Fable 5.1 World Modeling

Anthropic's Claude Fable 5.1 autonomous agent swarms have produced a browser-native, code-generated 3D reconstruction of San Francisco's Union Square, released as an open-source Three.js project with 453 building footprints, 129 named storefronts, and explorable Apple and Nintendo interiors. The project, available on GitHub under an MIT license, uses open data from OpenStreetMap and USGS, and includes 34 camera-matched validation viewpoints against real photographs.

Worlds via code. Explorable, browser-native reconstructions of real places — researched, modelled, and quality-checked end to end by autonomous Claude Fable 5.1 https://www.anthropic.com/claude/fable agent swarms, then shipped as plain Three.js https://threejs.org apps you can run with npm run dev . No game engine. No proprietary 3D tiles. Every building, storefront, sign, tree and traffic light is generated from open data and public reference imagery by code that lives in this repo. ▶ Watch the full 59-second walkthrough · 1920×1080 · aerial, plaza, Nintendo, lower level, Apple The square and its surrounding blocks — Powell, Geary, Post and Stockton — on real terrain and a real street grid, with 129 identified storefronts, working traffic lights and cable cars, day/sunset/night, and two explorable interiors: Apple Union Square 300 Post St and Nintendo SAN FRANCISCO 331 Powell St . Run it | cd union-square-sf && npm install && npm run dev | Buildings | 453 OSM footprints · 75 hand-authored façades · 129 named storefronts | Life | 220 pedestrians on a 1,398-node nav graph · 109 vehicles incl. Powell St cable cars | Interiors | Apple + Nintendo, 23 interactive objects | Validation | 34 camera-matched viewpoints vs. real photographs · 147 comparison sheets · 9 independent reviewer reports | More worlds coming. Each world follows the same pipeline, and every stage is in the repo so you can re-run it: Reconnaissance — parallel research agents pull OpenStreetMap geometry, USGS elevation, transit and street specs, and a storefront census with per-fact sources and confidence levels. Offline asset generation — Blender-as-a-library bpy scripts emit optimised GLB kits: façade modules, street furniture, vehicles, vegetation, retail fixtures, pedestrian body parts. Runtime — a pure Three.js app assembles terrain, streets, façades, props, crowds and traffic from JSON specs. Camera-match QA — Playwright drives the real app, screenshots fixed viewpoints, and diffs them against free-licensed photographs taken from the same spot; independent reviewer agents architect, geographer, technical artist, interaction file reports that drive the next fix cycle. Code and generated assets: MIT /PhiloLabs/fable51-worlds/blob/main/LICENSE . Geometry is derived from OpenStreetMap https://www.openstreetmap.org/copyright ODbL and USGS 3DEP public domain . Reference photographs are not redistributed here — their provenance is recorded per sector in each world's refs/ /SOURCES.md . Brand names and logos identify the real businesses at their real locations and belong to their owners.