Project Riko — Patreon Update (2026-05-07)
✨ What’s New
🥽 VR Integration
Project Riko now supports VR integration, allowing you to interact with Riko inside compatible VR environments for a much more immersive experience.
🚶 Improved Movement Features
Riko can now move around environments with expanded movement logic, including walking to specific locations and interacting with scenes more naturally.
🎬 Scene System Added
Scenes have now been added to the project, allowing for more dynamic interactions and environments — fully compatible with the new VR systems.
🧰 Updated Documentation
All setup instructions, feature details, and usage information can now be found inside the README / setup guide included with the project files.
💡 Quick Reminder — What is Project Riko?
Project Riko is my anime-focused AI companion system — built to listen, remember, and talk back like a cheeky anime partner.
It combines:
• OpenAI-compatible GPT streaming for real-time conversation
• GPT-SoVITS voice synthesis
• Faster-Whisper / Groq ASR
• A fully animated VRM avatar — compatible with VRM 1.0 for customizable avatars
• VR integration and interactive scene systems
• Simple personality configs
⚠️ Patreon Early Access
This build is exclusive to Patreon supporters and falls under the early access license:
Please don’t redistribute, resell, or share the code.
A public version will come later — you all are getting the frontier builds
As always, thank you for supporting the project. Every update like this gets us closer to the long-term vision for Riko.
Enjoy the new build.
— Rayen 💻✨
Download the code and follow the setup guide!
Comments (7)
Hi, I got the project up and running, i ran the "check_setup.py" and everything works perfectly. Now running the project i get this error in the debug window of the browser "movementController.js:158 Failed to load additive animation wave: Error: THREE.FBXLoader: Unknown format." "at FBXLoader.parse (FBXLoader.js:157:11) at Object.onLoad (FBXLoader.js:116:19) at three.core.js:44095:38" The vrma animations do work, only the fbx animations fail to work. (SOLVED)
hey, i am experimenting with this. However, the update path is a pain (?) or is it just me? maybe it would be easier, to set the most important things in a .env or a seperate file, that you don't include in the update, so you can just crash it all over. i am editing my code as well (for example to eliminate the voice stutters, when a text is too long), but then i always have to look, which parts are edited and which are not xD
Hey do you have direct chat? I have a Patreon with you but can’t find a direct chat link
ok so I just want a working, minimal setup that loads FBX animations on a VRM model via .py program in pycharm; I tried for hours now and nothing works. the issue is how you shoved all your features together and I just want the animation part.
I wrote my own server that supports FBX and VRMA. The LLM can select the animations via API and send them to the front end, where they are played.
check out the livingrimoire AGI software design pattern.
What llm do you use?
