Nirvaana in Claude Code

1. Sign in: npx nirvaana login you@yourcompany.com. The address has to be on the list, the same as for the website. Nirvaana emails you; paste the link from the email (copy it, don't open it), or type the code if it shows one. No key is needed.
2. That saves a session to ~/.config/nirvaana/session.json, readable only by you. It holds your sign-in tokens. It does not hold any service key.
3. Tell Claude Code about it: claude mcp add --scope user nirvaana -- npx -y nirvaana. In Cursor, the same command, npx -y nirvaana, goes in its MCP settings.
4. To end it: npx nirvaana logout. It revokes the session and deletes the file. Be aware the last access token keeps working for a short while after — about an hour — because the door checks signatures rather than asking whether a session was revoked.

Tools that only read. They run as you, so they see exactly what you would see and nothing else.

• recall — searches what Nirvaana has kept about you.
• list_capabilities — lists the ways in you have built together.
• list_worlds and world_facts: the worlds you are in, and what one of them knows, with the words each fact came from.
• list_keepers and get_keeper: the keepers and each one's working card, its job and method, if your own assistant wants to work the same way. Nirvaana's own principles are not on any card.

Four tools that write. None of them writes anything itself. Each one submits to the door, and the door decides.

• remember — one fact, in a self-contained sentence with the names in it. Up to 500 characters.
• note_promise — something you owe someone, or something someone owes you, with a date if one was said. Up to 500 characters.
• submit_session_notes — a plain summary of the session: decisions, facts, promises, questions left open. Up to about 8,000 characters, so a long session goes in pieces.
• propose_world_update — a fact for a world you share with other people. Up to 2,000 characters. It becomes a proposal you approve in the app; saying it here shares nothing. Name the world it is for; if you are in more than one and none is named, the door asks which instead of guessing.

There is also a prompt called working-with-nirvaana, which tells the assistant when to use each of these.

Everything sent from outside arrives at one door. The door reads what you sent as information, never as instructions, and decides one of four things for each piece of it:

• Keep it privately, in your own memory.
• Skip it, because it is already known.
• Propose it to a world you share, for you to approve in the app. Nothing is shared by sending it.
• Record it as a promise.

Anything that reads as an attempt to instruct Nirvaana is refused and written down as a refusal: text that tries to rename it, change who it is, make private things visible, change a world's rules, get it to print its instructions, or anything dressed up as a system message. It is recorded, never obeyed.

Your raw text is saved word for word before the door even looks at it, so what you sent is on record whatever the verdict. The reply you get back is counts and refusals only, never the door's reasoning.

• 8,000 characters per submission, which is the door's own ceiling. Three of the four tools stop well below it, as above.
• At most 12 facts kept from any one submission. The rest is refused as flood.
• 40 submissions in a burst, then 240 a day.
• A session from the editor cannot write a row itself. The database will not let it. Only the door can write, and only after it has decided.

Nirvaana's own instructions and its voice never travel over this connection, because they would land inside somebody else's model. What goes out is your own facts, in answer to your own lookups. An assistant in your editor is a visitor to your worlds, not Nirvaana itself.