More relighting!

Lets make video diffusion practical!

[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.

High performance self-hosted photo and video management solution.

tiny vision language model

No fortress, purely open ground. OpenManus is Coming.

Structured Outputs

SGLang is a high-performance serving framework for large language models and multimodal models.

Muon is Scalable for LLM Training

Turn Webpage to LLM friendly input text. Similar to Firecrawl and Jina Reader API. Makes RAG, AI web scraping, image & webpage links extraction easy.

Backup ZFS snapshots to cloud storage such as Google, Amazon, Azure, etc. Built with the enterprise in mind.

Convert the model in PaddleOCR to ONNX format

📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.

A pass extension for managing one-time-password (OTP) tokens

Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.

FUSE driver for APFS (Apple File System)

Modern, extensible Python project management

API libraries, samples, and system images for AIY Projects (Voice Kit and Vision Kit)

Pythonic bindings for FFmpeg's libraries.

Check syntax in Vim/Neovim asynchronously and fix files, with Language Server Protocol (LSP) support

Linear Assignment Problem solver (LAPJV/LAPMOD).

Insight Toolkit (ITK) -- Official Repository. ITK builds on a proven, spatially-oriented architecture for processing, segmentation, and registration of scientific images in two, three, or more dime…

Open Source Computer Vision Library

scikit-learn: machine learning in Python

Image processing in Python