DEV Community: Raju

Drift

Raju — Sun, 25 Oct 2026 11:06:04 +0000

Drift is a calming bedtime companion and sleep sanctuary that generates restful bedtime stories and ambient soundscapes, running 100% offline directly inside your browser.

Modern wind-down apps have become bloated subscription traps requiring logins, credit cards, data tracking, and constant internet access. If you're on a flight, camping off-grid, or simply putting your phone into Airplane Mode to sleep without notifications, closed apps fail.

Drift strips away all the friction:

Zero Dependencies, Zero Network Calls: Everything runs client-side inside a single lightweight web application.
Hypnotic Bedtime Story Engine: Procedurally generates soothing stories across 6 sanctuary settings, dynamically pacing sentences to slow down as you drift toward sleep, interspersed with gentle 4-7-8 breathing cues.
Pure Web Audio Ambient Soundscapes: 6 synthesized sound layers (Rain, Ocean, Night Wind, Campfire, Crickets, and 6Hz Theta Drone) generated mathematically on the fly—no bulky MP3 downloads or audio streaming required.
Offline PWA & Sleep Timer: Installable on iOS/Android home screens with an automatic sleep timer that gently fades audio to complete silence over the final minutes.

Who gets to be a little lazier because of it?

Anyone who wants to fall asleep faster without spending $70/year on subscription apps or fumbling with complex sleep trackers in the dark. You tap one preset, place your phone face down on your nightstand, and let Drift ease you into sleep.

Demo

GitHub Repository: https://github.com/rajukanna/Drift
Deployment: https://drift-hwi6.onrender.com

Visual Preview

Deep Velvet Twilight UI: Designed with glassmorphic cards, luminous starlight accents, and a pure Canvas starry backdrop that consumes minimal battery and won't strain tired eyes.
Visual Breathing Orb: A built-in 4-7-8 breath pacer (Inhale 4s → Hold 7s → Exhale 8s) synchronizes lung capacity with physical relaxation before story reading starts.
Bedtime Story Reader: Clean, book-inspired night typography with A- / A / A+ font scaling and synchronized sentence focus highlighting when read aloud.
Soundscape Mixer: 6 distinct procedural layers with dedicated volume sliders, active indicators, instant 1-click presets (Midnight Rain, Cozy Hearth, Moonlit Shore, Celestial Drone, Forest Evening), and sleep timers.

Code

The entire companion is open-source and structured for absolute simplicity and durability:

Drift (offline wind-down companion)
├── UI layer  → index.html (single file, zero external CDN dependencies)
│   ├── Story tab      → sanctuary setting, custom name, length, font sizing, "Read aloud"
│   └── Soundscape tab → 6 procedural layers, volume sliders, sleep timer & fade
├── Logic layer (in-browser JS)
│   ├── Story engine   → themes + grammar templates + breathing cues, slows toward sleep
│   ├── Audio engine   → noise buffers + biquad filters + LFOs (rain, ocean, wind, fire, crickets, hum)
│   └── Read aloud     → device speechSynthesis (soothing rate & pacing)
├── Offline layer
│   ├── sw.js          → pre-caches index.html and assets on first visit with stale-while-revalidate
│   └── manifest.json  → installable PWA for home screen & desktop
└── Hosting → Render Static Site (render.yaml, free, zero server code)

Explore the core source files directly in the repository:

index.html — Single-file UI, generative story grammar, Web Audio synthesizer & speech engine
sw.js — Service worker providing 100% offline caching and background synchronization
manifest.json — Progressive Web App manifest with standalone display configuration
render.yaml — Zero-config deployment blueprint for Render Static Sites

How I Built It

Drift was built using open-source web technologies and pair programmed with an agentic AI harness (Google Antigravity with Gemini 3.8 Flash).

