three.ws: 3D AI Agent Platform with Text-to-3D and Web Embedding

LinkTool

three.ws is a web platform for creating and embedding animated 3D AI agents. Users can generate 3D models or avatars from text prompts or selfies, customise their behaviour, and embed them via web components directly into websites.

Key points

  1. Text-to-3D pipeline ('Forge') generating textured GLB models without mandatory registration.
  2. Avatar creation from prompts or selfies with automatic rigging, over 110 motion clips, and VRM/GLB support.
  3. Two-line web component embedding (<agent-3d>) or iframe for HTML, React, Vue, and platforms like Ghost or WordPress.
  4. Support for real-time voice (ElevenLabs, LiveKit), webcam facial motion capture, and American Sign Language (ASL).
  5. Optional Solana-based on-chain features, including USDC micropayments per chat, agent identity verification, and pump.fun trading automation.

Why it matters

The platform consolidates 3D asset generation, conversational AI, animation blending, and WebGL rendering into lightweight web embed tags. This allows developers to add interactive 3D assistants without building custom rendering pipelines.

Analysis

three.ws bridges generative 3D meshes with interactive browser-based agent interfaces. While its web component architecture, AR support (WebXR, iOS Quick Look), and animation tools make it accessible for frontend developers, the platform also leans heavily into Web3 features like USDC micropayments and Solana trading bots, which may limit appeal for traditional enterprise applications.

Found in

Summary generated by AI (Gemini 3.8 Flash, 6 October 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.