Trending Projects

Raptor is an AI-powered security agent that performs adversarial research and attack/defense operations.

WhisperX for fast ASR with word-level timestamps and diarization

Supercharge your large language models (LLMs) with the fastest key-value cache layer for lightning-fast inference.

Pioneering automated GUI interaction with native agents for AI-powered development workflows.

The simplest way to run the LLaMA language model on your local machine.

Optimized attention mechanism for deep learning

An open-source speech recognition toolkit used for building speech recognition systems.

A multi-voice text-to-speech (TTS) system with a focus on high-quality audio output.

PersonaLive! is a Python-based tool for creating expressive portrait image animations for live streaming.

MLX is a machine learning array framework for Apple silicon with Python, C++, and Swift APIs.

OpenCV is a comprehensive computer vision library for tasks like image processing and deep learning.

The ultimate toolkit for finetuning diffusion models, a key component of AI-powered coding tools.

955 不加班的公司名单 - 工作 955, work–life balance

OCR library with 80+ languages and scripts support

Industrial AI Agent platform for end-to-end film & video production with Hollywood-standard workflows

中文ChatGPT提示词指南，涵盖多种使用场景

Qwen-Image-Layered is a Python library for layered decomposition and inherent editability of images.

An AI-powered GitHub Action that analyzes code changes for security vulnerabilities using the Claude language model.

A comprehensive AI-powered platform for developers to discover, integrate, and manage various AI models and services.

Roadmap to becoming an Artificial Intelligence Expert in 2022

Nugget is a Python library that unlocks the full potential of your device with AI-powered tools and features.

A TypeScript plugin for monitoring Google Antigravity AI model quotas and usage.

A Python library for using and fine-tuning over 900 large language models and multimodal models for various AI tasks.

Python robotics algorithms and textbook for developers.

A puzzle-based learning resource for developers to explore CUDA and machine learning.

BabelDOC is a Python-based document translation tool that leverages AI to enable multilingual communication.

A comprehensive library for debugging, evaluating, and monitoring LLM applications, RAG systems, and agentic workflows.

This repository contains tutorials, assignments, and competitions for MIT's deep learning courses, covering a wide range of AI and machine learning topics.

A MATLAB library for deep photo style transfer, enabling developers to apply artistic styles to photos.

SAM 3D Objects is a Python library for detecting and segmenting 3D objects in point cloud data.

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

Barebones NumPy ML implementations for learning

Foundational models for state-of-the-art speech and text translation

EverMemOS is an open-source, enterprise-grade intelligent memory system for AI-powered conversational applications.

A collection of sample agents built with the Agent Development Kit (ADK) for building AI-powered applications.

A curated catalogue of awesome agentic AI patterns for developers building with AI tools.

AI-powered desktop client for multiple LLMs with local storage and cross-platform support

A media player for language learning with AI-powered features like dual subtitles, real-time translation, and more.

An open-source platform for building AI-powered applications and tools.

A Python framework for efficient model inference with omni-modality AI models.

FastAPI wrapper for Grok AI with streaming, image generation, and load balancing

Implementation of 17+ agentic architectures for practical use across AI system development.

StreamDiffusion is a Python library that provides a pipeline-level solution for real-time interactive generation.

Qwen3 is Alibaba Cloud's large language model series with enhanced reasoning and coding capabilities.

An open-source framework for building voice and multimodal conversational AI applications.

A comprehensive SDK for running frontier LLMs and VLMs on multiple hardware platforms with day-0 model support.

A powerful JavaScript tool for creating datasets for fine-tuning large language models (LLMs) and retrieval-augmented generation (RAG).

An AI-powered framework for Java developers to build intelligent, context-aware applications.

A powerful tool for easy and efficient video subtitling using large language models.

A curated collection of AI-powered apps, tools, and projects for developers working with large language models and AI agents.