Can AI replace StocksBrew?

Build me a personal US-stock research cockpit to replace StocksBrew. Requirements:

- Node 22 + Express + better-sqlite3 + node-cron, server-rendered pages on
  localhost:8090, no frontend framework.
- watchlist.json holds my tickers; npm run refresh and a daily 7am cron pull
  end-of-day prices from Alpha Vantage (key in .env), filings from SEC EDGAR
  (no key needed), and items from a curated RSS list in sources.json.
- Score each stock with transparent rules in one rules.js file (price vs 50/200-day
  average, new 10-K/10-Q/8-K filings, earnings-date proximity) and show an
  add/hold/trim stance with the exact rule hits that produced it.
- Every summary line cites the filing or article URL and its timestamp; nothing
  uncited, nothing invented.
- Alerts: per-ticker price threshold and earnings-date reminder, sent by email over
  SMTP creds in .env.
- Rate-limit and cache all external calls (Alpha Vantage's free tier is 25
  requests/day, plan the refresh around it), dedupe news items, and mark stale
  data visibly.
- Dashboard: one watchlist table with price, stance, last-filing link, and next
  earnings date; one detail page per ticker with score history.
- SQLite tables: tickers, price_snapshots, filings, news_items, scores, alerts.
  One file I can back up by copying it.
- No accounts, no telemetry, everything local except the documented API calls.
- Out of scope: intraday data, brokerage connections, trading, and editorial stock
  calls. Put a clear not-investment-advice notice in the README along with setup,
  API limits, and the cron line.