Can AI replace LLM Pulse?

Build a local, single-user AI visibility tracker for one brand.
Use Node.js 22, TypeScript, Express, better-sqlite3, server-rendered HTML, and vanilla JavaScript.
Bind the app to localhost:4173 and provide one documented command for the first run.
Keep MODEL_BASE_URL, MODEL_API_KEY, and MODEL_NAME in .env and ship a safe .env.example.
Support one JSON chat endpoint configured entirely through those environment variables.
Document the endpoint contract and isolate it behind one small adapter so it can be replaced later.
Let the user configure one brand, aliases, three competitors, and up to 25 prompts.
Run prompts manually and on a weekly local schedule with a clear API budget limit.
Limit concurrency, retry transient failures, and keep failed prompts visible instead of dropping them.
Store every prompt, raw answer, model name, timestamp, latency, and error in SQLite.
Detect case-insensitive brand and competitor mentions using editable aliases.
Extract and normalize URLs from answers, then preserve the source answer for every citation.
Use one structured model pass to label brand sentiment as positive, neutral, negative, or absent.
Calculate mention rate, citation rate, competitor share of voice, and net sentiment with documented formulas.
Show current results, weekly trends, and a prompt-level evidence table on a compact dashboard.
Make every aggregate metric link back to the raw answers used to calculate it.
Export prompts, answers, mentions, citations, and weekly metrics as CSV files.
Add backup and restore commands for the SQLite database.
Do not add accounts, billing, teams, telemetry, web crawling, or an integration catalog.
Do not claim parity with managed multi-model collection, reputation workflows, traffic analytics, or production monitoring.
Write tests for alias matching, URL normalization, retry handling, and metric calculations.
Include a README with setup, API cost controls, data location, backup steps, and limitations.
Run the tests and production build before finishing, then list the exact commands used.