# Project export: SkyScraper This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small. ## Project metadata - Hackathon: UC Berkeley AI Hackathon 2025 - Tagline: SkyScraper is an AI-powered aviation operations and safety platform that provides real-time flight risk assessments, weather impact analysis, ATC coordination insights, and smart rescheduling. - Devpost: https://devpost.com/software/skyscraper - GitHub: https://github.com/TheClassicTechno/SkyScraper - Demo: https://www.loom.com/share/f35e6ae5d0c6421e8d92533539d3061f?sid=c39ad051-8bdb-421d-ae8f-2fd3cefd2faf - Team: 3 GitHub contributor(s) — David Aror (47 commits), Julia (Juli) Huang (17 commits), Christopher-Anandaraj (12 commits) ## Devpost submission (written by the team) No Devpost description available. ## README (from the GitHub repository) # SkyScraper by berk ai hack team Enhanced Flight Communication System A real-time speech translation system powered by Google Gemini AI for aviation communication. AI-Powered Translation Google Gemini AI: Context-aware translations with 95% accuracy Aviation Context: Specialized terminology for flight communication Multi-level Fallback: Google Translate → Basic Translate → Error handling # ✈️ SkyScraper: Enhanced Flight Communication System **by berk ai hack team** --- ## Overview SkyScraper is a real-time speech and text translation system designed for aviation communication. Powered by Google Gemini AI and Google Translate, it provides context-aware, accurate translations for pilots, crew, and travelers, supporting both manual and voice input. The system is built with a modern React/Next.js frontend and a robust Flask/Python backend, communicating via REST API and Socket.IO for real-time features. --- ## Features - **AI-Powered Translation** - **Google Gemini AI**: Context-aware translations with up to 95% accuracy. - **Aviation Context**: Specialized terminology for flight, ATC, and emergency communication. - **Multi-level Fallback**: Google Translate → Gemini AI → Error handling. - **Speech Recognition** - Real-time voice-to-text using Google Speech Recognition. - Adjustable sensitivity for noisy environments (e.g., cockpits). - **Manual Text Translation** - Translate typed text between 15+ languages. - Language auto-detection and confidence scoring. - **User Interface** - Modern React/Next.js frontend. - Floating language assistant popup for instant access. - Responsive design for desktop and tablet. - **Backend** - Flask API for translation, language/context info, and status. - Socket.IO for real-time speech events. - CORS enabled for seamless frontend-backend integration. --- ## Supported Languages - English, Spanish, French, German, Italian, Portuguese, Russian, Chinese, Japanese, Korean, Arabic, Hindi, Thai, Vietnamese, Dutch, and more. --- ## Aviation Contexts - General, ATC (Air Traffic Control), Pilot, Ground, Emergency, Weather, Navigation, etc. --- ## Quick Start ### 1. Clone the Repository ```sh git clone https://github.com/yourusername/skyscraper.git cd skyscraper ## Detected evidence (automated analysis) Indexed codebase: 65 recognized source files, 564 KB. - Anthropic (technology) — detected in the code - CSS (language) — detected in the code - Flask (technology) — detected in the code - HTML (language) — detected in the code - JavaScript (language) — detected in the code - Next.js (technology) — detected in the code - OpenAI (technology) — detected in the code - Python (language) — detected in the code - React (technology) — detected in the code - Tailwind CSS (technology) — detected in the code - TypeScript (language) — detected in the code - Vercel AI SDK (technology) — detected in the code - AI coding agent: Cursor — evidence: config files committed to the repository ## Codebase structure (from repository index) ### Files (74 of 74) ``` audio.py back.py flight-log/.cursor/rules/flight-log-rules.mdc flight-log/.env flight-log/.env.local flight-log/.gitignore flight-log/AI_DEMO.md flight-log/API_SETUP.md flight-log/app/api/ai-recommendations/route.ts flight-log/app/api/aviation-chat/route.ts flight-log/app/api/aviation-request/route.ts flight-log/app/api/flight-risk/route.ts flight-log/app/api/letta-context/route.ts flight-log/app/api/letta-memory/route.ts flight-log/app/api/letta-profile/route.ts flight-log/app/components/ai-chat-agent.tsx flight-log/app/components/ai-translate.jsx flight-log/app/components/apple-timeline.tsx