Open-source 3D AI agent framework — GLB/glTF avatars with LLM brains, memory, emotions, and autonomous payments. MCP server · x402 · Solana/EVM · Three.js. Embed anywhere as a web component. Character studio, animation gallery, OAuth 2.1. Browser-native.
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- !No standard license detected
git clone https://github.com/nirholas/three.ws{
"mcpServers": {
"three-ws": {
"command": "node",
"args": ["/path/to/three.ws/dist/index.js"]
}
}
}MCP Servers overview
# three.ws
[**Website**](https://three.ws) · [**X / Twitter**](https://x.com/trythreews) · [**GitHub**](https://github.com/nirholas/three.ws) · [**$THREE on pump.fun**](https://pump.fun/FeMbDoX7R1Psc4GEcvJdsbNbZA3bfztcyDCatJVJpump)
https://github.com/user-attachments/assets/d52515d1-cb04-4dd6-98bd-fef233312dc4
**Give your AI a body.** three.ws is an open-source, browser-native 3D AI agent platform. Type a prompt and [**Forge**](https://three.ws/forge) generates a textured 3D model — or drop a GLB you already have. Add an LLM brain, register on-chain, and embed anywhere — no plugins, no server uploads, no installs required.
> **Try it in 60 seconds:** open [three.ws/forge](https://three.ws/forge), type *"a brass steampunk owl, full body"*, and download the GLB. Text→3D, image→3D, and sketch→3D — free draft tier, no account. [Jump to the Forge section ↓](#forge--text--image-to-3d)
### $THREE
`$THREE` is the native token of the three.ws ecosystem — the one and only coin of the platform.
| | |
| --- | --- |
| **Token** | `$THREE` |
| **Contract Address (CA)** | `FeMbDoX7R1Psc4GEcvJdsbNbZA3bfztcyDCatJVJpump` |
| **Network** | Solana |
| **Trade** | [pump.fun](https://pump.fun/FeMbDoX7R1Psc4GEcvJdsbNbZA3bfztcyDCatJVJpump) |
> Always verify the contract address above before trading. `$THREE` is the only token associated with three.ws.
---
## Table of Contents
- [What is three.ws?](#what-is-threews)
- [Vision](#vision)
- [Roadmap](#roadmap)
- [Key Features](#key-features)
- [Forge — Text & Image to 3D](#forge--text--image-to-3d)
- [Platform Pages](#platform-pages)
- [Cloud Marketplaces](#cloud-marketplaces)
- [Ecosystem Directories](#ecosystem-directories)
- [IBM watsonx & Granite](#ibm-watsonx--granite)
- [Screenshots](#screenshots)
- [Architecture](#architecture)
- [Design Docs & Specs](#design-docs--specs)
- [Tech Stack](#tech-stack)
- [Browser Support](#browser-support)
- [Getting Started](#getting-started)
- [Examples](#examples)
- [Tutorials](#tutorials)
- [Project Structure](#project-structure)
- [The Agent System](#the-agent-system)
- [Event Bus (Agent Protocol)](#event-bus-agent-protocol)
- [LLM Runtime](#llm-runtime)
- [Empathy Layer](#empathy-layer)
- [Skills](#skills)
- [Memory](#memory)
- [Web Component & Embedding](#web-component--embedding)
- [Widget System](#widget-system)
- [Embed Editor](#embed-editor)
- [Pose Studio](#pose-studio)
- [Launchpad](#launchpad)
- [The Club](#the-club)
- [Walk & Multiplayer](#walk--multiplayer)
- [Coin Communities](#coin-communities)
- [City](#city)
- [Friends, Presence & Social](#friends-presence--social)
- [In-Game Economy](#in-game-economy)
- [Voice Lab & Mocap Studio](#voice-lab--mocap-studio)
- [x402 Payments](#x402-payments)
- [A2A — Agent-to-Agent Protocol](#a2a--agent-to-agent-protocol)
- [Talk Mode & Lip-Sync](#talk-mode--lip-sync)
- [Solana Mobile (Seeker)](#solana-mobile-seeker)
- [Selfie Reconstruction Pipeline (Phase 1)](#selfie-reconstruction-pipeline-phase-1)
- [Livepeer Inference Network (Phase 4)](#livepeer-inference-network-phase-4)
- [Voice & Persona Hub (Phase 2)](#voice--persona-hub-phase-2)
