๐ฃ Today, Iโm excited to walk you through Unityโs NEW AI offering, Meta MCP Extensions, and agentic tools to demonstrate how we can ๐๐๐ถ๐น๐ฑ ๐ ๐๐๐น๐น ๐ฉ๐ฅ/๐ฉ๐ฅ ๐๐ฎ๐บ๐ฒ from start to finish using these AI tools in a practical way.ย
๐ฅ Full video available at: https://t.co/4p5ZzdaRfg
๐ Hereโs what Iโm covering today:
- Unity VR project setup (with OpenXR plugins)
- Installing the Unity AI Assistant and demos
- Configuring Unity MCP + Meta MCP Extensions
- Configuring Claude Code & MCPs
- Building a VR/MR Basketball Game with the Unity AI Assistant, Claude Agent, and external Claude Code CLI
- A lot of iteration with Claude Code + the Meta XR Simulator
๐กAlso, itโs been a while since I've posted a new video, and Iโm genuinely excited to be back, especially with a topic like this that I know many devs have been waiting for.
I've spent years in both academic and industrial robotics labs. Every team I've worked with, from research groups to warehouse automation startups, was rebuilding the same infrastructure from scratch.
There's great open work out there, ROS, Open-X, LeRobot. But the infrastructure to actually train and deploy robot policies at scale has mostly stayed locked inside a handful of labs and companies. You can't iterate on what you can't access.
So at Neuracore, we made two calls from day one:
The core platform is open-source. Inspect it, extend it, contribute back.
Academia gets the full platform free for research. Students, PhDs, PIs. If you're working on robot learning, infrastructure shouldn't be what slows you down.
Robotics 2.0 won't be delivered by any single company. It'll be delivered by a generation of builders who had good tools at the right time.
We want @Neuracore_AI to be one of them.
Get started today for free: https://t.co/9kJpxyydJs
Been testing GPT 5.5 and it's implemented the HTML-in-Canvas spec
Worked for both WebGL and WebGPU out of the box
Then created this demo with the PixiJS + GSAP Skills
Hopefully there will soon be no excuses to make boring websites
Me and @andrew_d_d were busy getting Animateur to the next level!
Andy, did refactoring and UI improvements, while I went and got all of his fantastic work hosted somewhere for EVERYONE to enjoy his updates, even the non-techies!
Please enjoy: https://t.co/mqI62wV3Jy
NVIDIA DROPPED A MOTION DIFFUSION MODEL FOR HUMANOID ROBOTS
trained on 700 hours of mocap data
kimodo generates high-quality 3D human and robot motions from text prompts
you control it with:
โ full-body pose keyframes
โ end-effector positions/rotations
โ 2D paths and waypoints
works on human skeletons and unitree G1 robot
plug the outputs directly into mujoco or retarget to other robots using GMR
has a web-based interactive demo with a timeline editor. runs locally
needs ~17GB VRAM to run inference
open source under apache 2.0
https://t.co/kiqX768K0I