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
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Bare avatar — three.ws</title>
<style>
/* Checkerboard so a transparent agent background is visibly transparent. */
body {
margin: 0;
min-height: 100vh;
display: grid;
place-items: center;
background-color: #fff;
background-image:
linear-gradient(45deg, #d6d6d6 25%, transparent 25%),
linear-gradient(-45deg, #d6d6d6 25%, transparent 25%),
linear-gradient(45deg, transparent 75%, #d6d6d6 75%),
linear-gradient(-45deg, transparent 75%, #d6d6d6 75%);
background-size: 28px 28px;
background-position: 0 0, 0 14px, 14px -14px, -14px 0;
}
</style>
</head>
<body>
<!-- JUST the avatar — the default. No chat, no input, no debug GUI, no name-plate,
transparent background. Add the `chat` attribute to opt into the conversational UI. -->
<agent-3d body="/avatars/cz.glb" width="420px" height="560px"></agent-3d>
<script type="module" src="../src/element.js"></script>
</body>
</html>