Skip to content

AURA

AURA is an AI-powered visual intelligence engine that uses multi-modal recognition to identify, classify, and extract contextual metadata from buildings and architectural structures in real time.

Core trick

Camera frames go to a multimodal model that returns architecture style, era, and zoning fields, plus a photogrammetry mesh per scan.

Tags

Description

AURA is an AI-powered visual intelligence engine that uses multi-modal recognition to identify, classify, and extract contextual metadata from buildings and architectural structures in real time. Point the scanner at any building — commercial, residential, historical, or industrial — and AURA dynamically returns structured insights including architectural style classification, construction era estimation, ownership and tenancy data, zoning information, nearby amenities, and aggregate review sentiment. The system combines on-device detection with cloud-based inference for sub-second responses, personalized by user preferences, location, and scan history. Each scan also generates a photogrammetry-derived 3D mesh of the structure, exportable as OBJ, STL, or GLTF for archival, AR preview, or 3D printing as a collectible miniature.
context-labs-ai/aura★ 00 forksTypeScriptCreated Mar 7, 2026 · last push Apr 26, 2026

README excerpt

# AURA - Augmented Universal Recognition Assistant

**A camera-first PWA that overlays contextual AI intelligence on a live camera feed with a sci-fi HUD aesthetic. Point your phone at any building or product and get instant, grounded insights — enriched with real-time web data, Places API details, 3D model generation, and voice conversation.**

Built for the **Google Gemini API Developer Competition 2026**.

---

## What It Does

AURA turns your phone camera into an AI-powered lens. It identifies what you're looking at, enriches it with real-time data from multiple Google APIs, and presents everything in a futuristic heads-up display — all running client-side with zero backend.

### Building X-Ray Mode

Point at any building or storefront:

- **Visual identification** — Gemini reads signs, logos, and architectural cues to identify the building
- **Real-time enrichment** — Google Search Grounding fetches live reviews, news, and neighborhood context
- **Places API data** — Rating, opening hours, reviews, and editorial summaries from Google Places (New)
- **Landmark detection** — Recognizes iconic buildings with historical summaries and future development plans
- **Trust layer** — Every grounded claim gets a confidence rating (high/medium/low) with reasoning
- **3D scan** — Generates a 3D model of the building via Hyper3D Rodin, displayed with Three.js
- **Architectural details** — Year built, architect, height, floors, style, and notable facts

### Product Decompiler Mode

Poi

Team