Render user-supplied VRM models with 162 animations and lip-sync via WebSocket control.
npx skills add https://github.com/genesis-plan/hongchen-lingjing --skill clawatar
Please help me install this Agent Skill. Skill: clawatar Source: https://github.com/genesis-plan/hongchen-lingjing/tree/main/skills/clawatar Command: npx skills add https://github.com/genesis-plan/hongchen-lingjing --skill clawatar
Provide a 3D VRM avatar body for an AI agent with animations and lip-sync to enable natural visual interaction.
Drop a VRM model onto the viewer, then start the server to see your avatar come alive.
High-intent search queries and answers about installing and using this skill.
You can add a 3D VRM avatar by dropping a user-supplied VRM model onto a browser-based viewer and controlling it via a WebSocket interface to enable visual interaction with animations and lip-sync.
Yes, controlling VRM avatar animations and lip-sync requires a WebSocket control channel at ws://localhost:8765 to drive actions, expressions, and speech from your AI agent.
The best way to build a VTuber-style 3D character is using a web-based VRM viewer that supports 162 animations and lip-sync, driven through a WebSocket connection for real-time speech and expression control.
Yes, you must supply your own VRM model to render in the browser-based viewer, which then applies 162 animations and lip-sync to bring your custom 3D character to life.
Limitations include the requirement for a specific WebSocket control channel at ws://localhost:8765 and a browser-based viewer, meaning the 3D avatar cannot run standalone without a local server environment.
viverseofficialAttach GLB weapon models to VRM avatar hand bones in Three.js.
CastrozanOrchestrate VTuber avatar lip-sync, expressions, and audio routing via WebSocket API.
GroundMountCompanyGenerate AI talking head videos with lip-sync using multiple model backends.
MonumentalSystemsGuide VRM avatar creation and export from VRoid Studio for streaming.