- [WASM Vanity Grinder](#wasm-vanity-grinder)
- [News CMS & Syndication](#news-cms--syndication)
- [Security Hardening](#security-hardening)
- [Developer SDKs](#developer-sdks)
- [Claude Code Integration](#claude-code-integration)
- [Demos Hub](#demos-hub)
- [Skill Library](#skill-library)
- [Animation System](#animation-system)
- [Avatar Accessories & Coin Launchpad](#avatar-accessories--coin-launchpad)
- [Brain Proxy & LLM Routing](#brain-proxy--llm-routing)
- [API Reference](#api-reference)
- [Authentication & OAuth 2.1](#authentication--oauth-21)
- [MCP Server](#mcp-server)
- [On-Chain Identity (ERC-8004 + Metaplex Core)](#on-chain-identity-erc-8004--metaplex-core)
- [Pump.fun Integration](#pumpfun-integration)
- [Database Schema](#database-schema)
- [Build & Deployment](#build--deployment)
- [Versioning & Compatibility](#versioning--compatibility)
- [Environment Variables](#environment-variables)
- [Testing](#testing)
- [FAQ & Troubleshooting](#faq--troubleshooting)
- [Contributing](#contributing)
- [Contributors](#contributors)
- [License](#license)
---
## What is three.ws?
three.ws is a full-stack system for creating, deploying, and embedding 3D AI agents. It combines a WebGL model viewer, an LLM-driven agent runtime, on-chain identity contracts, and a distributable web component into one cohesive platform.
At its core, it does five things:
1. **Generate** — turns a text prompt, 1–4 photos, or a sketch into a textured, downloadable GLB via [Forge](https://three.ws/forge). Free draft tier, no account required; auto-rigging, restyling, and retexturing in the same flow.
2. **Render** — loads and validates glTF 2.0 / GLB models in WebGL 2.0 with zero server-side processing. Drag a file onto the browser and it renders instantly with full Draco, KTX2, and Meshopt decompression.
3. **Embody** — wraps any avatar with an LLM brain. The agent listens to the user, thinks with Claude, executes tools (animations, gestures, memory operations, skill calls), and expresses emotion through morph-target blending on the 3D model in real time.
4. **Register** — optionally mints the agent on-chain: as an **ERC-8004 token on any EVM chain**, or as a **Metaplex Core NFT on Solana**. Either path gives the agent a stable on-chain identity, a wallet address, signed action history, and a reputation score that cannot be forged.
5. **Embed** — distributes the agent as an `<agent-3d>` web component that anyone can drop into a page, or as one of five purpose-built widget types (turntable, animation gallery, talking agent, passport card, hotspot tour) with Open Graph and oEmbed support built in.
The backend is a set of Vercel serverless functions backed by Neon Postgres for metadata, Cloudflare R2 for model storage, and Upstash Redis for rate limiting. It exposes a full OAuth 2.1 authorization server and an MCP (Model Context Protocol) endpoint so external AI systems can drive avatars programmatically.
three.ws is production-ready and serves [three.ws](https://three.ws) live. The entire stack — viewer, agent runtime, contracts, backend, and web component — is open source under Apache 2.0.
---
## Vision
One day, creating your agent should be as simple as taking a selfie.
Point your camera at yourself — or anyone — and watch a fully realized 3D avatar emerge: your face, your voice, your personality, alive in the browser. That avatar becomes an agent with memory and skills, registered onchain — as an ERC-8004 token on EVM or a Metaplex Core asset on Solana — permanent and verifiable by anyone forever. No 3D software. No wallet setup. No uploads. Just a photo and a name.