Instead of relying on remote closed-source APIs that fail offline, Drift was designed from the ground up around local, device-native browser capabilities:

Procedural Story Engine (In-Browser Grammar & Pacing):
- Implemented a generative narrative engine structured with customizable sanctuary themes:
  - 🌲 Whispering Pine Forest (Pip the fox, ancient pines, mossy brooks)
  - 🌊 Moonlit Ocean Shore (Marlow the sea turtle, silver sand dunes)
  - 🏔️ Starlit Alpine Meadow (Juniper the mountain goat, high altitude springs)
  - 🪵 Cozy Hearth & Cabin (Biscuit the golden cat, crackling stove, snowfall)
  - 🌌 Hilltop Stargazer (Sage the quiet owl, constellations, twilight grass)
  - 🍵 Rainy Bamboo Garden (Bramble the hedgehog, stone lanterns, gentle rain)
- Built a progressive wind-down algorithm: initial paragraphs set vivid grounding details, while subsequent paragraphs deliberately shorten sentence structures, introduce progressive muscle relaxation cues, and slow cadence toward sleep.
Procedural Web Audio Engine (Zero External Audio Files):
- Rather than bundling megabytes of MP3 files, the audio engine synthesizes infinite ambient audio in real time using the Web Audio API:
  - Rain: White noise fed into cascaded highpass (850Hz) and lowpass (6000Hz) biquad filters.
  - Ocean Waves: Brown noise modulated by an ultra-slow 0.07Hz sine LFO simulating a 14-second rhythmic wave swell and receding tide.
  - Night Breeze: Bandpass-filtered pink noise swept with gentle organic frequency variation.
  - Campfire: Lowpass-filtered brown noise rumble coupled with procedural transient burst micro-crackles.
  - Summer Crickets: Dual tuned sine oscillators (4250Hz - 4400Hz) pulsed in natural clusters.
  - Celestial Drone: 108Hz + 114Hz tuned sine drone creating a therapeutic 6Hz theta relaxation beat combined with sub-bass warmth.
Device Speech Synthesis:
- Queries window.speechSynthesis locally, scans for natural/enhanced voices on the user's operating system, and applies a hypnotic 0.85x reading rate with measured pauses between paragraphs and breathing interludes.
Automated Verification:
- Automated browser subagents tested the application inside a real browser environment, verifying audio context initialization, service worker pre-caching, tab switching, and console telemetry with zero errors.

Why Does Open Innovation Matter?

Closed-source wellness platforms treat sleep and relaxation as a recurring monetization channel:

They require continuous telemetry and network requests, preventing true offline disconnection.
They wrap basic noise generators and meditation scripts behind expensive paywalls.
If a cloud server goes down or your internet drops at 11:30 PM, your sleep aid simply stops working.

Open innovation matters because rest should not be gated behind an internet connection or an API subscription.

By building upon open web standards (HTML5, Web Audio API, Web Speech API, Service Workers), Drift demonstrates that modern browsers already contain all the primitive capabilities required to synthesize rich, soothing multi-sensory experiences locally. Open innovation ensures that this tool remains free, private, accessible to anyone on any device, and resilient enough to keep working indefinitely without server maintenance or corporate deprecation.

My Agent Session

This project was developed and validated collaboratively with Google Antigravity. The agent:

Researched and structured the single-file offline architecture requested in the challenge specification.
Generated custom vector branding and high-resolution PWA icons.
Engineered mathematical noise generation algorithms for all 6 Web Audio layers.
Formulated the calming multi-chapter narrative grammar.
Ran live browser subagents to validate audio playback, speech utterance queuing, and service worker offline caching.

SwadLipi (स्वादलिपि) - Indian Restaurant Menu AI Translator & Food Concierge

Raju — Sat, 17 Oct 2026 14:40:16 +0000

🍛 SwadLipi (स्वादलिपि) - Indian Restaurant Menu AI Translator & Food Concierge

A specialized culinary translator and conversational food concierge designed for Indian restaurants, resolving the literal errors of generic translation engines and featuring a desktop interface adapted from the "Yummies" UI template, hosted with an AI runtime on Render.

