🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Deep Learning for humans

The fundamental package for scientific computing with Python.

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

A Conversational Speech Generation Model

A collaborative note taking, wiki and documentation platform that scales. Built with Django and React.

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

A simple, easy-to-hack GraphRAG implementation

A Deep Learning Recommender System

MemU is an open-source memory framework for AI companions

Profile-Based Long-Term Memory for AI Applications. Memobase handles user profiles, memory events, and evolving context — perfect for chatbots, companions, tutors, customer service bots, and all ch…

Empowering RAG with a memory-based data interface for all-purpose applications!

A quickstart and benchmark for pytorch distributed training.

AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.

The PyTorch implementation of LightGCN

The code for NeurIPS 2025 paper "A-MEM: Agentic Memory for LLM Agents"

[CVPR 2022] StyleSwin: Transformer-based GAN for High-resolution Image Generation

Turn detection for full-duplex dialogue communication

AWM: Agent Workflow Memory

A simple Python sandbox for helpful LLM data agents

A huggingface transformers implementation of "Transformer Memory as a Differentiable Search Index"

A simple, easy-to-hack Vector Database

Implementing some features of Manus with MCP

Build event-driven workflows with python async functions