Ofrendalant: A Local AI Día de los Muertos Altar for Your Dead Bookmarks

Description and use

Ofrendalant transforms a list of dead bookmarks into a personalized digital altar, preserving privacy, eliminating API costs, and enabling offline interaction with archived content.

Problem

Digital bookmarks often become dead links, leaving users with a forgotten archive of lost websites.

Outcome

Ofrendalant turns a dead bookmark list into a personalized digital altar, preserving privacy, eliminating API costs, and enabling offline interaction with archived content.

Workflow

• Export bookmarks to bookmarks.html
• Run Ofrendalant locally (git clone, pip install, ollama pull, python -m app)
• Ofrendalant scans the file for dead links
• For each dead link, query Wayback Availability API and fetch closest snapshot
• Clean HTML with BeautifulSoup4 and cache text
• Generate a remembrance card using Ollama JSON mode
• Display cards on a digital altar UI
• Click a card to open an offline RAG chat that retrieves passages from the archived text

Evidence

Everyone carries a digital graveyard inside their browser—bookmarks saved 5 to 10 years ago where nearly half the links have rotted into 404 Not Found errors, expired domains, or vanished indie blogs.

Source

Instead of letting dead bookmarks rot in a forgotten folder, Ofrendalant: Scans your exported bookmarks.html to detect dead links (404s, DNS failures, dead servers, timeouts, and domains that now redirect somewhere else.

Source

Resurrects their memory via the Internet Archive's Wayback Machine API to retrieve the snapshot closest to the day you bookmarked them.

Source

Builds a candlelit Digital Ofrenda using a local open-weight LLM running on Ollama (llama3.2:3b / qwen2.5:3b) to write a warm remembrance card for each departed site—summarizing what it offered the web, why you bookmarked it, and when it passed away, with an epitaph and a small offering.

Source

Lets you "Commune with the Spirit" (Local RAG): Click any card on the altar to open an offline séance chat where the local model channels the archived text of the dead webpage, letting you query tutorials, essays, or memories from a site that no longer exists on the live internet.

Source