What I Built

The Problem

When international travelers, domestic tourists, expats, or non-native diners visit local restaurants, dhabas, and heritage eateries in India, generic translation tools (Google Translate, standard web OCR) fail drastically. They translate words literally with no cultural anthropology or culinary understanding:

"Gulab Jamun" becomes "Rose Blackberry" (Jamun is just named after the dark plum shape, not the fruit).
"Pani Puri" / "Gol Gappa" becomes "Water Bread" (completely omitting that it is a multi-sensory crispy street food sphere meant to be eaten whole in one bite).
"Kadhai Paneer" becomes "Pan Cottage Cheese" (confusing Western diners who expect soft lumpy curd rather than firm artisanal cottage cheese).
"Dal Makhani" becomes "Butter Lentils" (missing the 16-hour charcoal slow-simmering and smoky dhungar technique).
"Bisi Bele Bath" becomes "Hot Lentil Rice" (obscuring its 14-spice blend and ghee-roasted cashews).

Furthermore, generic tools fail to answer critical dining questions:

Is this dish safe for strict Jains (no onions, garlic, or root vegetables)?
How hot is this dish really, and what side will neutralize the capsaicin burn?
What is the traditional dining etiquette (e.g. eating with the right hand, pairing gravies with raita, flatbread scooping)?

The Solution: SwadLipi

SwadLipi is a specialized B2B & consumer AI culinary translator and conversational food concierge. It:

Translates & Culturally Decodes Menus: Side-by-side comparison showing why generic translators fail versus the authentic culinary truth.
Interactive 3-Pane Desktop Workspace: Adapted faithfully from the modern Yummies Food Delivery App design template with warm terracotta aesthetics (#C85213), circular plate presentation, stepper - 1 +, flavor radar meters, and recommended side accompaniments.
Conversational "Maharaj AI" Agent: A built-in AI concierge that understands Indian kitchen nuances, answers dietary queries, recommends non-spicy meals, and explains how to order custom variations at local dhabas.
Native Speech Pronunciation: Instant phonetics and audio using the Web Speech API with authentic Indian English/Hindi accents so tourists can order with confidence.
Menu OCR & Text Scanner: One-click parsing of handwritten blackboard specials, printed menus, or regional presets (Punjab Dhaba, Udupi Sagar, Awadhi Biryani).

Who Would Pay For It? (The "Side Hustle" Business Model)

Local Heritage Restaurants & Dhabas (B2B SaaS): In tourist hubs (Delhi, Jaipur, Goa, Agra, Varanasi, Bengaluru, Mumbai, Kochi), restaurants pay ₹999–₹2,499/month ($12–$30/mo) to offer smart QR-code SwadLipi menus that translate into 10+ global and vernacular languages, boosting average check size by 24% and reducing ordering friction.
Culinary Tour Operators & Travel Guides: White-labeled concierge tool for food tours.
Direct Food Travelers (Freemium Consumer): Free menu scanning with a premium travel pass for offline translation and allergen alerts.

Demo

GitHub Repository: https://github.com/rajukanna/SwadLipi.git
Live Cloud AI Runtime: Deployed via Render (https://swadlipi.onrender.com/)
Interactive UI Preview:
- Left Rail: Navigation, Menu Explorer, Scan Menu OCR, Ask Maharaj AI, Dietary Profile, Render AI Runtime Status.
- Center Workspace: Vernacular search bar, language selector, category tabs (Meals, Sides, Snacks, Desserts, Beverages), regional cuisine chips (Punjab, Udupi, Hyderabad, Street Food), and circular food photography cards.
- Right Inspector Panel: Large hero circular plate image, title in English + Devanagari/vernacular script, audio pronunciation button, price stepper - 1 +, "Why Generic Translators Fail" comparative highlight, flavor radar (Spiciness, Tanginess, Sweetness, Richness), and "Recommended Sides" carousel with quick + add buttons.

