Learn Japanese grammar with TypeScript

A little Python library for making simple Electron-like HTML/JS GUI apps

A minimal, embeddable, JS-native Infrastructure-as-Code library designed with gen-AI in mind.

Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.

The open-source reactive database for app developers

Simple Three.js animation mixer demo.

RF-DETR is a real-time object detection model architecture developed by Roboflow, SOTA on COCO & designed for fine-tuning.

Start and end frames video generation nodes based on the modified Kijai version Wan2.1 nodes

[CVPR 2025]MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM

The most comprehensive authentication framework for TypeScript

Open TTS models, built for streaming on the edge

Model Context Protocol (MCP) that allows LLMs to use QGIS Desktop

YOLOE: Real-Time Seeing Anything

Geospatial Rendering in Three.js

Spark-TTS Inference Code

Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analysis, from understanding the key statistics and characteristi…

LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

A Conversational Speech Generation Model

flow-pilot is an openpilot based driver assistance system that runs on linux, windows and android powered machines.

[ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Copy & Paste React components to build modern web applications.

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…

Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- H…

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

Official implementation of Continuous 3D Perception Model with Persistent State

container image to single executable compiler