flight-log/app/components/aviation-dashboard.tsx flight-log/app/components/flight-booking-modal.tsx flight-log/app/components/flight-map.tsx flight-log/app/components/flight-risk-assessment.tsx flight-log/app/components/flight-search.tsx flight-log/app/components/letta-memory-dashboard.tsx flight-log/app/components/letta-profile-settings.tsx flight-log/app/components/main-page.tsx flight-log/app/components/radar-overlay.tsx flight-log/app/components/radar-time-slider.tsx flight-log/app/components/vapid-chat-agent.jsx flight-log/app/components/wind-field-loader.tsx flight-log/app/components/wind-field-overlay.tsx flight-log/app/error/page.tsx flight-log/app/flight-score/page.tsx flight-log/app/globals.css flight-log/app/layout.tsx flight-log/app/page.tsx flight-log/components.json flight-log/components/ai-recommendations-panel.tsx flight-log/components/ui/badge.tsx flight-log/components/ui/button.tsx flight-log/components/ui/card.tsx flight-log/components/ui/checkbox.tsx flight-log/components/ui/dialog.tsx flight-log/components/ui/input.tsx flight-log/components/ui/progress.tsx flight-log/components/ui/scroll-area.tsx flight-log/components/ui/select.tsx flight-log/components/ui/separator.tsx flight-log/components/ui/slider.tsx flight-log/lib/advanced-risk-assessment.ts flight-log/lib/ai-flight-recommendations.ts flight-log/lib/aviation-apis.ts flight-log/lib/flight-booking.ts flight-log/lib/flight-risk-assessment.ts flight-log/lib/letta-agent.ts flight-log/lib/turbulence-data.ts flight-log/lib/utils.ts flight-log/lib/vapi-client.ts flight-log/next.config.ts flight-log/package.json flight-log/postcss.config.mjs flight-log/README.md flight-log/tailwind.config.ts flight-log/tsconfig.json gemini.py gemini2.py gemini3.py hi.py install.py README.md requirements.txt templates/index.html templates/indexOLD.html test.py ``` ### Dependencies - flight-log/package.json: @ai-sdk/anthropic@^1.2.12, @ai-sdk/openai@^1.3.22, @radix-ui/react-dialog@^1.1.14, @radix-ui/react-progress@^1.1.7, @radix-ui/react-scroll-area@^1.2.9, @radix-ui/react-select@^2.2.5, @radix-ui/react-separator@^1.1.7, @radix-ui/react-slot@^1.2.3, @tailwindcss/postcss@^4, @types/leaflet@^1.9.18, @types/node@^20, @types/react@^19, @types/react-dom@^19, @vapi-ai/web@^2.3.6, ai@^4.3.16, axios@^1.10.0, class-variance-authority@^0.7.1, clsx@^2.1.1, leaflet@^1.9.4, lucide-react@^0.522.0, next@^15.3.4, openai@^5.6.0, react@^19.1.0, react-dom@^19.1.0, react-leaflet@^5.0.0, tailwind-merge@^3.3.1, tailwindcss@^4, tailwindcss-animate@^1.0.7, tw-animate-css@^1.3.4, typescript@^5 - requirements.txt: asyncio-mqtt@>=0.11.0, black@>=23.0.0, deep-translator@==1.11.4, eventlet@==0.33.3, flake8@>=6.0.0, flask@==2.3.3, Flask@==2.3.3, flask-socketio@==5.3.6, Flask-SocketIO@==5.3.6, google-generativeai@>=0.3.0, pyaudio@>=0.2.11, pytest@>=7.0.0, python-dotenv@>=1.0.0, python-engineio@==4.7.1, python-socketio@==5.8.0, requests@>=2.28.0, SpeechRecognition@==3.10.0, translate@==3.6.1 ### Recent commits (newest first) - Bug Fixes - Merge remote-tracking branch 'refs/remotes/origin/main' - Fix hella bugs - Added lots of UI fixes - Added lots of UI fixes - Merge remote-tracking branch 'refs/remotes/origin/main' - Final-fixes - Added Letta for memory management of user's personal risk score, airline prefs, and flight times - Added Letta for memory management of user's personal risk score, airline prefs, and flight times - Sweet sweet yummy changes - Adding english as a target language - Dynamic Stuff with ElevenLabs - Update README.md - made readme - fixed bugs related to pop up translator - changed window size, ui, format of pop up translator - made popup version of my translation website - Merge branch 'main' of https://github.com/TheClassicTechno/SkyScraper - updated goo goo gaa gaa - Merge remote-tracking branch 'refs/remotes/origin/main' ## Key source files (fetched from GitHub, selected and truncated for size) ### flight-log/AI_DEMO.md ```markdown # AI Flight Recommendations Demo ## Overview The AI Flight Recommendations system provides intelligent route optimization based on real-time weather data, aircraft capabilities, and multiple safety factors. This system analyzes alternative routes and provides detailed explanations for each recommendation. ## Features ### 🤖 AI-Powered Analysis - **Multi-factor scoring**: Safety, efficiency, and comfort scores - **Aircraft-specific optimization**: Different recommendations for different aircraft types - **Real-time weather