Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
{
"$schema": "NPC dialogue table for the walk scene (Task 19). Slots: greeter, guide-wait, guide-arrive ({landmark} token). landmarks steer the guide NPC.",
"greeter": [
"Welcome to the void — nothing here but focus.",
"Hey. Pure grid, pure quiet. Wander as far as you like.",
"Glad you came. Sometimes empty space is the point.",
"Welcome in. No distractions out here — just you."
],
"guide-wait": [
"Take your time — I'll wait on the grid.",
"No rush. There's nowhere to be but here.",
"I'll hold this spot until you catch up."
],
"guide-arrive": [
"Here — {landmark}.",
"This is {landmark}, such as it is.",
"We've reached {landmark}. Breathe it in."
],
"landmarks": [
{ "name": "the grid's edge", "pos": [0, 0, -8] },
{ "name": "the far marker", "pos": [8, 0, 0] },
{ "name": "the quiet corner", "pos": [0, 0, 8] },
{ "name": "the open expanse", "pos": [-8, 0, 0] }
]
}