This is the direction three.ws is heading: **photo → avatar → agent → onchain identity**, in a single flow. The infrastructure is already here — the viewer, the runtime, the contracts, the embedding layer. What comes next is closing the gap between a picture of a person and a living, ownable, embeddable piece of them that exists on the internet permanently.
---
## Roadmap
three.ws ships in four phases. Each phase closes a specific gap between the current platform and the end-state vision: **anyone can mint a 3D agent of themselves, own it onchain, and embed it anywhere on the internet.**
| Phase | Theme | Status |
| ----- | -------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- |
| **0** | Platform foundations (viewer, runtime, ERC-8004 + Metaplex Core identity, embed layer) | ✅ Shipped |
| **1** | Selfie → Avatar engine (3-photo capture, hosted inference) | 🟡 In progress — capture UX + quality gates shipped; GPU reconstruction backend wiring |
| **2** | Agent personalization + voice cloning | 🟡 In progress — voice clone, persona, memory seeds shipped behind `/demos`; main-flow integration next |
| **3** | Onchain economy (agent tokens, reputation markets, royalties) | 🟡 Scaffolding — bonding-curve sim, EAS-reputation viewer, 0xsplits + EAS SDKs landed; contracts + audits next |
| **4** | Open inference network (decentralized GPU layer) | 🔮 Future — livepeer dep landed for early experimentation |
---
### Phase 0 — Foundations _(Shipped)_
The full stack is live at [three.ws](https://three.ws): WebGL viewer, LLM agent runtime, ERC-8004 identity contracts (EVM) and Metaplex Core mints (Solana), OAuth 2.1 server, MCP endpoint, and the `<agent-3d>` web component. Anyone can register an agent today — but the avatar still has to come from a 3D artist or a third-party tool.
**What works:** model upload, agent runtime, onchain registration, embedding, signed action history, reputation scores.
**What doesn't:** there is no automated path from a real human face to a usable 3D avatar.
---
### Phase 1 — Selfie → Avatar Engine
**Goal:** any user takes 3 selfies (left, center, right) and receives a rigged, animatable 3D avatar in under 60 seconds.
**Deliverables**
- Mobile-first capture UX with realtime quality gates (lighting, framing, blur)
- Multi-view face reconstruction pipeline (FLAME / 3DMM fitting on top of a base body mesh)
- Hosted inference workers (GPU-backed) for sub-minute generation
- Output written directly to R2 and minted as a draft agent token — ERC-8004 on EVM, Metaplex Core asset on Solana
**Compute What people ask about three.ws
What is nirholas/three.ws?
+
nirholas/three.ws is mcp servers for the Claude AI ecosystem. Open-source 3D AI agent framework — GLB/glTF avatars with LLM brains, memory, emotions, and autonomous payments. MCP server · x402 · Solana/EVM · Three.js. Embed anywhere as a web component. Character studio, animation gallery, OAuth 2.1. Browser-native. It has 59 GitHub stars and was last updated today.
How do I install three.ws?
+
You can install three.ws by cloning the repository (https://github.com/nirholas/three.ws) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is nirholas/three.ws safe to use?
+
Our security agent has analyzed nirholas/three.ws and assigned a Trust Score of 62/100 (tier: OK). See the full breakdown of passed checks and flags on this page.
Who maintains nirholas/three.ws?
+
nirholas/three.ws is maintained by nirholas. The last recorded GitHub activity is from today, with 1 open issues.
Are there alternatives to three.ws?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy three.ws to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/nirholas-three-ws)<a href="https://claudewave.com/repo/nirholas-three-ws"><img src="https://claudewave.com/api/badge/nirholas-three-ws" alt="Featured on ClaudeWave: nirholas/three.ws" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。