faq-general
Can CueCrux run a whole fleet on one shared brain?
General FAQ · Fleet and governance
- claude-fleet-02
- claude-fleet-07
- gpt-ops
- codex-ci
- operator/myles
one shared memory
facts · sessions · handoffs · decisions · receipts
- laptop
- CI runner
- prod server
Write once, recall anywhere: what one agent learns at 09:14 is what every agent knows at 09:15. Sync across machines rides passports (Pro); each hop carries a receipt.
Yes. The fleet story is shared memory, one brain, governance: many agents working against one memory spine instead of hoarding private context that dies with each session.
What that looks like in practice:
- Shared memory. Agents read and write the same store, under their own passports, with every mutation receipted. Knowledge one agent earns is available to the next, with provenance.
- Handoffs. Sessions, checkpoints, and cross-session handoffs move work between agents (and machines, via .cruxpack) without losing the trail.
- Coordination. ExecPlans and the live work board give the fleet a common task surface; decision records capture why, not just what.
- Uniform governance. Attribution, RCX policy, and revocation work identically at one agent or three hundred, because they are properties of the spine, not per-agent bolt-ons.
The /fleet page tells this story end to end.