integration**: Uses actual turbulence and weather data - **Confidence scoring**: Each recommendation includes a confidence level ### 🎯 Priority-Based Recommendations - **Safety First**: Prioritizes turbulence avoidance and weather hazards - **Fuel Efficiency**: Optimizes for fuel savings and route efficiency - **Passenger Comfort**: Minimizes passenger discomfort and turbulence exposure - **Balanced**: Combines all factors for optimal overall performance ### 📊 Detailed Explanations Each recommendation includes: - Safety improvement percentage - Time penalty vs. fuel savings - Weather hazards avoided - Confidence level in the recommendation ## How to Use ### 1. Access the AI Recommendations Panel - Navigate to the Aviation Dashboard - Scroll down to the "AI Flight Recommendations" section - The panel will automatically load with sample data ### 2. Configure Your Preferences - **Aircraft Type**: Select your aircraft (B737, B777, A320, A350, CRJ) - **Priority**: Choose your optimization priority - **Generate**: Click "Generate Recommendations" to analyze routes ### 3. Review Recommendations - Each recommendation shows safety, efficiency, and comfort scores - Click on any recommendation to see detailed explanations - Use the "Use This Route" button to select a recommended route ## Sample Data The demo uses a sample flight route: - **Origin**: JFK (New York) - **Destination**: LAX (Los Angeles) - **Current Position**: Mid-flight over Kansas - **Aircraft**: Boeing 737 ## API Endpoint The AI recommendations are powered by the `/api/ai-recommendations` endpoint: ```bash POST /api/ai-recommendations { "route": { "origin": { "lat": 40.7128, "lng": -74.0060, "name": "JFK", "icao": "KJFK" }, "destination": { "lat": 34.0522, "lng": -118.2437, "name": "LAX", "icao": "KLAX" }, "currentPosition": { "lat": 37.0902, "lng": -95.7129, "altitude": 35000, "timestamp": 1234567890 } }, "aircraftType": "B737", "priority": "balanced", "includeTurbulenceData": true } ``` ## Technical Implementation ### AI Recommendation Engine - **Route Alternatives**: Generates altitude variations, lateral deviations, and optimized waypoints - **Scoring Algorithm**: Multi-factor analysis considering safety, efficiency, and comfort - **Weather Integration**: Real-time turbulence data from multiple sources - **Aircraft Database**: Comprehensive aircraft capabilities and limitations ### Key Components 1. **AIFlightRecommendationEngin [truncated — 1495 more characters] ``` ### flight-log/API_SETUP.md ```markdown # Aviation API Setup Guide This application integrates with free aviation APIs to provide accurate flight tracking and turbulence data. ## Required API Keys (Optional) Create a `.env.local` file in the `flight-log` directory with the following API keys (all optional): ```env # Vapi AI - AI-powered calling and messaging # Get your key at: https://vapi.ai NEXT_PUBLIC_VAPI_API_KEY=your_vapi_api_key_here # OpenWeatherMap API (free tier available) # Get your key at: https://openweathermap.org/api NEXT_PUBLIC_OPENWEATHER_API_KEY=your_openweather_api_key_here # FlightLabs API (free tier available) # Get your key at: https://www.goflightlabs.com/ FLIGHTLABS_API_KEY=your_flightlabs_api_key_here ``` # Vapi AI Setup Guide ## Getting Started with Vapi AI Your flight tracking app now includes **VapidAgent** - an AI-powered phone assistant that can make calls, send texts, and summarize conversations. ### 1. Get Your Free Vapi API Key 1. Visit [Vapi.ai](https://vapi.ai) 2. Sign up for a free account 3. Get your API key from the dashboard 4. Free tier includes: **100 minutes of calls per month** ### 2. Configure Your Environment Add to your `.env.local` file: ```bash # Vapi AI Configuration NEXT_PUBLIC_VAPI_API_KEY=your_vapi_api_key_here ``` ### 3. Features Available ✅ **AI-Powered Phone Calls** - Natural language call initiation - Intelligent conversation handling - Call summaries and transcripts - Multi-language support ✅ **Smart Text Messaging** - AI-generated responses - Context-aware conversations - Message history tracking - Automated follow-ups ✅ **Call Management** - Call history and analytics - Conversation summaries - Voice-to-text transcription - Integration with flight data ### 4. Testing Your Setup 1. Add your Vapi API key to `.env.local` 2. Restart your development server 3. Open the VapidAgent chat (green phone icon) 4. Try commands like: - "Call +1234567890 to check flight status" - "Send a text to +1234567890 about