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>
<head>
<meta charset="utf-8">
<title>agent-3d Framer component harness</title>
<!--
Playwright-only fixture for tests/e2e/agent-3d-framer-component.spec.js.
Mounts the real Agent3DView (the framer-free component Agent3D.tsx wraps)
with plain ReactDOM, served by this package's own vite.config.mjs so the
repo root's vhtml JSX transform never touches it. Loads the real pinned
agent-3d CDN release (integrations/framer/src/pinned-release.ts) and a
real production avatar GLB, no mocks.
-->
<style>html,body{margin:0}</style>
</head>
<body>
<div id="root"></div>
<script type="module" src="./main.tsx"></script>
</body>
</html>