Trending Projects

A Python package that provides advanced image background removal and object/face/clothes segmentation using multiple AI models.

verl-agent is a Python framework for training LLM/VLM agents using reinforcement learning.

An LLM-based multimodal agent framework designed to operate smartphone apps

A compact Python implementation of SGLang to demystify modern LLM serving systems.

One-click AI-powered short video creation and editing tool for product marketing and content

An open-source library for GPU-accelerated robot learning and sim-to-real transfer.

A fast offline inference version of the Segment Anything Model (SAM) for PyTorch developers.

A GUI-based smart Sudoku solver that can extract and solve Sudoku puzzles from photos using computer vision and machine learning.

A library for single- and multi-modal speaker verification, recognition, and diarization.

An open-source, tokenizer-free text-to-speech (TTS) model for context-aware speech generation and voice cloning.

A task-aware, agent-driven prompt optimization framework for prompt engineering and fine-tuning language models.

Comprehensive resources for developers working with Generative AI, including projects, use cases, and interview prep.

Absolute Zero Reasoner is a Python library for logical reasoning and inference on text data.

A privacy-focused middleware for AI-powered applications built on trusted execution environments like Intel SGX.

The Havoc Framework is a Go-based framework for building AI-powered applications and tools.

A Flutter-based LLM chat client with support for mobile and desktop platforms.

Spiking Brain-inspired Large Models with efficient attention, MoE, and spike encoding for AI and ML developers.

A library that reproduces the results of a paper on fixing train-test resolution discrepancy in computer vision models.

Voyager is an interactive RGBD video generation model that supports real-time 3D reconstruction from camera input.

A GitHub repository for a developer discovery platform focused on 'vibe coders' (developers who build with AI tools).

Concurrent chat with multiple AI language models like ChatGPT, Bing Chat, Bard, and more to discover the best answers.

A Python library for simple test-time scaling of machine learning models.

An AI-powered customer service tool that integrates with popular platforms like WeChat, Pinduoduo, and Douyin.

A Kotlin library that runs Stable Diffusion on Android devices with Snapdragon NPU acceleration.

Fast3R is a Python library for 3D reconstruction from a large number of images in a single forward pass.

A slimmed-down, fine-tuned fork of the oh-my-opencode project, optimized for efficient consumption of AI model tokens.

A powerful mixture-of-experts vision-language model for advanced multimodal understanding.

A simple Python implementation of a GRPO-like LLM for reproducing r1-like thinking.

An open-source toolkit for general OCR research and applications, with integrated training, evaluation, and production-ready OCR systems.

A JavaScript-based repository that helps developers learn and experiment with generative AI technologies.

Build AI-powered applications that can see, hear, and speak using screens, mics, and cameras.

This Python repository provides a whole body tracking solution for robotics and computer vision applications.

Instant AI Face Swap, a TypeScript library for developers to easily add AI-powered face swapping to their projects.

An AI-powered video clipping and highlight generation tool for creators and developers.

WebThinker is a powerful framework for building large language models with deep research capabilities.

A one-stop shop for building AI-powered products and businesses with Stripe's AI and MCP tools.

A starter agent that can solve a number of OpenAI Universe environments, useful for AI and ML developers.

An open-source project exploring advanced Retrieval-Augmented Generation systems with AI LLM agents.

Official Python bindings for llama.cpp and gpt4all, enabling use of large language models in Python projects.

All-in-one WebUI for AI generative image and video creation, captioning and processing

TimeGPT-1 is a production-ready pre-trained time series foundation model for forecasting and anomaly detection.

A lightweight and generalist NER model for extracting entities from text, with support for prompt-tuning.

A diffusion-based model for generating realistic talking portrait videos.

Access OpenAI models programmatically through your ChatGPT subscription.

A GPU-accelerated NumPy & SciPy library for high-performance scientific computing

A JavaScript library for animating 3D poses of human bodies using AI-powered algorithms.

Use Hugging Face, a leading AI platform, with JavaScript/TypeScript through a comprehensive API client.

A curated collection of the latest machine learning and AI courses on YouTube for developers.

Enchanted is an iOS and macOS app for chatting with private self-hosted language models like Llama2, Mistral or Vicuna using Ollama.

A Python and OpenCV-based scene cut/transition detection library for video processing.