@simplifyinAI: An open source project turns any LLM into a 3D character that talks, moves, and reacts in the browser, no game engine, …

X AI KOLs Timeline Tools

Summary

An open-source project enables turning any LLM into a 3D character that talks, moves, and reacts in the browser with memory of emotional states and relationships, fully customizable and free to use.

An open source project turns any LLM into a 3D character that talks, moves, and reacts in the browser, no game engine, no local render setup. Characters have a memory system tracking emotional state and relationship history, so replies shift based on what's happened in the conversation so far, not just the last message. Fully customizable: swap the 3D model, the personality prompt, the LLM, or the text-to-speech provider. Try it free with zero setup, a hosted version includes complimentary API access to get started. Self-hosting needs your own API keys but gives full control to modify it. From the team behind Digital Life Project (CVPR 2024), presented at SIGGRAPH Asia 2025. 100% Free. Open Source.
Original Article
View Cached Full Text

Cached at: 08/29/26, 10:04 AM

An open source project turns any LLM into a 3D character that talks, moves, and reacts in the browser, no game engine, no local render setup.

Characters have a memory system tracking emotional state and relationship history, so replies shift based on what’s happened in the conversation so far, not just the last message.

Fully customizable: swap the 3D model, the personality prompt, the LLM, or the text-to-speech provider.

Try it free with zero setup, a hosted version includes complimentary API access to get started. Self-hosting needs your own API keys but gives full control to modify it.

From the team behind Digital Life Project (CVPR 2024), presented at SIGGRAPH Asia 2025.

100% Free. Open Source.

Similar Articles

Open-LLM-VTuber/Open-LLM-VTuber

GitHub Trending (daily)

Open-LLM-VTuber is an open-source voice-interactive AI companion with a Live2D avatar, supporting real-time conversations and visual perception, fully operable offline.