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
Examples
Each page embeds a live, draggable 3D model - GitHub renders them natively, no plugins.
| Example | Facets | Block size | Shows |
|---|---|---|---|
| Cube | 12 | 1.7 KB | the minimal hand-writable case |
| Torus | 700 | 101 KB | parametric mesh, 70% simplification |
| Avatar | 1,200 | 172 KB | AI-generated character, 88% simplification |
The source ASCII STL files live in models/ - GitHub's file viewer renders those interactively too (click one).
Regenerate any of them from the repo root:
node bin/readme3d.js examples/models/torus.stl --facets 700 --name torus -o examples/torus.md
(The .md files here add context around the CLI output; the STL blocks themselves are verbatim CLI output.)