weather conditions" - "Summarize my last call" ### 5. Safety Features - **Traffic Controller Mindset**: All operations prioritize user safety - **Call Validation**: Phone numbers are validated before calls - **Error Handling**: Graceful fallbacks when API is unavailable - **Rate Limiting**: Respects Vapi's usage limits ### 6. Free Tier Limitations - **100 minutes of calls per month** - Basic AI assistant features - Standard voice quality - Rate limiting applies ### 7. Upgrading (Optional) For production use, consider upgrading to paid plans: - **Starter**: $10/month - 1,000 minutes - **Professional**: $50/month - 5,000 minutes - **Enterprise**: Custom pricing ### 8. Integration with Flight Data VapidAgent can: - Call airlines for flight status updates - Send weather alerts to pilots - Summarize flight-related conversations - Schedule follow-up calls for delays ## Current Status Your VapidAgent is now configured with: - ✅ Real Vapi AI integration - ✅ Safety-first design principles - ✅ Graceful API [truncated — 5600 more characters] ``` ### requirements.txt ``` # Core requirements that work with conda flask==2.3.3 flask-socketio==5.3.6 requests==2.31.0 # For translation - using a more reliable library translate==3.6.1 # For speech recognition (optional - can be added later) # speechrecognition==3.10.0 # pyaudio==0.2.14 # WebSocket support python-socketio==5.8.0 eventlet==0.33.3 # Enhanced Flight Communication App Requirements # Core Flask Dependencies Flask==2.3.3 Flask-SocketIO==5.3.6 python-socketio==5.8.0 python-engineio==4.7.1 # AI Translation - Google Gemini (PRIMARY) google-generativeai>=0.3.0 deep-translator==1.11.4 # Fallback Translation Services #googletrans==4.0.0rc1 translate==3.6.1 requests>=2.28.0 # Speech Recognition SpeechRecognition==3.10.0 pyaudio>=0.2.11 deep-translator==1.11.4 # Additional Dependencies python-dotenv>=1.0.0 asyncio-mqtt>=0.11.0 # Development Dependencies (optional) pytest>=7.0.0 black>=23.0.0 flake8>=6.0.0 # Platform-specific audio dependencies # For Linux: python3-pyaudio, portaudio19-dev, pulseaudio # For macOS: portaudio (via homebrew) # For Windows: pyaudio wheel from https://www.lfd.uci.edu/~gohlke/pythonlibs/ ``` ### flight-log/package.json ``` { "name": "flight-log", "version": "0.1.0", "private": true, "scripts": { "dev": "next dev --turbopack", "build": "next build", "start": "next start", "lint": "next lint" }, "dependencies": { "@ai-sdk/anthropic": "^1.2.12", "@ai-sdk/openai": "^1.3.22", "@radix-ui/react-dialog": "^1.1.14", "@radix-ui/react-progress": "^1.1.7", "@radix-ui/react-scroll-area": "^1.2.9", "@radix-ui/react-select": "^2.2.5", "@radix-ui/react-separator": "^1.1.7", "@radix-ui/react-slot": "^1.2.3", "@types/leaflet": "^1.9.18", "@vapi-ai/web": "^2.3.6", "ai": "^4.3.16", "axios": "^1.10.0", "class-variance-authority": "^0.7.1", "clsx": "^2.1.1", "leaflet": "^1.9.4", "lucide-react": "^0.522.0", "next": "^15.3.4", "openai": "^5.6.0", "react": "^19.1.0", "react-dom": "^19.1.0", "react-leaflet": "^5.0.0", "tailwind-merge": "^3.3.1", "tailwindcss-animate": "^1.0.7" }, "devDependencies": { "@tailwindcss/postcss": "^4", "@types/node": "^20", "@types/react": "^19", "@types/react-dom": "^19", "tailwindcss": "^4", "tw-animate-css": "^1.3.4", "typescript": "^5" } } ``` ### flight-log/app/page.tsx ```typescript import MainPage from "./components/main-page"; export default function Home() { return ( ); } ``` ### flight-log/app/layout.tsx ```typescript import type { Metadata } from "next"; import { Geist, Geist_Mono } from "next/font/google"; import "./globals.css"; const geistSans = Geist({ variable: "--font-geist-sans", subsets: ["latin"], }); const geistMono = Geist_Mono({ variable: "--font-geist-mono", subsets: ["latin"], }); export const metadata: Metadata = { title: "Create Next App", description: "Generated by create next app", }; export default function RootLayout({ children, }: Readonly<{ children: React.ReactNode; }>) { return ( {children} ); } ``` ### flight-log/app/flight-score/page.tsx ```typescript import AviationDashboard from "../components/aviation-dashboard"; export default function Home() { return ( ); } ``` ### flight-log/app/error/page.tsx ```typescript "use client" import { Search, Plane, AlertCircle, ArrowLeft, HelpCircle, RefreshCw } from "lucide-react" import { Card, CardContent } from "@/components/ui/card" import { Badge } from "@/components/ui/badge" export default function Home() { return (
{/* Header */}

