Trending Projects

AI-powered browser automation for workflows

This repository contains lecture materials for a course on deep learning and natural language processing from the University of Oxford.

Caffe2 is a lightweight, scalable deep learning framework for building and deploying AI models.

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

A Python library that uses deep learning to enhance the resolution of images.

OWL is an AI-powered task automation framework for building multi-agent systems to assist developers.

A comprehensive speech recognition toolkit with state-of-the-art pretrained models for various speech tasks.

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

An AI-powered quantitative investment research platform for algorithmic trading and backtesting.

An open-source Python tool that uses AI to remove backgrounds from images and videos with a simple command line interface.

DeepFace is a lightweight Python library for face recognition and facial attribute analysis, including age, gender, emotion, and race detection.

A powerful Python framework for building real-time voice AI agents powered by OpenAI and other AI tools.

An open-source, multilingual code generation model for AI-powered coding tools and developers.

OptiScaler bridges upscaling/frame gen across GPUs, supporting DLSS2+, XeSS, FSR2+ and more.

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

A demo project that showcases building a conversation-based search experience with the Lepton AI platform.

A repository for a course on mastering large language model (LLM) engineering for AI-powered coding tools.

Tool to remove image backgrounds using AI

Interpret is a framework for fitting interpretable machine learning models and explaining black-box models.

An open-source personal assistant that provides AI-powered voice and text interactions.

PredictionIO is a machine learning server for developers and ML engineers, enabling building and deploying production-ready ML services.

A project that helps automate the creation and distribution of short-form and long-form video content across social media platforms.

An extensible toolkit for finetuning and inference of large language models, enabling 'large models for all'.

Qwen-Image is a powerful AI-powered image generation model for complex text rendering and precise image editing.

Officially maintained deep learning models by PaddlePaddle, covering computer vision, NLP, speech, and more.

The spatial perception framework for rapidly building smart robots and spaces

🐸TTS is a deep learning toolkit for advanced Text-to-Speech generation with 1100+ languages and tools for training and fine-tuning models.

Demystify AI agents by building them yourself with no black boxes, real understanding of function calling, memory, and ReAct patterns.

Automate your mobile devices with natural language commands using an LLM-agnostic mobile agent.

A Python library for converting PDF files into various formats, focused on processing scanned book PDFs.

A PyTorch-based reference implementation and models for the DINOv3 self-supervised vision transformer.

AI orchestration framework for building LLM applications with pipelines and agents

Trigger.dev is a platform for building and deploying fully-managed AI agents and workflows.

A fun project that generates AI-powered random nonsense essays in Chinese, for a good laugh.

An index of algorithms for offline reinforcement learning (offline-rl) targeting AI and ML researchers.

TinyMaix is a tiny inference library for microcontrollers, enabling efficient AI/ML on resource-constrained devices.

Curated list of machine learning frameworks, libraries, and software

Flock is a low-code platform for rapidly building AI-powered chatbots, RAG, and multi-agent workflows.

A PyTorch implementation of the Mean Flows for One-step Generative Modeling paper, for vibe coders building AI tools.

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

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

NocoBase is an AI-powered no-code/low-code platform for building business applications and enterprise solutions.

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

Arknights game automation with image recognition

Infinite Photorealistic Worlds using Procedural Generation, a library for generating realistic virtual worlds.

A Python library based on PaddlePaddle for developing virtual anchors (vtubers) with AI tools.

CodeGeeX2 is a powerful multilingual code generation model for AI-powered coding tools and workflows.

Facebook's extensions to the Torch/CUNN deep learning framework, primarily for GPU-accelerated neural network computations.

OpenChat is a hackable Next.js AI chatbot template for building chatbot apps with AI SDK, supporting multiple model providers and Vercel deployment.

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