Trending Projects

2D/3D face analysis with AI

An Android automation tool based on vision-language models that allows developers to automate mobile app interactions.

A learning platform that leverages LLMs to assist students, scholars, and lifelong learners.

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

A real-time motion tracking addon for Blender using MediaPipe and Rigify.

Silero VAD is a pre-trained enterprise-grade Voice Activity Detector library for Python.

High-performance ML inferencing and training accelerator

A fast, integrated AI Gateway to route to 200+ LLMs and 50+ AI Guardrails with a friendly API.

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

A minimal yet professional single agent demo project showcasing the core execution pipeline and production-grade features of AI agents.

A deep dive into the fundamentals of embeddings, a powerful machine learning technique for NLP.

An open-source library for estimating optical flow, a fundamental computer vision task, using deep neural networks.

A state-of-the-art 3D reconstruction tool using diffusion models for high-quality 3D reconstructions.

JAX is a high-performance numerical computing library for Python, enabling transformations like differentiation and JIT compilation for GPUs/TPUs.

Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents.

An intelligent Xianyu (Chinese e-commerce platform) customer service chatbot powered by AI and LLMs.

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

Triton is a development repository for a domain-specific programming language and compiler focused on machine learning and AI workloads.

Implementation of a real-time audio-driven avatar generation system for vibe coders.

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

A modern, cross-platform, and free AI RSS reader built with Go.

A customizable, multi-modal AI chatbot that can be integrated with various chat platforms and leverages LLMs like ChatGPT, Bard, and GPT-3.

Instant voice cloning model with tone color cloning and multi-lingual support

Open-source notebooks for music information retrieval research and education.

A chatbot that allows you to chat with and extract information from PDF documents using language models and AI.

Code for a model that learns to summarize text from human feedback, useful for AI-powered summarization.

This Python-based suite of tools allows developers to interact with AI services directly from their terminal.

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

Latent text-to-image diffusion model for generating images from text prompts

A repository for running inference with the Meta Segment Anything Model 2 (SAM 2) and example notebooks.

Bend is a massively parallel, high-level programming language written in Rust for building AI-powered applications.

PentestAgent is an AI-powered framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

A collection of Jupyter Notebook tutorials for accelerated tabular data machine learning in Python.

A fast BPE tokenizer for use with OpenAI's language models in Python.

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

A flexible and fast reinforcement learning library for building LLM-powered agents and reasoning systems.

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

A curated list of gradient boosting research papers with implementations in Python.

YOLOv5 is a state-of-the-art computer vision model for object detection, segmentation, and classification.

A minimal solution for high-speed hand motion capture from a single color camera.

OpenAI's open-weight language models for powerful reasoning and agentic tasks.

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

A programming language with static memory management based on λ-calculus for vibe coders.

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

Interactive deep learning book with code and math

A curated list of awesome works in world modeling, serving as a resource for researchers and practitioners.

Effortless data labeling with AI support from Segment Anything and other powerful models.

An AI-powered tool for removing hard-coded subtitles and text-like watermarks from videos or pictures, with no need for third-party APIs.

Offline AI image generation with minimal user input

Materials for learning PyTorch, a deep learning framework, from zero to mastery.