Trending Projects

An awesome list of AI Agents for developers building with AI tools and platforms.

A trainable PyTorch reproduction of the AlphaFold 3 protein structure prediction model.

Official implementation of the paper 'Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection'.

AIGCPanel is an all-in-one AI digital human system that simplifies local model management, import, and use.

A fast, full-featured web app that provides access to popular AI chatbots like ChatGPT, Bard, and Bing.

A comprehensive collection of PyTorch documentation translated to Chinese for easy access to the framework.

Lightweight Python framework for building autonomous AI agents with memory and exploration capabilities.

A compiler for neural network hardware accelerators, focusing on performance and efficiency.

This GitHub repository appears to be a machine learning library, but without more details it's difficult to determine the specific use case.

A web app for interacting with any LangGraph agent (PY & TS) via a chat interface.

An effective paradigm for building tiny-scale vision-language-action models for robotics and embodied AI.

A PyTorch library for building CNN-based text classification models.

A Python library that trains a large language model on data from specific time periods to reduce modern bias.

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

Open source implementation of CLIP, a contrastive learning model for multi-modal tasks like zero-shot classification.

This is a free 4-month course to learn machine learning engineering, covering deployment, Docker, FastAPI, and more.

MuseTalk is a Python library for real-time, high-quality lip synchronization using latent space inpainting.

A powerful multi-resolution diffusion transformer for fine-grained Chinese text understanding and generation.

A local chatbot fine-tuned by bilibili user comments, built with Python.

An open autoregressive foundational video AI model for vibe coders building with AI tools.

This repository contains annotated research papers on machine learning and deep learning topics.

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification.

This GitHub repository provides a curated list of resources related to neural rendering, a technique in computer graphics and computer vision.

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

A curated list of awesome object detection resources and libraries for computer vision and deep learning.

An advanced real-time screen translator for games, videos, and static text, powered by machine learning.

A collection of tutorials for the MONAI open-source AI framework for medical imaging and research.

HolmesGPT is an AI agent that helps SREs and DevOps teams solve incidents faster with automatic correlations, investigations, and more.

A modular full-stack reinforcement learning library for large language models (LLMs).

An interface library for reinforcement learning (RL) post-training with environments.

Facets is a set of data visualization tools for machine learning datasets, helping developers explore and understand their data.

DeepChat is a smart AI assistant that integrates powerful language models into your personal workflow.

A high-performance video frame interpolation library for real-time video processing.

A unified and scalable ML library for large-scale distributed training, model serving, and federated learning.

This repository is likely a library or CLI tool for machine learning and AI development in Python.

A Torch implementation of DeepMask and SharpMask, deep learning algorithms for instance segmentation.

A curated collection of papers on generative information extraction using large language models.

An API for extracting, anonymizing, and parsing text from various document formats using state-of-the-art OCR and LLM models.

A collection of research papers and resources on computer vision tasks like image classification, object detection, and face recognition.

A fast, local neural text-to-speech system for developers building voice-enabled applications.

Boa is an embeddable JavaScript engine written in Rust, suitable for use in AI coding tools and MCP frameworks.

An open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

A deep learning-powered Chinese couplet generation tool using the seq2seq model.

High-performance data engine for AI and multimodal workloads, processing images, audio, video, and structured data at scale.

A cross-platform tool for batch generating subtitles and translations for videos and audio using AI models like Whisper, OpenAI, and DeepSEEK.

An official repository for the 'Mini-Gemini' model, a multi-modal vision-language model for generation tasks.

A feature-rich WeChat bot with AI-powered capabilities for developers, including security news, vulnerability lookup, and more.

Quantized attention that achieves 2-5x speedup over FlashAttention for language, image, and video models.

This GitHub repository contains code for reproducing large language model (LLM) related algorithms and learning materials.

A recurrent neural network for generating little stories about images.