DigestAI news desk

Cut through the AI noise.

Society & Work3 min read

Survival LLM offers offline AI assistant with emergency guides

Survival LLM is a free, open-source AI assistant designed to function without internet access. It runs entirely on a user’s computer, answering questions about food safety, first aid, water purification, and repairs using trusted sources like Wikipedia, FEMA, CDC, and medical encyclopedias. The app includes about 930,000 Wikipedia articles, medical references, and repair guides, totaling 9 GB…

1 source HN 44

Key points

  • Free, open-source AI assistant runs offline with no internet dependency or data tracking
  • Includes **930,000 Wikipedia articles** plus medical, FEMA, and repair guides in a **9 GB** library
  • Adapts model size to user’s memory; larger models perform better but require more disk space

The app adapts to available memory, downloading a model sized to fit. Larger models perform better—an earlier test graded it correct on 22 blackout and first-aid questions—but all answers cite sources for verification. Setup takes 20 minutes to 2½ hours, depending on internet speed and hardware. It requires 64-bit Windows 10/11 or Apple Silicon Macs (M1 or newer) with macOS 14 Sonoma. Updates are available via the app, and battery usage is moderate: 100 W for answers lasting 5 to 40 seconds, allowing roughly 100 to 300 queries on a full charge.

Full story from brangus.io · via Hacker NewsOpen source ↗

Survival LLM: AI assistant and emergency library that runs on your own computer

brangus.io · 27 October 2026

Loading the full article…

This text was published by brangus.io. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

1source
Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Society & Work

All →

Related stories