Privacy Policy
Applies to the MindMap Chat desktop and mobile app. Last updated with version 1.19.0, released .
The short version
MindMap Chat collects nothing. There is no account, no analytics, no telemetry and no server that stores your content. Your maps, notes and conversations are written to your own device, encrypted at rest.
Data we collect
None. We operate no backend that receives your content, and the app contains no analytics or tracking SDK.
Where your content lives
- Maps, notes and chat history are stored in a local database in a folder you choose.
- That database and the settings file are encrypted at rest with AES-256 (SQLCipher) using your passphrase.
- Nothing is uploaded to us. If you sync that folder with a cloud drive, that is your choice and your provider's terms apply — the contents remain encrypted.
Network connections the app makes
The app is usable entirely offline. It makes only these outbound connections, all of which you control:
| Connection | When | What is sent |
|---|---|---|
| Update check | On startup, if enabled (Settings → About). Can be turned off. | A request for the release manifest. No personal data, no account identifier. |
| Your AI model | Only when you use an AI feature. | The prompt and the relevant part of your map. By default this goes to your own Ollama or LM Studio server on your machine or local network, and never leaves your control. If you deliberately choose a cloud provider, it goes to them instead — see below. |
| Model download | Only if you ask the app to install a local model. | A request to the model registry. Nothing about you or your content. |
Cloud AI providers
The app is local-first, and stays that way unless you decide otherwise. Out of the box the AI runs against your own Ollama or LM Studio server on your machine or local network, and nothing you write is sent anywhere.
Claude (Anthropic) and OpenAI are available as an opt-in. They are never selected for you and never active by default. Choosing one opens a dialog naming the provider and listing exactly what would be sent, and until you accept it the AI features stay switched off for that provider.
If you do accept, this is what leaves your device when you use an AI feature: the outline of the map you are working on, the text and notes of the node you act on, and the messages in that chat. It is sent over HTTPS to that provider, processed on their servers, and handled under their privacy policy and terms, not this one. They bill you for it directly; the app is not involved in that, takes no commission, and never sees your account.
What does not change: your maps stay encrypted on this device, your API key is stored encrypted here alongside them and is never sent anywhere but to the provider it belongs to, and the app's logs record sizes and counts, never the content of a prompt. A ceiling on request size means a large map cannot be sent by accident, and an optional scrubbing pass can replace email addresses, IP addresses, file paths and similar identifiers with placeholders before sending — defence in depth, not a guarantee.
If a map must never leave your device, use Ollama or LM Studio. That is the only guarantee, and it remains the default. If you do want a cloud model, setting up Claude or OpenAI walks through it.
Who is responsible for what
MindMap Chat is not affiliated with Anthropic or OpenAI, and does not resell, host or intermediate their services. When you enable one, you are using your own account with that provider, and that is an agreement between you and them: their terms of service, privacy policy, acceptable-use policy, pricing and availability govern it. Any account, billing, quota or support matter is yours to take up with them directly — this app has no visibility into your account and cannot act on your behalf.
Warranty and liability are the licence's, not a second set of terms. This software ships under the Elastic License 2.0, whose No Liability section reads:
As far as the law allows, the software comes as is, without any warranty or condition, and the licensor will not be liable to you for any damages arising out of these terms or the use or nature of the software, under any kind of legal claim.
That covers anything that goes wrong when a provider is involved — outages, rate limits, models changed or withdrawn, refused or wrong answers, how the provider handles what is sent, a suspended account, or charges made to it — for the same reason it covers everything else.
Deleting a chat here deletes it here. Clear conversation removes the messages from this device's encrypted database and makes no network call — there is nothing to delete at the provider in the sense you might expect, because the API is stateless and keeps no conversation of its own. What it does keep is the requests already sent, for as long as its retention policy says. Nothing in this app can reach that; the provider's privacy policy governs it.
What the app does guarantee is narrow, and worth stating plainly: it will not send anything to a provider you have not selected and agreed to. The local runtimes remain the default and send nothing anywhere.
Read the provider's own policies before enabling this:
- Anthropic — Consumer Terms, Commercial Terms, Privacy Policy, Usage Policy
- OpenAI — Terms of use, Privacy policy, Usage policies
Semantic search
Search runs fully on-device using an embedding model bundled with the app. Your queries are never transmitted.
Children
The app collects no data from anyone, including children.
Changes
If this policy ever changes, the updated version will be published on this page.
Contact
Questions about privacy: [email protected]