ProPainter is an open-source video inpainting system from ICCV 2023 that removes objects and watermarks from videos and fills the gaps with…
Layout Parser is a unified open-source toolkit for deep-learning-based document image analysis, giving developers a single, consistent API for detecting and understanding…
Wenda is an open-source LLM application platform designed for efficient, private content generation on modest hardware. Built originally for Chinese language models,…
mistral.rs is a fast, flexible LLM inference engine written in Rust. Despite the name, it is not limited to Mistral models: it…
Plano is an AI-native proxy server and data plane for agentic applications, built by Katanemo on top of Envoy. It moves the…
skorch is an open-source Python library that wraps PyTorch neural networks in a scikit-learn-compatible interface. It has earned about 6,200 stars on…
Go Stock is an open-source desktop app that puts AI inside stock analysis. Built with Go and Wails, it pulls market data…
DeepLabCut is the landmark open-source toolbox for markerless pose estimation with deep learning, letting researchers track user-defined body parts in videos of…
GPT-Load is a self-hosted AI gateway that unifies access to multiple LLM providers and credentials behind one endpoint. Written in Go, it…
Fast Stable Diffusion is a hugely popular collection of optimized notebooks that let you run Stable Diffusion — and train it with…
MMdnn is a comprehensive set of tools from Microsoft that helps you work across different deep learning frameworks — converting trained models…
RealChar is an open-source project for creating, customizing and talking to AI characters in real time, with natural voice conversation across mobile,…