PrivacyNotes
English
System Català Čeština Deutsch English Español Français Italiano Nederlands Polski Português (BR) Português (PT) Slovenčina Svenska Türkçe Русский Українська العربية ไทย 한국어 日本語 繁體中文
Try the demo App

Help & FAQ/Extension & AI

Can I add notes from the command line (CLI) or an AI agent?

Ask your AI agent instead

Yes, with privacynotes, the PrivacyNotes command line interface (CLI). Anything that runs in a terminal can use it: your own scripts, scheduled jobs and AI coding agents. Pipe in Markdown, add a title and tags, and the note lands in the Agent folder of your notes, on all your devices after their next sync. privacynotes can only add notes: it cannot open, change or delete the notes you have. It needs Node.js 20 or newer, and it is part of Pro.

To set it up, open SettingsCLI in the desktop app and choose Turn on. Choose Install, which puts the privacynotes command on this computer, then Make a code. In a new terminal, run privacynotes login and paste the code. Then save your first note:

echo "# Hello" | privacynotes save

privacynotes has few commands, because it does one job. Each one prints a short card for a person, or one line of JSON with --json for a script:

  • privacynotes login connects this computer with a one-time code from SettingsCLI. Paste the code, or pipe it in.
  • privacynotes save note.md adds a note from a file, and privacynotes save alone reads Markdown piped in. --title sets the title, otherwise the first # heading or the first line is used. --tag work,ideas adds tags.
  • privacynotes status shows whether this computer is connected, and the last note it saved.
  • privacynotes logout disconnects this computer.
  • privacynotes mcp runs the command as a tool for an AI app with no terminal, see MCP.
  • privacynotes help (or privacynotes --help) lists every command and option, and privacynotes --version prints the version.

With an AI coding agent, connect privacynotes once on the computer where the agent runs, then ask in plain words: "Save this plan to my PrivacyNotes with privacynotes save, tagged project." The agent can read privacynotes --help for the details, writes the Markdown and pipes it in. The same command works in your own scripts and scheduled jobs:

  • git log --oneline -20 | privacynotes save --title "Recent commits" saves your latest commits.
  • pbpaste | privacynotes save --tag inbox saves what you copied, on a Mac.
  • privacynotes save --tag daily report.md in a nightly job saves a generated report.
  • A key you pick in your system's settings can run privacynotes save too, see Can I add a note with a keyboard shortcut, without opening the app?

A note holds up to 700 KB of Markdown, 20 tags and a 200-character title, and privacynotes checks this before it sends. It exits with 0 when the note is saved, 1 when the server refuses it, 2 for bad input, 3 when the computer is not connected and 4 when there is no network, so a script can react. A saved note waits, sealed, until one of your apps opens; if none does within 90 days, or you remove the computer first, it is deleted. To disconnect a computer, choose Remove next to it in SettingsCLI. What the command and an agent can see is in Can the command line tool or an AI agent read my notes?.

// Related questions

Can an AI app save notes to PrivacyNotes over MCP? Can I add a note with a keyboard shortcut, without opening the app? Can the command line tool or an AI agent read my notes? Can I use my own AI agent to get help with PrivacyNotes? Is there a PrivacyNotes browser extension? What can I do with Ninja, the Cmd+K box?

Help & FAQ

Answers and step-by-step guides: security, sync, pricing, and switching from other apps.

Still stuck? Ask your AI agent.

You get an answer in seconds instead of waiting for a reply. Your assistant reads all 173 answers and every import guide at once, so it can combine them, follow up on your question, and explain it in your own words. We never see any of it, because we do not run a chatbot.

  1. Copy the prompt.
  2. Paste it into ChatGPT, Claude, Gemini, or any other AI assistant.
  3. Ask your question, in your own language.
  4. Keep that chat open. Next time, ask straight away.
Show AI prompt 
Answer my questions about PrivacyNotes using only its help center, its changelog and its security documentation.

Start here: https://privacynotes.app/llms-index.txt
It lists every question with the page that answers it. Fetch the one or two that match mine.
If you can only make one request, fetch https://privacynotes.app/llms-full.txt instead.
If you cannot fetch a .txt or .md file, read https://privacynotes.app/help, https://privacynotes.app/changelog and https://github.com/LifetimeLabsHQ/PrivacyNotes.app instead.

For what changed, or where something moved, fetch https://privacynotes.app/changelog.md.

For how the encryption works, what the server can read, or how to check any of it yourself, fetch https://privacynotes.app/docs/index.md and follow it to one of the documents it lists. That index is a router: cite the document, never the index.

Rules:
- Use only those pages. If they do not answer something, say so instead of guessing.
- Never invent a feature, a menu path, a price, or a limit.
- End your reply with the "Source:" URL from the page you used, exactly as written.
- Answer in the same language as my question.
- Never ask me for my recovery phrase, my PIN, or the contents of a note.

If no question follows, ask me what I would like to know.

My first question:

Never paste your recovery phrase, your PIN, or a note into an AI.