Can AI replace BrandGEO?

Build me a local AI brand visibility auditor for one brand. Requirements:

- Node 22, TypeScript, better-sqlite3, a CLI. Local only, no accounts, no telemetry.
- brand.json holds my brand name, aliases, domain, one competitor, and up to 25
  audit questions (who is X, best tools for Y, X vs competitor, is X legit).
- `audit run` sends every question through OpenAI, Anthropic, Gemini, xAI, and
  DeepSeek APIs. Keys from .env; skip engines whose key is missing and say so in
  the report instead of failing.
- Store one immutable row per run, question, and engine: raw answer, model id,
  latency, error text. Never overwrite a previous run.
- Cap concurrency at 2 per engine and retry twice on 429 and 5xx with backoff.
- A separate scoring pass grades each stored answer 0-10 on six dimensions:
  recognition, knowledge depth, competitive context, sentiment, contextual
  recall, discoverability. Rubric text lives in rubric.md, scores must cite the
  answer sentence that justifies them.
- `audit report` renders a Markdown report: overall score per engine, the
  six-dimension table, competitor mentions, and every flat-out wrong claim the
  models made about the brand, quoted.
- `audit history` prints score per engine across runs from SQLite, so week two
  starts meaning something.
- Out of scope: white-label PDFs, multi-brand management, scheduled monitoring,
  and scraping the consumer web UIs. One brand, run by hand.
- README: setup, per-run cost estimate by engine, and a plain note that API
  answers only approximate what the apps actually show users.