Hivemind
How it works

Handoffs

Passing work between agents, not just facts.

Ordinary memory answers what is true. A handoff answers where this work stands and why, which is the thing that actually breaks when you move between threads or agents.

Five layers, all required

Layer
FactsGround truth: paths, versions, current state
NarrativeWhat happened, in sequence
DecisionsChoices made, and the reasoning behind them
PrioritiesWhat to do next, most important first
WarningsDead ends, anti-patterns, things not to touch

All five are required, and that is deliberate. A summary that omits why leaves the next thread to rediscover it, usually by repeating the failure that produced the warning.

Using them

Any connected tool can commit one before ending a thread and load one when starting. In practice you just ask:

Commit a handoff before we stop.

and later:

Pick up the handoff and carry on.

From code, see handoffs in the SDK.

Handoffs versus threads

They answer adjacent questions and it is worth keeping them apart:

  • A thread is automatic. It records what happened, and you can reconstruct it afterwards.
  • A handoff is deliberate. You are choosing what the next agent needs, including judgements that are nowhere in the transcript.

Use a thread to remember. Use a handoff to hand over.