FlightSafe

Real-time Flight Tracking

Live Data
{/* Error Section */}
{/* Error Icon */}

Flight Not Found

We couldn't find your flight in our database. This could be due to several reasons.

{/* Error Details Card */}

Possible Reasons

Flight number may be incorrect

Double-check the flight number on your ticket or booking confirmation

Flight may not be scheduled today

Some flights operate on specific days of the week

Flight may have been cancelled

Check with your airline for the latest updates

Airline code might be different

Some flights are operated by partner airlines with different codes

{/* Tips Section */}

Helpful Tips

Check Your Booking

Look at your booking confirmation email or ticket for the exact flight number and airline code.

{ type Flight = { id: string; departure: string; arrival: string; departureTime: string; arrivalTime: string; date: string; aircraft: string; passengers: number; crew: number; riskScore: number; weather: string; atcLoad: string; runway: string; gate: string; }; const router = useRouter(); const [flightNumber, setFlightNumber] = useState("") const [flightData, setFlightData] = useState([]) const [loading, setLoading] = useState(false) const [error, setError] = useState(null) const [showTranslator, setShowTranslator] = useState(false); return (
{/* Animated Clouds */}
{/* Cloud 1 */}
☁️
{/* Cloud 2 */}
☁️
{/* Cloud 3 */}
☁️
{/* Cloud 4 */}
☁️
{/* Cloud 5 */}
☁️
{/* Cloud 7 */}
☁️
{/* Cloud 8 */}
☁️
{/* Additional clouds for better visibility */}
☁️
☁️
{/* Header */}

SkyScraper

Real-time Flight Tracking

Live Data
{/* Hero Section */}