting started with Phi, a family of high-performance small language models from Microsoft.

A thorough PyTorch tutorial for developers to learn and master the deep learning framework

An IDA plugin that uses language models to speed up reverse-engineering tasks for developers.

Clean, robust, and unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms.

A light-hearted yet rigorous approach to learning about impact estimation and causality in Python.

Minimal implementations of basic reinforcement learning algorithms in PyTorch for educational purposes.

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

A GUI for the faster-whisper library, which enables fast, open-source speech transcription using OpenAI's Whisper model.

Native multimodal model for high-quality image generation with text-to-image capabilities

An open-source library for local feature matching using Transformers, useful for 3D vision and pose estimation tasks.

An AI-powered tool for training supervised models without manual labeling, using foundation models and multimodal learning.

Blazing-fast GPU compute framework built on Vulkan for advanced data processing use cases.

A fast Rust-based tool to serialize text-based files for LLM consumption

Efficient neural feature detector and descriptor for computer vision tasks.

TokenOps provides easy token price estimates for over 400 large language models (LLMs).

A curated collection of must-read papers and blogs on large language model-based long-context modeling.

This is the official implementation of Multi-Agent PPO (MAPPO), a reinforcement learning algorithm for multi-agent environments.

A Python library for deep and online learning with spiking neural networks (SNNs) using PyTorch.

A curated reading list for security, safety, and privacy of large language models (LLMs) and AI systems.

A Python library that provides type annotations and runtime checking for JAX/NumPy/PyTorch arrays.

Generate animated math/physics visualizations & study notes from text/images using Manim

A Rust library for running customized and fine-tuned large language models (LLMs) locally or on the edge.

BrainFlow is a library for obtaining, parsing and analyzing data from various biosensors like EEG, EMG, ECG.

MultiAgentPPT is an AI-powered presentation generation system that leverages multi-agent collaboration and streaming concurrency.

A comprehensive PHP Generative AI Framework using OpenAI GPT 4, inspired by Langchain.

A collection of must-read papers on Physics-Informed Neural Networks (PINNs), a powerful approach for solving differential equations.

An open-source, multi-tenant, self-building knowledge graph for developers building with AI tools.

A Python re-implementation of the pi0 vision-language-action (VLA) model for developers working with AI tools.

A large and diverse 3D human motion-language dataset for deep learning and motion generation.

Automated Time Series Forecasting library for Python with advanced features like deep learning and feature engineering.

FireRedTTS2 is a long-form streaming TTS system for generating multi-speaker dialogue in Python.

A C++ library for learning safe flight in dynamic environments using reinforcement learning and the NVIDIA Isaac Sim.

A curated list of resources on large language model-based text-to-SQL for developer productivity and database access.

A high-performance image synthesis model with improved distribution matching distillation.

A TypeScript tool to get article summaries and bypass paywalls, powered by AI and next-gen web frameworks.

A tutorial to build a RAG (Retrieval Augmented Generation) system from scratch using local LLMs and no black boxes.

A Spark accelerator for Apache DataFusion, a SQL query engine written in Rust, aimed at vibe coders.

A library for universal monocular metric depth estimation using computer vision techniques.

Hephaestus is a semi-structured, agentic framework that allows workflows to build themselves as agents discover what needs to be done.