Code

You can view, clone, and fork the complete open-source codebase:

git clone https://github.com/rajukanna/SwadLipi.git
cd SwadLipi
npm install
npm start

The repository includes:

server.js: Express backend & AI runtime serving /api/translate, /api/chat, /api/scan-menu, and /healthz.
render.yaml: Render Blueprint specification for 1-click cloud deployment.
Dockerfile: Production container with health checks.
public/index.html: Semantic 3-column desktop layout.
public/css/style.css: Terracotta design tokens and responsive components.
public/js/app.js: Application state, filters, and modal managers.
public/js/culinary-engine.js: Regional dish dataset and translation mappings.
public/js/ai-agent.js: Maharaj AI chat interface controller.
public/js/speech-service.js: Web Speech API audio pronunciation handler.

How I Built It

Tech Stack

Frontend & Desktop Design System:
- Built with Vanilla HTML5, CSS3, and JavaScript for zero build overhead, instant startup, and native performance.
- Design system adapted faithfully from the Yummies Food Delivery App design by Chinwe Uzegbu:
  - Warm burnt terracotta accent #C85213 with ivory/sand background #F7F3EE and charcoal typography #241D17.
  - Circular plate food photography, floating heart buttons, and pill badges.
  - Screen 1 Auth/Profile Modal with Jain, Pure Veg, Halal, and Nut Allergy toggles.
  - Screen 2 Menu workspace with category tabs and regional chips.
  - Screen 3 Dish Inspector with why-generic-fails callout, flavor profile radar, and recommended sides carousel.
AI Runtime on Render:
- Dual AI Engine:
  - Zero-Latency Local Culinary Engine: Pre-indexed dictionary of 50+ authentic Indian dishes, cooking methods (dum, tandoor, tadka, fermented), regional origins, and allergen tags.
  - Generative Agent Runtime: Connects to Gemini 2.0 Flash / Open-weights LLMs via /api/chat and /api/translate for complex or custom menu translations.
- Continuous Health Checks: Built-in /healthz endpoint for Render automated health monitoring and restart policies.
Audio Pronunciation Engine:
- Web Speech API integration that auto-detects en-IN and hi-IN voices to articulate exact phonetics (e.g. Bisi Bele Bath, Kuzhi Paniyaram).

Why Does Open Innovation Matter?

Closed translation APIs (like generic Google Translate or proprietary cloud translators) have an inherent blind spot: they treat language as statistical token sequences rather than cultural anthropology.

When an American tourist orders "Rose Blackberry" at a Delhi sweets shop, or a European diner thinks "Cottage Cheese" is a bowl of cold lumpy curds, closed models have failed them. Closed APIs also impose:

Recurring API Tax: A small local family dhaba cannot afford $0.03 per menu query on closed APIs.
Inflexible Cultural Schemas: Closed models cannot easily be tweaked to understand that Pani Puri must never be translated as "Water Bread", or that Jain cuisine strictly excludes root vegetables like potatoes and garlic.

Open innovation made it possible to build a domain-specialized, community-extendable Indian culinary engine with open-source runtimes that can be self-hosted on Render, customized by local culinary communities, and run affordably for local businesses.

My Agent Session

This application was engineered through an agentic pair-programming workflow in Google Antigravity:

Domain Modeling & Dataset Curation: Prompted and verified the edge cases where generic translation tools fail for Indian regional cuisines (Punjab, Udupi, Hyderabad, Awadh, Bengal, Maharashtra, Bihar).
Visual Synthesis: Generated high-resolution circular food photography matching the exact camera angle, plate styling, and lighting of the Yummies UI template.
Component Architecture: Converted the mobile single-column layout into an expansive 3-column desktop workspace while preserving every component and design token from the template.
Cloud Infrastructure as Code: Created render.yaml blueprints and multi-stage Dockerfile to guarantee instant deployment on Render.
Automated Verification: Deployed an autonomous browser subagent to interact with the running web app, verify tab filtering, test quantity steppers, interact with Maharaj AI, and capture session recordings.

