Trending Projects

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

Open-source library for training and running inference with ColVision models for vision-language retrieval and generation.

An open-source audio wake word detection framework with a focus on performance and simplicity.

A secure low-code honeypot framework that leverages AI for system virtualization and preemptive cybersecurity.

A TypeScript framework for building AI-powered applications and workflows using a modular, agent-based architecture.

Zero-shot vulnerability discovery using large language models (LLMs) for security researchers.

Kimi-VL is a multimodal AI model for advanced vision-language understanding and reasoning.

An AI-powered anime super-resolution tool built for developers who work with computer vision models.

A Python library for learning and using OpenCV, a popular computer vision library.

TerraBrush is a C++ library for procedural terrain generation, providing tools for vibe coders to create dynamic and realistic environments.

Pointcept is a codebase for point cloud perception research, featuring the latest works on 3D computer vision.

A Python-based library for generating videos from code, focused on the vibe coding and AI tools ecosystem.

Distributed deep learning on Hadoop and Spark clusters for vibe coders.

A unified framework for text-to-3D and image-to-3D generation powered by Tencent's Hunyuan3D technology.

Offline speech recognition for Android using the Vosk library, a popular open-source speech recognition toolkit.

Minimal, clean Python implementation of the Byte Pair Encoding (BPE) algorithm for tokenization in LLMs.

An AI-powered research assistant that performs deep research on any topic by combining search, scraping, and language models.

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

VADER is a Python library for sentiment analysis, especially suited for social media text.

HolmesGPT is an AI agent that helps SREs and DevOps teams solve incidents faster with automatic correlations, investigations, and more.

A comprehensive collection of resources to learn the essential mathematics for machine learning.

Collection of generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

A library for using large and small language models together in machine learning applications.

Lightweight PyTorch models for real-time semantic segmentation on computer vision tasks.

Chunkr is a Rust-based vision infrastructure for turning complex documents into RAG/LLM-ready data.

UNO is a universal customization method for both single and multi-subject image generation using diffusion models.

An open-source library that simplifies the use of Retrieval-Augmented Generation (RAG) with small language models.

A Rust-based AI agent framework for creating AI-powered creative assistants and tools.

Open-source machine learning library in Python with implementations of popular algorithms like kNN, decision trees, and SVM.

A deep reinforcement learning tool that instrumentizes bettercap for WiFi pwning and handshake collection.

A comprehensive Ruby API for integrating with various AI tools and platforms, including OpenAI, Anthropic, Gemini, and more.

A web-based audio transcription and translation tool powered by Whisper AI models, built with Svelte.

PaddleX is an all-in-one development tool based on PaddlePaddle, providing AI pipelines for computer vision, NLP, and more.

An open-source successor to UTAU, a platform for singing voice synthesis and audio production.

LAVIS is a comprehensive library for multimodal deep learning, including image captioning, visual question answering, and more.

This project aims to speed up large language model (LLM) inference and enhance their understanding of key information through prompt and KV-Cache compression.

A simple Java library for working with images, focused on developers who use AI tools.

A Jupyter Notebook library for building Kolmogorov Arnold Networks, a type of neural network.

A sample app for the Retrieval-Augmented Generation pattern using Azure AI Search and Azure OpenAI large language models.

A Python library for scientific machine learning and physics-informed learning

A framework to enable multimodal AI models to control a computer, automating various tasks.

An optimized library for efficient multi-GPU communication in deep learning applications.

An open-source API management and distribution system that supports multiple AI models, including OpenAI.

A community-driven platform that transforms study materials into interactive resources like quizzes, flashcards, notes, and podcasts.

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

A private & local AI personal knowledge management app for high entropy people with a focus on vibe coders.

Chinese version of CLIP for cross-modal retrieval and representation generation

A library for developing neural operators using Fourier methods and PyTorch, enabling efficient learning on infinite dimensional spaces.

A TypeScript-based platform that aggregates various LLM APIs into a single hub for easy access and integration.

A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration.