Vale construir sua versão de Auritrack?

Build me an AI expense tracker to replace Auritrack. Requirements:

- Local web app: Node + Express + better-sqlite3, server-rendered, binds to
  localhost only.
- Chat box on the home page: I type "lunch 12.50 at Chipotle yesterday" and the
  app calls the Claude API (claude-sonnet-5) with a tool schema to extract
  amount, payee, category, and date, then saves the transaction. Show the parsed
  result inline with an edit button so I can correct mistakes.
- Categories are auto-created the first time the model uses one; also give me
  plain manual add/edit forms for transactions and categories as a fallback.
- Statement import: upload a CSV or a text-layer PDF (use pdf-parse). Send rows
  or pages to the model in batches with a strict JSON schema, show everything in
  a review table before committing, and dedupe on date + amount + payee.
- Budgets: monthly limit per category with a progress bar that turns red on
  overspend.
- Reports: spending by category per month and a 6-month trend line with
  Chart.js, plus an "ask about my spending" box where the model writes a SQL
  query, runs it against a read-only connection, and explains the answer.
- Nightly copy of the SQLite file to backups/, keep 30.
- ANTHROPIC_API_KEY lives in .env; send the model only the rows a request
  needs and never log transaction data.
- Out of scope: bank sync, scanned-image PDFs, mobile apps, Telegram bots, and
  multi-user. Note in the README that imports cost real API money and roughly
  how much per statement.
- README: how to map my bank's CSV columns on first import.