Skip to content

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.

1.2 KB
Raw Blame
<!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>&lt;agent-3d&gt;</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>