Python

Easy-to-use image converter for modern formats. Supports fast parallel encoding, lossless JPEG transcoding, JPEG XL, AVIF, JPEGLI, ExifTool, and more.

This Garmin Connect integration allows you to expose and upload data from and to Garmin Connect to Home Assistant.

[EMNLP'25 findings] An easy-to-use Graph RAG system using hierarchical knowledge.

[ACL2026 main] Official implementation of "Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance"

(ECCVW 2025)GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

[ICLR 2025 Spotlight] Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

[Built by humans] 👨‍💻 Всё, что нужно знать о System Design для прохождения интервью и не только

Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch

CRSLab is an open-source toolkit for building Conversational Recommender System (CRS).

SkyReels V3: Multimodal Video Generation Model

从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)

scp module for paramiko

Quickly search, compare, and analyze genomic and metagenomic data sets.

A hub for various industry-specific schemas to be used with VLMs.

Scrobbler for trakt.tv that supports VLC, Plex, MPC-HC, and MPV.

Python for DevOps repo with useful python scripts to learn and implement in your day-to-day devops automation tasks.

A single file container/archive that can be reconstructed even after total loss of file system structures

[IJCV 2026] Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving

An open-source Chinese font derived from Tanugo

Supercharge your command line with LLMs and get shell scripting assistance in Fish. 💪

Python script to download Instagram livestreams.

ParseBench - A Document Parsing Benchmark for AI Agents

Your own personal AIGC Factory. Any picture. Any reel. The Comfy way. ©️

Python re-implementation of the (constrained) spectral clustering algorithms used in Google's speaker diarization papers.

The SHA-256 Project, developed for NYU Tandon's Applied Cryptography course

Self-hostable web app for isolating the vocal, accompaniment, bass, and drums of any song. Supports Spleeter, Demucs, BS-RoFormer. Started in 2019.

Brute Force Attack Tools Using Python

Diffusion Convolutional Recurrent Neural Network Implementation in PyTorch

Text to speech alignment using CTC forced alignment