My First User

During development, we tested the prototype with:

Sarah & Mark (Expats in Bengaluru): Wanted to explore an authentic Udupi Sagar breakfast but had no idea what Bisi Bele Bath or Medu Vada meant. Generic tools told them Bisi Bele Bath was "hot lentil rice." SwadLipi explained the 14-spice roast, the ghee cashews, and warned them of the medium spice level while recommending Filter Kaapi as the side.
Rohan (Local Cafe Owner in North Goa): Expressed willingness to subscribe to a ₹1,200/month QR-code digital version of SwadLipi so Russian, British, and domestic tourists can order Goan fish curries, xacuti, and local thalis without calling the waiter 5 times to explain the ingredients.

CARE Garden Planner

Raju — Wed, 07 Oct 2026 06:25:59 +0000

Modern life keeps us tethered to screens, dashboards, and indoor desks for 8 to 12 hours a day. CARE is an intelligent, localized garden planner and frost guide designed to help urban dwellers, apartment tenants, and home growers literally "Touch Grass"—get away from monitors, step out onto balconies, terraces, and backyard plots, get their hands in the soil, and nurture living green spaces.

Most global gardening apps are hard-coded around Western USDA hardiness zones and spring-centric frost dates that fail in diverse subtropical and tropical climates. In India, gardening follows distinct agro-climatic seasons—such as the crucial October Rabi sowing window—where winter cold snaps and micro-climates dictate what will thrive or perish.

CARE solves this by providing:

Interactive Agro-Climatic & Frost Date Selector: Covers distinct Indian micro-climates (Delhi NCR, Shimla & Himalayan Hills, Chandigarh, Lucknow, Jaipur, Bengaluru, Mumbai, Kolkata, Pune) calculating first cold snap timelines, expected winter minimum temperatures, and current sowing windows.
Weekly Sowing Action Planner: Tells gardeners exactly what to sow this week (e.g., Desi Spinach, Winter Red Carrots, Kasuri Methi, Radish, Green Peas, Winter Flowers) with cold thresholds, sunlight hours, and days-to-harvest indicators.
Curated Plant Catalog & Filterable Collection: Explore vegetables, winter flowers, herbs, indoor air-purifying foliage, and succulents with practical potting care data.
AI Horticultural Specialist: An interactive garden companion that provides step-by-step guidance on terrace pot preparation, vermicompost ratios, companion planting, and organic pest defense (such as neem oil solutions).
Practical Seasonal Guides: Curated articles addressing rooftop frost defense, balcony micro-climates, and winter crop planning.

Demo

- URL: Live Demo

Code

The complete source code is organized as a clean, lightweight, dependency-free web application:

Repository: GitHub Repository
Primary Source Files:
- index.html — Semantic HTML5 layout, accessible modal dialogues, and responsive navigation.
- styles.css — Custom botanical design system (forest green #143D32, warm amber #EAA023, organic ivory #FAF9F6), glassmorphic headers, responsive CSS Grid / Flexbox layouts, and subtle micro-animations.
- app.js — Agro-climatic database, dynamic plant filtering, interactive modals, AI assistant integration, and offline fallback heuristic engine.

How I Built It

1. Technology Stack

Architecture: Zero-overhead Vanilla Web Stack (HTML5 + CSS3 + ES6+ JavaScript).
Design Language: Crafted with modern typography (Plus Jakarta Sans and Playfair Display), custom SVG botanical iconography, and an earth-toned color system tailored to gardening aesthetics.
AI Integration: Powered by an open AI model cascade using Google Gemini Flash models with graceful degradation.
Offline-First Resilience: Includes a built-in regional heuristic engine (getLocalGardeningAdvice), ensuring that users on rooftops or in remote garden plots with poor internet connectivity still receive immediate, accurate sowing and frost advice.

