Trending Projects

Deep learning library for fast and easy model building

An agent framework for fintech and banks, with support for AI tools like OpenAI and LLMs.

Fast and accurate AI-powered file content type detection library for Python developers.

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

Open-source implementation of AlphaEvolve, a coding agent for iterative code optimization and discovery.

A Python library for technical analysis of stocks and futures using the Chaikin volatility indicator.

An AI-powered PDF chatbot agent built with LangChain and LangGraph for vibe coders.

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

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

A suite of tools to develop RAG, semantic search, and other AI apps more easily with PostgreSQL

A vision transformer model for image classification tasks, part of the Google Research project.

Taichi Lang is a high-performance GPU programming language embedded in Python for numerical computation and parallel execution.

Open-source trading OS with pluggable AI brain for market data analysis, AI reasoning, and trade execution

Mesa is an open-source Python library for agent-based modeling and simulation of complex systems.

The AI developer platform to train and fine-tune models, and manage models from experimentation to production.

MultiAgentPPT is an AI-powered presentation generation system that leverages multi-agent collaboration and streaming concurrency.

A TensorFlow-based text classifier implementation that can be used as a starting point for building AI-powered coding tools.

Microsoft's research repo for large-scale self-supervised pre-training across tasks, languages, and modalities

Clean, robust, and unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms.

TimeCraft is a time series generation framework for building real-world AI applications.

An open-ended evolution system for self-improving AI agents that can be used for developing advanced AI applications.

This GitHub repository provides in-depth analysis and code explanations for state-of-the-art VIO (Visual-Inertial Odometry) research papers.

PaddlePaddle is a deep learning framework for industrial-scale ML, offering distributed training, model deployment, and Python/C++ support.

An open-source SDK for working with quantum computers at the level of quantum circuits, operators, and primitives.

An open-source tutorial that helps developers deploy large language models (LLMs) like Ollama on CPU for production use.

Super easy library for building BERT-based NLP models with FastAI and Transformers.

High-level network definitions with pre-trained weights in TensorFlow for deep learning and computer vision tasks.

A multiagent persona simulation tool powered by large language models for business insights and imagination enhancement.

State-of-the-art text embedding library for building advanced natural language processing applications.

Practical algorithm for real-world face restoration using GANs and deep learning.

Python bindings for the llama.cpp library, enabling developers to use LLMs in their Python projects.

A deep learning-powered tool for computer-aided comic/manga translation with AI-assisted image and text editing.

A collection of ComfyUI workflows for AI-powered coding and content generation

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

A blazing fast inference solution for text embeddings models built with Rust.

ORB-SLAM3 is an open-source library for visual, visual-inertial, and multi-map SLAM (Simultaneous Localization and Mapping).

ModelScope is an open-source AI framework that brings the notion of Model-as-a-Service to life, providing a comprehensive suite of tools for building, deploying, and managing AI models.

A puzzle-based learning resource for developers to explore CUDA and machine learning.

Sequence-to-sequence toolkit for NLP tasks like translation and summarization

An open-source enterprise-level AI knowledge base and management platform for chatbots and LLM applications.

A Python library for building AI agents that learn from experience using the Agentic Context Engineering framework.

Official repository for a paper on a large vision-language model for medical applications

A Python-based benchmarking framework for evaluating large-scale machine learning models and datasets.

A collaboration-friendly studio for building NeRF-based 3D reconstructions using PyTorch and other ML tools.

An open-source project that explores the use of world models for reinforcement learning in diverse domains like Minecraft.

A Python library that enables training powerful AI agents using end-to-end reinforcement learning.

Uni-MoE is a large multimodal model family from Lychee, a Python library for AI model development and deployment.

A Python tool that concatenates a directory of files into a single prompt for use with large language models (LLMs)

Textbook on reinforcement learning from human feedback, focused on AI alignment research.

Open3D is a modern C++ library for 3D data processing, including reconstruction, registration, and visualization.