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
# syntax=docker/dockerfile:1
# agent-crawler: three.ws agents reading the open web in real browsers (/crawl).
#
# The base image ships Chromium plus every system dependency it needs. Its tag
# MUST match the playwright version pinned (exactly) in package.json and the
# lockfile: the image bakes the browser build that playwright release expects,
# so a drifted pair dies on launch with "Executable doesn't exist at
# /ms-playwright/chromium-<rev>". Bump both together.
FROM mcr.microsoft.com/playwright:v1.61.1-noble
WORKDIR /app
COPY package.json package-lock.json ./
RUN npm ci --omit=dev
COPY index.js crawler.js frontier.js extract.js guard.js robots.js seeds.js ./
ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
ENV NODE_ENV=production \
BASE_URL=https://three.ws \
CRAWLERS=8 \
JPEG_QUALITY=55
# CRAWL_WORKER_SECRET must be supplied at runtime.
USER pwuser
CMD ["node", "index.js"]