---
id: "offline-mode"
date: "2026-04-18"
title: "Your LLM at 37,000 feet"
summary: "Cache your vault and a local model before boarding. Work with your own AI for the whole flight. The other first-class passengers are still waiting on satellite internet."
image: "/medias/offline-mode.png"
header: "Major feature"
tags: ["offline", "privacy", "vault", "productivity", "travel"]
---

You are somewhere over the Pacific, 7 hours into a 12 hour flight, working on a legal case your firm cannot afford to leak.

The CEO in the next seat is typing the same kind of question into ChatGPT, and every keystroke is traveling from the cabin network through a geostationary satellite into a third-party datacenter before the reply comes back: three networks he does not control see every word.

On your laptop, Daneel is running IBM Granite 4.0 at full speed against the 20 contract drafts you loaded before boarding.

**Your vault knows your research. Nothing leaves the aircraft.**

Offline Mode shipped today. One switch, full autonomy. Your documents, your local model, your knowledge graph, all answering as fast as your laptop can. Outbound network calls are blocked by design and verifiable in DevTools: when you say the extension is offline, you can actually prove it.

## Prepare before takeoff

Settings, Offline mode, Prepare for offline.

The panel shows you exactly what is ready and what is missing: vault documents imported, license token refreshed, language model downloaded, embedding model downloaded, static docs cached.

A single Cache resources button prefills the news, changelog, and documentation so you can still browse them at cruise altitude.

Models have to be downloaded separately in the Models section, because a multi-gigabyte pull is not something we do silently.

**Three rules of thumb from internal testing:**

- Refresh your license if it has fewer than three days left. The JWT caches for seven days, so a fresh refresh gets you comfortably to Tokyo and back.
- Make sure at least one vault holds the documents you actually want to work with. Marketing brochures are not useful when you need to edit a real contract.
- If you want the knowledge graph while offline, download the extraction model. It is optional, but the in-vault entity graph goes with it.

## What stays on, what goes off

Offline Mode is keyed on where the data would go, not where the call starts.

Ollama on localhost keeps answering, Docker-hosted MCP servers on your machine keep working.

WebGPU inference has never left your browser in the first place.

Anything that would reach a third-party API, Claude, Azure OpenAI, cloud storage, the license backend, analytics, markdown browser, the docs site, is blocked with a typed error that the UI knows how to recover from.

If you submit a question to Claude while offline, Daneel shows you an amber banner with a one-click switch to WebGPU, Gemini Nano, or Ollama, whichever you have configured. No silent failure, no retry loop against an unreachable host.

## Access from anywhere

Chrome extensions traditionally live inside a webpage.

That assumption breaks at 37,000 feet when the only webpage you have loaded is an airline entertainment portal.

The Open Vault button in the popup launches a dedicated Vault tab, a real extension page that hosts the full vault experience: search, chat, knowledge graph, import. It works on a blank new tab, on a chrome://error page, on a captive-portal holding page.

Three ways to flip Offline Mode off again:

- the popup card,
- the banner at the top of the Vault tab,
- or Settings from any webpage widget.

Wherever you get trapped, you are never more than one click from the exit.

## Closing thought

Everything we ship is aimed at one bet: that your best work happens when your tools, your data, and your model all stay under your control.

Have a good flight.

---

[Read on site](https://daneel.injen.io/news/offline-mode.html?utm_source=extension_news_reader&utm_medium=extension_settings&utm_campaign=extension)