Ayush
Malviya

01

WhatsApp-native AI SaaS

450+ peak users · 98% delivery

Paused · Aug 2026

RemindMe India

Renewal reminders that live where India already lives — WhatsApp. Gyms, clinics and coaching centres run their members by chat: no app, no signup form. Built solo, end to end.

Owners manage members entirely through WhatsApp commands, and their members get reminded before a membership runs out. The same backend runs personal reminders in Hindi, Hinglish or English — even by voice note: GPT-4o-mini reads the intent, Whisper turns voice into text.

• Owner commands: ADD, MY MEMBERS, REMOVE, RENEW, BIZ STATUS, BROADCAST, with analytics for the owner
• Renewal reminders at 7d / 3d / 1d / expiry with DONE and SNOOZE buttons: 1,500+ sent at a 98% delivery rate
• Plans at ₹999 / ₹1,999 / ₹2,999 a month via Razorpay, a referral system and 5 approved Meta utility templates
• Privacy Policy, B2B Terms and a DPA live — accepted on payment, or signed as a PDF with the DPA SIGN command

• Node.js
• TypeScript
• Express
• Prisma
• PostgreSQL (Supabase)
• BullMQ
• Upstash Redis
• GPT-4o-mini
• Whisper
• WhatsApp Cloud API
• Razorpay
• Render
• Vercel

02

Real-time multiplayer game

431 tests · synced in under a second

Auction Night

A live football player auction where 2–10 friends bid from their own phones — synced in under a second. Join by link, nickname only.

All game logic is server-authoritative: every write goes through Postgres RPC functions, so simultaneous bids are resolved by the database, not the client. The timer lives in the database too, pg_cron sweeps expired lots every 5 seconds, and a dropped phone is back in the right state within 3 seconds.

• 11 Postgres RPC functions own every write; place_bid is atomic (row lock, base price, slot and budget checks), with row-level security on every table
• 678-player pool from a Python pipeline over Kaggle FIFA 20 → EA FC 24 data and Transfermarkt values, 110 curated legends, photos via the Wikipedia API, and its own rating formula
• 431 tests across four layers: 165 pgTAP, 173 Vitest, 13 Playwright E2E (5 simulated phones bidding at once) and 80 pytest
• Host controls (skip, pause, 60-second undo), 16 formations with position fit, bots that play with the same budget and info, and a 1080×1920 result card to share

• Next.js
• TypeScript
• Tailwind CSS
• Framer Motion
• Supabase Postgres
• Supabase Realtime
• PL/pgSQL
• pg_cron
• Python
• Vitest
• pgTAP
• Playwright

03

Hindi / Hinglish voice assistant

3-lane LLM fallback

TITAN

A JARVIS-style assistant for Windows: say "Hey Titan" in Hindi, Hinglish or English, and it does the job on the laptop — then answers in English.

Always-on speech recognition with voice activity detection, a fuzzy-matched wake word, barge-in and turn detection that waits out half-finished Hinglish sentences. The brain is an LLM with a three-lane fallback, and function calling turns each request into a real action on the PC.

• Three-lane LLM fallback — NVIDIA (Llama 3.3 70B), then Groq, then Gemini 2.5 Flash — switching silently when one fails
• Wake word "Hey Titan" with Levenshtein fuzzy matching for mishears, barge-in, and semantic turn detection for English and Hinglish
• Actions: open and close apps, search sites, play on YouTube, web search, weather, file search, volume, lock, sleep, screenshots — each reports success or failure out loud
• Memory that survives restarts (reminders, notes, long-term facts with atomic writes); the server listens only on 127.0.0.1 with CORS locked

• React
• Vite
• Tailwind CSS
• Node.js
• Express
• Whisper
• Llama 3.3 70B
• Groq
• Gemini
• Google Cloud TTS
• PowerShell