Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Sharp Monocular View Synthesis in Less Than a Second

MagicLeap with OpenCVforUnity Example

UVC4UnityAndroid

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Official implementation of a free pupillometry platform called PupilEXT proposed in the article "PupilEXT: flexible open-source platform for high resolution pupillometry in vision research".

PyPupilEXT allows to detect the pupil diameter in images captured by stereo- and mono camera systems. The pupil diameter can be detected using one of the state-of-the-art open-source algorithms, St…

PhysioKit: Open-source, accessible Physiological Computing Toolkit [Sensors 2023]

One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

Generates a texture for 3D models created by the TripoSR image-to-3D model

Self-adversarial Multi-scale Contrastive Learning for Semantic Segmentation of Thermal Facial Images [BMVC 2022]

Generate 3D objects conditioned on text or images

A Unity library and MRTK extension for estimating and replicating the current environment's lighting on Mixed Reality devices.

Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching,…

Graphics tools and components for developing Mixed Reality applications in Unity.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

HoloLens 2 Sensor Streaming. Real-time streaming of HoloLens 2 sensor data over WiFi. Research Mode and External USB-C A/V supported.

a state-of-the-art-level open visual language model | 多模态预训练模型

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

This repository holds the third generation of the Mixed Reality Toolkit for Unity. The latest version of the MRTK can be found here.

Extremely Fast MessagePack Serializer for C#(.NET, .NET Core, Unity, Xamarin). / msgpack.org[C#]

TIPA open source project: Thermal Imaging-based Physiological and Affective computing (TIPA) open source toolkits

Context-Aware Online Adaptation of Mixed Reality Interfaces