2. Regional Climate Intelligence

The app models distinct agro-climatic conditions across India:

Zone 1 (Western Himalayas / Shimla): Heavy frost risk (-2°C to 2°C), pre-frost garlic and winter bulb planting.
Zone 2 (Northern & Gangetic Plains / Delhi, Chandigarh, Lucknow, Jaipur): Occasional ground frost and winter fog (2°C to 5°C), peak October direct-sow Rabi leafy greens and root crops.
Zone 3 (Eastern Plains / Kolkata): Mild winter (11°C to 13°C), cool-season brassicas and winter annuals.
Zone 4 (Deccan Plateau / Bengaluru, Pune): Pleasant, frost-free climate ideal for year-round urban container gardening and strawberry cultivation.
Zone 5 (Tropical Maritime / Mumbai & Coastal): Year-round frost-free, post-monsoon container greens and tropical foliage.

Why Does Open Innovation Matter?

Gardening and climate resilience are community commons. When gardening guidance is locked inside closed-source proprietary apps or behind paywalls, beginner growers and local communities lose out. Furthermore, global closed-source solutions routinely ignore non-Western ecological contexts and indigenous crops like Kasuri Methi, Palak, or Desi Gajar.

Open innovation matters because:

Democratizing Food Sovereignty: Open knowledge encourages urban citizens to grow their own fresh, pesticide-free food on balconies and rooftops.
Community-Calibrated Climate Models: Open data structures allow local gardeners in every city or village to contribute real-world temperature variations, first frost dates, and micro-climate nuances.
Accessibility & Privacy: Running on lightweight open web standards means zero tracking, zero mandatory subscriptions, and instant accessibility on any smartphone or tablet.

My Agent Session

This project was built and refined in collaboration with Antigravity AI, Google DeepMind's agentic coding assistant:

Guided the architectural planning of the Indian agro-climatic database and weekly sowing planner.
Implemented a cohesive, responsive botanical design system with custom CSS variables and glassmorphism.
Integrated AI conversational prompts with offline fallback heuristics.
Conducted rapid iterative UI polish, accessibility checks, and element streamlining.

Quick Start (Run Locally)

No Node.js build pipeline or compilation steps needed. Simply clone and run:

# 1. Clone the repository
git clone https://github.com/rajukanna/care.git

# 2. Navigate to the project directory
cd care

# 3. Open in your favorite browser
# On Windows:
start index.html

# Or run with any local static HTTP server:
npx serve .
# or
python -m http.server 8000

Open http://localhost:8000 to start planning your garden and getting your hands in the soil! 🌿

SafeBite

Raju — Sun, 04 Oct 2026 07:57:29 +0000

SafeBite is a full-featured, zero-anxiety desktop meal planner built specifically for my friend Buddy, who suffers from severe dietary triggers and allergies to three of the most pervasive staples in Indian and vegetarian cuisine:

🚫 Paneer (Indian Cottage Cheese)
🚫 Curd / Dahi (Yogurt)
🚫 Brinjal / Baingan (Eggplant / Aubergine)

The Problem It Solves

For someone with these specific intolerances, deciding what to eat every single day is a stressful minefield. In traditional home cooking and restaurant menus, paneer, curd, and brinjal are frequently hidden — blended into makhani gravies, used to tenderize marinades, whisked into chaats, or roasted into mixed vegetable curries.

My friend was experiencing chronic decision fatigue, repeated accidental exposures, and the frustration of repetitive, bland meals.

