Starred repositories
Sharp Monocular View Synthesis in Less Than a Second
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
🚀2.3x faster than MinIO for 4KB object payloads. RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platfor…
SeaweedFS is a fast distributed storage system for blobs, objects, files, and data lake, for billions of files! Blob store has O(1) disk seek, cloud tiering. Filer supports Cloud Drive, xDC replica…
CADAM is the open source text-to-CAD web application
ComfyUI wrapper for Motion capture from video
A local-first personal finance app
Weighs the soul of incoming HTTP requests to stop AI crawlers
KRITA Plugin - Smart Segments - AI Segment Anything Model 2
Krita plugin which adds selection tools to mask objects with a single click, or by drawing a bounding box.
Nodes for using ComfyUI as a backend for external tools. Send and receive images directly without filesystem upload/download.
AI-powered video object removal (diffusion inpainting under the hood).
Reference PyTorch implementation and models for DINOv3
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
Unofficial snap repo for notepad-plus-plus snap
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
The full stack toolkit to build onchain app UX
Local-first AI Notepad for Private Meetings
Simplifying reinforcement learning for complex game environments
MiniMax-M2, a model built for Max coding & agentic workflows.
Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows
State-of-the-art 2D and 3D Face Analysis Project
Hackable and optimized Transformers building blocks, supporting a composable construction.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.