Privacy

Your memory is yours.

Open Agentic Brain and Memory is built so that we never see your data. This page explains what the website and the software do.

Last updated 14 October 2026

This website

No accounts and no forms.
Visit statistics. We use Google Analytics to count visits and see which pages are read. It sets cookies and sends Google your IP address, browser details and the pages you view, under Google's privacy policy. We don't use it for advertising, and we don't combine it with anything else. It only loads if you click Accept on the cookie banner; until then nothing is sent to Google for analytics. Change your cookie choice.
The pages are static files hosted on GitHub Pages. GitHub may log your IP address when it serves them, under GitHub's own privacy statement.
Fonts load from Google Fonts, so your browser asks Google's servers for the font files.
The brain animation and every other effect run entirely in your browser.

It runs on your machine. Your memory lives in a local SQLite database in your home folder.
We run no server. Nothing you capture is sent to us, and the software has no telemetry or usage analytics.
Sync goes to your own GitHub. When you sync, the memory is encrypted with age and uploaded as a Release asset to a private repository in your own GitHub account.
Only you hold the key. The encryption key is kept in your operating system's keychain and is never uploaded. If you lose it, nobody, including us, can recover your memory.
Distilling uses your AI tool. To turn sessions into memories, Open Agentic Brain and Memory asks the AI tool you choose (Claude, Codex or Antigravity) under your own account, so that content is handled by that provider's terms.
Secrets are scrubbed first. API keys and tokens are removed before anything is stored or written into instruction files. This is best effort, not a guarantee.
Optional semantic search runs locally. If you turn it on, a small open model is downloaded once and then runs on your machine.