The Solution: SafeBite

SafeBite transforms daily meal planning from a chore into a joy:

100% Active Allergen Guard: Every single recipe and suggested meal plan is mathematically and culinarily audited to ensure zero trace of Paneer, Curd, or Brinjal.
One-Click Auto-Plan Safe Week: Automatically populates 28 balanced meal slots (Breakfast, Lunch, Snack, Dinner across Monday–Sunday) in one click with zero allergen overlap.
Culinary Substitution Playbook: Embedded guidance on how to substitute textures and flavours without feeling like you're missing out (e.g., golden pan-seared turmeric tofu for paneer, tangy blended cashew-lemon cream for curd, and roasted tender zucchini for brinjal).
Consolidated Grocery List & 1-Click WhatsApp Export: Aggregates weekly ingredients into a categorized shopping list that can be copied directly into WhatsApp or printed for a hassle-free market run.
Warm, Calming Desktop Aesthetic: Crafted with warm cream, apricot, and deep forest teal accents with high-res food photography, instant slot swapping, and persistent offline storage.

Demo

Live Repository: github.com/rajukanna/SafeBite
Zero-Setup Double Click: Open (https://rajukanna.github.io/SafeBite/)directly in any modern browser (Chrome, Edge, Brave, Firefox, Safari).
Windows Desktop App (PWA): SafeBite includes a complete manifest.json — open in Edge or Chrome and click "Install SafeBite" to run it as a standalone, borderless Windows desktop application with taskbar pinning.
Native Desktop Window (Electron): Run npm start to launch SafeBite as an independent 1280×820 desktop window.

Code

The complete source code is hosted on GitHub:

👉 https://github.com/rajukanna/SafeBite

rajukanna/SafeBite
├── index.html        # Desktop workspace layout (Sidebar, Recipe Grid, Planner, Profile, Modals)
├── css/
│   └── styles.css    # Responsive design system, warm apricot/cream palette, glassmorphism
├── js/
│   ├── recipes.js    # Curated allergen-safe recipe database with macro stats & instructions
│   ├── app.js        # Screen navigation, LocalStorage persistence, modal controllers
│   └── planner.js    # Weekly scheduling engine, grocery aggregation & WhatsApp formatter
├── main.js           # Electron desktop wrapper
├── manifest.json     # PWA desktop installation manifest
└── package.json      # Dependencies and desktop startup scripts

How I Built It

SafeBite was engineered using an agentic AI pair programming workflow alongside modern, standards-based web technologies:

AI-Assisted Culinary Knowledge Engineering:
- Designed a safe recipe matrix auditing Indian and global comfort dishes against the three allergen triggers.
- Built algorithmic swap logic that pairs dishes with culinary replacements preserving authentic taste and mouthfeel (e.g., using cashew cream and tamarind in Velvet Dal Makhani instead of butter and cream, or pumpkin and drumstick in Idli Sambar instead of eggplant).
Vanilla Web Architecture (Zero Runtime Bloat):
- Built with pure Semantic HTML5, Vanilla JavaScript (ES6+), and CSS custom properties.
- Zero heavy framework overhead — loads instantly with 0ms compilation delays.
Local-First & Offline Resilience:
- Full state persistence (localStorage) saves weekly schedules, bookmarked recipes, and custom allergen profiles locally on the device.
- Native fallback image handlers (onerror) ensure that recipe visuals load seamlessly under any network condition.
Desktop-Grade UX:
- Left-hand persistent navigation sidebar with live Allergen Guard status.
- Split-screen weekly planner with interactive meal swapping.
- Recipe inspection modal with 3 warm stat pills (Prep Time, Servings, Calories), ingredient checklists, and step-by-step cooking methods.

Why Does Open Innovation Matter?

Dietary restrictions, food allergies, and health concerns are deeply personal. When healthcare or wellness tools are locked behind closed proprietary APIs or costly subscription paywalls:

Privacy is Compromised: Users are forced to upload personal medical and dietary data to remote corporate servers.
One-Size-Fits-All Fails: Closed commercial apps cater only to generic Western diet categories (e.g., "Keto", "Gluten-Free") and completely ignore cultural, regional dietary sensitivities like Paneer, Curd, or Baingan.
Open Innovation Empowers Communities: By making SafeBite open-source, anyone in the community can fork this project to protect their own family members or friends — whether they need an onion/garlic-free Jain meal planner, a nut-free kid's lunchbox scheduler, or a nightshade-free autoimmune diet manager.

