Can I vibecode Recall?

Build a personal replacement for Recall in an empty repository. Use Next.js 15, TypeScript, SQLite, Drizzle ORM, Readability.js, and a local background worker; do not offer alternative stacks.
The core loop is: save user-provided content sources (URLs to articles, videos, or podcasts), extract readable text, summarize the content using a local or API-based LLM, build a linked personal knowledge graph by automatically identifying related concepts, and export the archive in open formats.
Make the first run work locally with one documented command. Store all user data locally by default and make export straightforward. Put secrets in .env, ship .env.example, and never commit credentials.
Support manual URL saving, RSS or Atom subscriptions, OPML import, and provide a simple bookmarklet or browser extension manifest for quick saving.
Fetch content politely with a clear user agent, rate limits, conditional requests, and robots-aware behavior.
Extract title, author, publish date, canonical URL, readable HTML, and prominent images.
Provide a clean UI with an inbox, unread queue, archive, favorites, tags, highlighted snippets, manual notes, and robust full-text search.
Automatically generate summaries and suggest tags or connections to existing saved items in the user's library.
Keep the original URL prominent and never attempt to bypass authentication or paywalls. Export OPML, bookmarks HTML, Markdown, and a complete JSON backup.
Include clear empty, loading, success, and recoverable error states. Add input validation, safe filenames, and graceful handling of unavailable AI APIs.
Write focused tests for the core text extraction and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps. Do not add accounts, billing, telemetry, or analytics.
Finish by running the tests and listing the exact commands used.