On-device AI across mobile, embedded and edge for PyTorch

Build and query dynamic, temporally-aware Knowledge Graphs

A browser extension that generates Cypress, Playwright and Puppeteer test scripts from your interactions 🖱 ⌨

A list of (almost) all headless web browsers in existence

A simple HTML content extractor in Python. Can be run as a wrapper for Mozilla's Readability.js package or in pure-python mode.

A standalone version of the readability lib

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

Brand new TTS solution

Heritrix is the Internet Archive's open-source, extensible, web-scale, archival-quality web crawler project.

This project demonstrates a basic chain-of-thought interaction with any LLM (Large Language Model)

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

OCR, layout analysis, reading order, line detection in 90+ languages

Python library for Room Impulse Response (RIR) simulation with GPU acceleration

The DICOM standard, in JSON format, parsed from the HTML version using Python scripts

The Memory layer for your AI apps

Code release for ConvNeXt model

Chat first code editor. To download the packaged app:

Machine Learning Toolkit for Kubernetes

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Lightning-fast serving engine for AI models. Flexible. Easy. Enterprise-scale.

Code release for ConvNeXt V2 model

The rendered book can be found at https://liulab-dfci.github.io/bioinfo-combio/

High-resolution models for human tasks.

Harness LLMs with Multi-Agent Programming

PyTorch tutorials and best practices.

An unofficial styleguide and best practices summary for PyTorch