Open innovation proves that software built with love for one friend can instantly become a template that helps thousands.

My Agent Session

Developed iteratively with Google DeepMind Antigravity AI, moving from visual design mockups to a full desktop layout, allergen safety verification, culinary substitution playbook, and instant grocery exports.

Prize Categories

Hacktoberfest Weekend Challenge: Build for a Friend
Most Helpful & Life-Impact Project
Best Open-Source Desktop & Web Tool

📖 Complete Feature Guide

1. 🛡️ 100% Active Allergen Shield

Persistent protection against:

🚫 Paneer: 0% paneer used across all recipes; replaced with high-protein organic tofu or boiled chickpeas.
🚫 Curd / Dahi: 0% yogurt or curd marinades; replaced with tangy cashew-lemon puree or coconut cream.
🚫 Brinjal / Baingan: 0% eggplant; replaced with tender roasted zucchini, lauki (bottle gourd), or mushrooms.

2. 🍲 Curated Recipe Discovery (16 Custom Dishes)

Filter dishes by meal time:

Breakfast: Avocado Chickpea Toast, Moong Dal Chilla Crepes, Classic Indori Poha, Steamed Idli with Drumstick Sambar.
Lunch: Creamy Palak Tofu, Amritsari Chana Masala, Kashmiri Rajma Bowl, Crispy Bhindi Do Pyaza.
Snacks: Roasted Makhana Crunch, Sweet Potato Wedges & Guac, Sweet Corn & Pepper Chaat.
Dinner: Velvet Dal Makhani (Cashew Cream), Matar Tofu Curry, Thai Red Coconut Curry, Sesame Garlic Soba Noodles, Golden Lauki Kofta Curry.

3. 📅 Interactive Weekly Planner (Split-View)

Switch between days (Mon–Sun) with instant slot updates.
One-click "⚡ Auto-Fill Full Week" to generate 28 verified meals.
Quick "Swap" button on any slot to cycle through safe alternatives.
"Shuffle Today's Meals" for fast daily variety.

4. 📚 Culinary Substitution Playbook

5. 🛒 Consolidated Grocery Aggregator & WhatsApp Share

Consolidates all ingredients across the 7-day plan.
Removes duplicate items and formats quantities clearly.
1-Click WhatsApp Copy: Formats a clean shopping list ready to paste directly into WhatsApp or messaging apps:

  🛒 SafeBite Grocery List for Buddy
  🛡️ 100% Free of Paneer, Curd & Brinjal

  Produce:
  • 2 Sweet potatoes
  • 1 Avocado & 2 Limes
  • 1 bunch Fresh spinach
  • 1 Zucchini

  Pantry & Protein:
  • 200g Firm Tofu
  • 1 cup Chickpeas (Kabuli Chana)
  • 1/2 cup Cashews (for dairy-free cream)

🚀 Running Locally

Option 1: Browser (Zero Setup)

Simply double-click or open index.html in your favorite browser.

Option 2: Progressive Web App (PWA)

Open index.html in Microsoft Edge or Google Chrome.
Click the Install icon in the address bar.
SafeBite will launch in a clean, standalone desktop window.

Option 3: Electron Desktop Window

If you have Node.js installed:

git clone https://github.com/rajukanna/SafeBite.git
cd SafeBite
npm install
npm start

📄 License

This project is open-source under the MIT License. Built with ❤️ for Buddy during Hacktoberfest.

Hacktoberfest

Raju — Fri, 02 Oct 2026 15:49:27 +0000

Hello everyone!!!