Open-source AI tool turns messy documents into an auto-updating personal Wikipedia
thisdudelikesAI · x · 2026-10-19
An open-source GitHub project uses an LLM to turn scattered documents into a self-updating personal Wikipedia: it first extracts entities, concepts, and contradictions with existing pages, then writes entries, each with a sources field tracing claims back to the original file.
Notable engineering details: files are SHA256-hashed before ingest so unchanged PDFs are skipped and tokens aren't paid twice; deleting a source cascades cleanup of its summary page and dead wikilinks while shared entity pages keep other sources. Pages are ranked by four signals including direct links, shared sources, and common neighbors (Adamic-Adar).
More from Apps
- Boba, a 'social intelligence' AI, wins fans for actually being funny — gharik · 2026-10-23
- Eric Zelikman unveils social AI 'Boba', says it learned interaction 'from millennia of dreams' — gharik · 2026-10-23
- Boba team celebrates app launch, invites users to try it in group chats — gharik · 2026-10-23
- Account hacks surge: 6-step emergency checklist plus an AI audit prompt — petergyang · 2026-10-23
- 30 websites to download research papers for free, from arXiv to Sci-Hub — Faheem_uh · 2026-10-23
- Discord now renders Markdown file previews properly, a boon for AI workflows — The Verge AI · 2026-10-23