datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Jai-World-VRM-3D-Embodied-AI
Jai World - VRM 3D Embodied AI
Interact with an AI powered 3D vrm avatar in a virtual world. A lightweight desktop folder-based Flask app that supports both Ollama and OpenRouter.
This project explores personalized 3D world generation, embodied AI, AI spatial navigation, and virtual character interaction. This code is a working example. It's a starting point that can be tuned and expanded.
Tech stack:
Three.js + HTML + CSS + JS + Flask + Ollama/OpenRouter (qwen3.5:9b/… See the full description on the dataset page: https://huggingface.co/datasets/vbookshelf/Jai-World-VRM-3D-Embodied-AI.ibb-embodied-agi-notes
IBB: Intention–Body–Behavior as a Loop for Embodied Intelligence
Most stacks still treat cognition as something completed before the body executes. IBB (Intention–Body–Behavior) models intelligence as a non-divisible loop:
Intention orients — task entry, purpose, what would count as success.
Body bears — limitation, capability, physics, vulnerability.
Behavior exposes the system to the world and returns consequence as write-back.
Write-back reshapes the next cycle of intention.… See the full description on the dataset page: https://huggingface.co/datasets/AIxHAI/ibb-embodied-agi-notes.