Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

A lightweight yet powerful audio-to-MIDI converter with pitch bend detection

Massively Parallel Deep Reinforcement Learning. 🔥

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

A lightweight Python library for simulating Chinese handwriting

Selfhosted PDF manager, viewer and editor offering a seamless user experience on multiple devices.

Simiki is a simple wiki framework, written in Python.

A lightweight UI framework based on tkinter with all UI drawn in Canvas!🎨

Official PyTorch implementation of Superpoint Transformer [ICCV'23], SuperCluster [3DV'24 Oral], and EZ-SP [ICRA'26]

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

High Performance Software-Defined Object Storage for Big Data and AI, that supports Amazon S3 and Openstack Swift

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

Powerful and flexible Instagram scraping library for Python, providing easy-to-use and expressive tools for accessing data programmatically

100M parameter lightweight conversational text-to-speech model with breaths, laughter, multi-speaker dialogue, voice cloning, and streaming. Llama-based, on-device.

The official implementation of GTCRN, an ultra-lightweight SE model.

Lightweight Image Super-Resolution with Information Multi-distillation Network (ACM MM 2019, Winner Award of ICCVW AIM 2019 Constrained SR Track1&Track2)

A light-weight, power efficient, and general purpose convolutional neural network

detect stages in video automatically

Decorator-first Python scheduler — cron/interval/at jobs with simple persistence and built-in run history.

LFD is a big update upon LFFD. Generally, LFD is a multi-class object detector characterized by lightweight, low inference latency and superior precision. It is for real-world appilcations.