Trending Projects

A powerful agent framework for building open-source AI-powered applications and tools.

A comprehensive list of papers on World Models, a technique for general video generation, embodied AI, and autonomous driving.

AI-powered ID photo generation with face detection and matting

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

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

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

A TypeScript-based financial agent for investment research and analysis.

A scalable toolkit for efficient model reinforcement learning in Python.

Zipline is a Pythonic algorithmic trading library for backtesting and live trading.

This repository contains the book 'Large Language Models' authored by a team of researchers.

A handbook for beginners on writing AI conference papers, useful for vibe coders working with AI tools.

A real-time object detection model that leverages the DINO transformer for efficient and accurate object recognition.

A Telegram-based support system that uses AI to help users and generate responses for operators.

Sealos is an AI-native Cloud Operating System that unifies the entire application lifecycle for building and scaling modern AI applications.

A tutorial on deep learning by renowned professor Li Hongy, covering a wide range of AI and machine learning topics.

Open-source offline translation library written in Python, supporting multiple language models and formats.

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

A high-quality voice conversion tool focused on ease of use and performance for AI-powered audio applications.

A secure and interoperable platform for AI-driven payments, catering to the needs of vibe coders.

This C++ framework provides a powerful and flexible command-and-control (C2) infrastructure for developers building AI-powered applications.

A community-maintained hardware plugin for running large language models (LLMs) on Ascend accelerators.

LiteRT is Google's on-device framework for high-performance ML & GenAI deployment on edge platforms.

SHAP explains ML model outputs using Shapley values for interpretability.

Graph Neural Network library for PyTorch

AI-powered dataset management and preprocessing library for ML projects

A robust, efficient, and low-latency speech-to-text library with advanced voice activity detection and wake word activation.

An open-source SDK for working with quantum computers at the level of quantum circuits, operators, and primitives.

A Python library for solving and discovering nonlinear partial differential equations using physics-informed neural networks.

A Python-based tool that generates high-fidelity 3D assets from images with production-ready PBR materials.

A curated list of papers and resources on large language model (LLM) agents, covering methodologies, applications, and challenges.

A benchmark for evaluating knowledge transfer in lifelong robot learning using AI tools.

Configure and deploy autonomous AI agents in browser

Access OpenAI models programmatically through your ChatGPT subscription.

An enterprise-grade, API-first LLM workspace for unstructured document processing, with features like data extraction, redaction, and prompt engineering.

Refine high-quality datasets and visual AI models with this Python library for active learning and data curation.

A multiagent persona simulation tool powered by large language models for business insights and imagination enhancement.

A Go-based multi-channel AI proxy with intelligent key rotation for vibe coders using AI tools

High-performance data engine for AI and multimodal workloads, processing images, audio, video, and structured data at scale.

VeOmni is a scalable distributed training framework for multi-modal AI models, focused on vibe coders.

Curated list of top machine learning Python libraries, updated weekly with quality scores.

An open-source library for hybrid spectrogram and waveform source separation, useful for audio processing tasks.

A tiny vision language model for developers building AI-powered applications.

An open-source Python tool to transform multimodal content into captivating multilingual audio podcasts powered by GenAI.

A suite of tools to develop RAG, semantic search, and other AI apps more easily with PostgreSQL

An open-source GPU-accelerated robotics simulator and benchmark for manipulation skill learning.

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

Provides TypeScript access to Anthropic's safety-first language model APIs for building AI-powered applications.

WeChat message archiver with AI integration

CUDA on non-NVIDIA GPUs, a Rust library for utilizing CUDA on a variety of GPU architectures.

A cross-platform image super-resolution tool built with TypeScript, Vue3, and PyTorch.