Trending Projects

An open-source asynchronous coding agent built with TypeScript and AI tools for vibe coders.

An open-source platform for managing large language models, datasets, and agents with features similar to Hugging Face.

Material for lectures on GPU-accelerated computing, focused on AI and machine learning topics.

A Python library for web crawling and RAG capabilities for AI agents and AI coding assistants.

Quantized attention that achieves 2-5x speedup over FlashAttention for language, image, and video models.

A local, offline-first AI research and report writing assistant for developers building with AI tools.

A collection of image prompts for AI image generation tools like GPT-4o and Nanobanana.

Open standard for ML interoperability and model exchange

A Rust-based deep learning library that aims to achieve high performance and low latency for AI applications.

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

HunyuanVideo is a systematic framework for large-scale video generation using diffusion models and transformers.

A standard framework for modeling deep learning models for tabular data in PyTorch.

JavaScript OCR library for image text extraction

PartCrafter is a 3D mesh generation tool that uses compositional latent diffusion transformers to create structured 3D objects.

AxonHub is a Go-based AI gateway system that provides a unified API for OpenAI, Anthropic, Gemini, and other AI SDKs.

A collection of tutorials and notebooks on state-of-the-art computer vision models and techniques for developers.

Semantic search and document parsing tools for the command line, built with Rust.

An open-source implementation of the LoRA (Low-Rank Adaptation) technique for fine-tuning large language models.

A comprehensive collection of AI-powered tools, techniques, and resources for building advanced data-driven applications.

RF-DETR is a SOTA real-time object detection and segmentation model architecture designed for fine-tuning.

MAGI-1 is a powerful autoregressive model for generating high-quality video at scale, built for vibe coders who work with AI tools.

A text-to-SQL generation system powered by large language models and RAG, enabling intelligent data analysis through conversational queries.

Keras 3 is a multi-backend deep learning framework for building and training models with support for JAX, TensorFlow, PyTorch, and OpenVINO.

High-performance mobile-optimized neural network inference framework for deploying AI models on mobile devices

An open-source project that enables voice control for Xiaomi AI speakers, unlocking new possibilities for developers.

Reinforcement learning toolkit for developing and comparing algorithms.

Quark Agent is an AI-powered Android APK analyzer that helps developers and security researchers detect vulnerabilities in Android apps.

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit.

A practical guide for LLM engineers, covering fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices.

An official repository for the 'Mini-Gemini' model, a multi-modal vision-language model for generation tasks.

A comprehensive collection of deep learning tutorials, articles, and resources for developers.

Paper2Slides is a Python library that converts academic papers into presentation slides with one click.

Open platform for training, serving, and evaluating LLM chatbots with Vicuna and Chatbot Arena

Implements the 4 agentic patterns from scratch in a Jupyter Notebook for developers building with AI tools.

Open-source motion capture system using computer vision to track body movement and skeleton data.

GigaBrain-0 is a powerful AI model that enables vision-language-action capabilities for vibe coders.

Biomni is a general-purpose biomedical AI agent that can be used for a variety of tasks in the healthcare and life sciences domains.

A high-performance Python library for backtesting, algorithmic trading, and quantitative research.

An AI-powered platform for building machine learning models from natural language prompts.

Enterprise-grade agentic workflow platform for building next-generation SuperAgents with AI and low-code tooling.

A collection of reusable Python modules for building AI-powered applications and tools.

Curated list of open source libraries for deploying, monitoring, and scaling machine learning in production

LimiX is a Python library that enables structured-data modeling capability for generalist intelligence.

Opiniated RAG for GenAI integration in apps

A Python library for fine-tuning stable diffusion models for text-to-image generation.

统计学习方法代码实现

A comprehensive guide and resources for developing AI agents and working with large language models (LLMs).

Flutter development tools for vibe coders

A high-performance 3D rendering library for ray tracing and hybrid rasterization of Gaussian particles.

An open-source browser agent that autonomously performs complex web tasks using state-of-the-art AI tools.