Full Stack
RegretTracker
AI-Powered Expense Tracker with Personality
An automated expense tracker that turns bank email notifications into actionable insights with AI-powered analysis. Features a self-improving two-stage parsing pipeline, multi-channel ingestion, and a personality system that humorously roasts users for overspending.
Self-improving regex from AI results
Multi-channel ingestion (Gmail + Cloudflare + manual)
Two-stage parsing pipeline (regex → AI)
Key Features
- Two-stage transaction parsing: Stage 1 uses regex for fast/free parsing, Stage 2 falls back to Gemini AI with confidence scoring
- Self-improving system: AI generates new regex patterns from its own results for future emails
- Multi-channel ingestion: Gmail API OAuth sync + Cloudflare Worker email forwarding + manual entry
- Transaction deduplication across multiple Indian bank formats (Axis, HDFC, SBI)
- Supabase Auth with PKCE flow and real-time subscriptions for live dashboard updates
- Chart.js visualizations for spending patterns and trends
- AI personality feature: humorous spending roasts with daily/monthly summaries via cron jobs
Tech Stack
Nuxt 4Vue 3Tailwind CSS v4SupabaseCloudflare WorkersGmail APIOpenRouter (Gemini 2.5 Flash)Chart.js