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>One line, one 3D agent — three.ws</title>
<style>
body {
margin: 0;
font: 16px/1.5 system-ui, sans-serif;
background: #0b0e14;
color: #e6edf3;
}
main {
max-width: 760px;
margin: 0 auto;
padding: 64px 24px;
}
h1 {
font-size: 34px;
margin: 0 0 8px;
}
p {
color: #9aa7b4;
}
.frame {
margin: 32px 0;
border: 1px solid #1f2733;
border-radius: 16px;
overflow: hidden;
background: #0e1320;
}
</style>
</head>
<body>
<main>
<h1>This page has one agent.</h1>
<p>Everything below the heading is a single <code><agent-3d></code> tag.</p>
<div class="frame">
<!-- THE ONE LINE — `chat` adds the conversational UI; drop it for just the avatar -->
<agent-3d chat body="/avatars/cz.glb" instructions="You are a friendly 3D guide for three.ws." width="100%" height="460px" brain="claude-opus-4-8"></agent-3d>
</div>
</main>
<!-- The framework loader (the only other line) -->
<script type="module" src="../src/element.js"></script>
</body>
</html>