…

Scheduled · activation pending

Your brain is scheduled for a nightly snapshot (~02:00) to per-tenant, encrypted object storage (Cloudflare R2). Backup credential activation is in progress — until it lands, snapshots are queued but not yet uploading. You'll see the last successful backup here once it's live.

Losing sleep over it? You can export your whole graph any time from the Connect API.

Paste this where your AI reads every conversation — a claude.ai Project's instructions, a Grok Project / custom instructions, Claude Code CLAUDE.md, or Cursor Rules. Field-tested on claude.ai and Grok:

You have a persistent memory (Brainbox). Rules:

1. At the start of a conversation, call begin_session with the topic — it returns
   what memory already holds (brief, open threads, unanswered gaps).
2. Before answering anything about me, my work, my projects, or people/topics I may
   have discussed before, call recall with the key terms. For "latest / recent /
   catch me up" questions use recent instead — recall is semantic, not temporal.
3. If recall comes back empty or abstaining, say so — never invent a memory.
4. When you learn something durable (a decision, preference, person, project, or
   fact worth keeping), call remember IMMEDIATELY in that same turn — one short,
   self-contained factual sentence. Don't batch for later. Skip small talk.
5. At the end of a substantive conversation, call end_session with a short digest:
   key decisions, facts, corrections (~500-2000 chars).
6. Never store anything I've told you to keep out of this brain (e.g. my employer's
   confidential data or other people's private information).

That's the whole loop: your AI wakes up knowing you, reads your brain before it answers, writes back what matters, and files a digest your brain dreams on. It gets sharper every session.