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
Reference photo sources
All three reference photos are CC0 (public domain dedication), downloaded from Wikimedia Commons. Kept locally so the benchmark never depends on a third party staying online, and so the exact bytes fed to image->3D never drift.
| File | Title | Source |
|---|---|---|
chair.jpg |
Antique Wooden Chair from Bharat | https://commons.wikimedia.org/wiki/File:Antique_Wooden_Chair_from_Bharat.jpg |
sneaker.jpg |
Imani Bahati, unpaired gray Nike running shoe | https://commons.wikimedia.org/wiki/File:Imani-bahati-unpaired-gray-nike-running-shoe.jpg |
teapot.jpg |
Covered teapot, China, early 19th century, nephrite, Honolulu Museum of Art | https://commons.wikimedia.org/wiki/File:Covered_teapot,_China,_early_19th_century,_nephrite,_Honolulu_Museum_of_Art.jpg |
Downloaded 2026-07-23. Re-verify CC0 status on Commons if these are ever swapped.