Trending Projects

An open-source on-device speech recognition library for Apple Silicon devices, built with Swift and Transformers.

A multimodal evaluation toolkit for assessing AI models across text, image, video, and audio tasks.

DORA is middleware for creating AI-powered robotic applications with low latency, composable, and distributed dataflow capabilities.

DeepSpeed optimizes deep learning training and inference with distributed computing techniques.

A curated list of modern Generative AI projects and services for developers building AI-powered applications.

A curated collection of prompts and examples for mastering the Nano Banana Pro AI image model.

An open-source Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Unlimited-length talking video generation that supports image-to-video and video-to-video generation

Real-time AI assistant for Ray-Ban smart glasses using vision, voice, and agentic actions via Gemini Live.

A robotics simulation platform for training generalist robots on everyday tasks.

Practical image/video restoration with Real-ESRGAN for developers

FaceFusion is an industry-leading face manipulation platform for deepfake and face-swapping tasks.

A general-purpose physics simulator for robotics and dynamic simulation.

An open source SDK for logging, storing, querying, and visualizing multimodal and multi-rate data.

A curated list of machine learning techniques and resources for cybersecurity professionals.

An open-source deep research agent optimized for research and prediction with state-of-the-art AI capabilities.

This is a stock prediction AI project that uses a GAN with LSTM and CNN to forecast stock price movements.

Real-time voice cloning using deep learning

Graph Neural Network library for PyTorch

LLM入门教程，基于吴恩达课程的中文版实践指南

Conversational data analysis with LLMs using natural language queries on databases, CSVs, and data lakes.

Curated list of Chinese open-source LLMs, including base models, fine-tuning, and applications

A TypeScript library for building context-aware reasoning applications using large language models.

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

An AI-powered personalized learning assistant that leverages large language models and multi-agent systems.

LeetCUDA is a comprehensive collection of modern CUDA learning resources, including 200+ CUDA kernels, Tensor Cores, HGEMM, and FA-2 MMA.

A local-first AI coworker with memory, helping developers build with AI tools and agents.

NarratoAI is a Python-based tool that uses AI models to automatically provide commentary and edit videos with a single click.

Data transformation framework for AI with ultra-fast, incremental processing capabilities.

This repository allows developers to train their own medical language models using the ChatGPT training pipeline.

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

GLM-5 LLM framework enabling agentic AI development and autonomous coding workflows

State-of-the-art diffusion models for image, audio, and video generation in PyTorch.

FishAudio-S1 is a high-quality open-source TTS model with voice cloning capabilities.

CAMEL is a multi-agent framework for exploring the scaling law of artificial intelligence agents.

Resources for AI engineers, including supporting materials for the book 'AI Engineering' (2025)

DiffSynth-Studio is a Python library that allows developers to enjoy the magic of Diffusion models.

A WeChat bot powered by AI services like ChatGPT, Claude, and Kimi to automate various messaging tasks.

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

A Python framework for building AI security tools and conducting cybersecurity pentesting with AI.

Efficient implementations of state-of-the-art linear attention models for large language models and NLP tasks.

AI-powered web scraping and data gathering SDK for building intelligent agents and LLM apps

An event-driven framework for building and orchestrating multi-agent AI systems with real-world data integration.

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

A machine learning-based video upscaling and frame interpolation framework for developers working with AI tools.

Train transformer language models with reinforcement learning using a Python library.

A Python library that translates videos from one language to another, with support for dubbing and subtitles.

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

An open-source AI avatar toolkit for offline video generation and digital human cloning.

This GitHub repository provides a jailbreak for the ChatGPT model, allowing developers to bypass OpenAI's content restrictions.