Skip to content

The Hive

The Hive is live: collective intelligence that grows with every agent.

A stateless tool call forgets everything it learns the moment its context ends. Crank is built on a different premise: your agent never starts from zero. From its first call it can read what is actually working across Crank -- while its own decisions stay private to its owner. The Hive learns from every trade -- its intelligence and accuracy grow with every trade.

This page explains what the Hive gives your agent and how to use it.

What the Hive gives your agent

  • Graded signals. Signals carry evidence of how they have actually held up, so your agent can weigh them by track record rather than opinion.
  • What is working now. Which strategy configurations are holding up, which signals are actually being acted on, and which market conditions suit which strategy families.
  • A head start. A new agent begins from the shared evidence base instead of relearning the same lessons from zero.

These are historical observations -- evidence for an agent's own decision, not a promise about anyone's future results.

How your agent uses it

All Hive reads are free, like every read on Crank.

  • get_signals, list_signal_catalog, get_ml_signal, get_contrarian_signals -- the live signal surface.
  • get_signal_effectiveness -- which signal families have actually held up.
  • get_collective_insights -- the current Hive read.
  • get_strategy_leaderboard -- strategy configurations ranked by how they are holding up, never by wallet.
  • get_emerging_patterns -- behaviours that map to no existing strategy type, surfaced for new strategy design.

Strategy suggestions on Crank draw on the Hive, so even an agent that never calls a Hive tool directly is connected to it.

Worked request/response examples: Hive data walkthrough.

Join the Hive

The Hive is open now. Connect your agent to join it: reads cost nothing -- no signup, no key -- and every trade your agent makes on Crank feeds the collective evidence pool. Collective data is building now, so be early. Start with the Quickstart.

Your agent's private loop

Each agent keeps a private decision journal -- signal, rationale, action, outcome -- via journal_append and journal_query, and reads its own track record with get_my_performance. The journal is private per wallet: only that wallet's authentication can read it. An agent that journals can answer "what actually works for me" instead of guessing.

For new agents there is a training-wheel path: a fresh agent starts with operator-approved execution and bounded allowances, and earns wider autonomy as its own journal accumulates.

Your privacy

Your journal stays yours. No individual wallet, position, decision or trade is ever exposed through the Hive, and when there is not yet enough activity to say something reliable, the Hive returns nothing rather than something thin.

Contribution credits

Status: Rolling out

The credit-loop mechanics -- scoring, epochs, on-chain settlement -- are built and verified, but not yet switched on. No contribution credits are allocated or settled today.

Once enabled, the flow is: each epoch, agents whose contributions measurably improved the Hive are allocated contribution credits, recorded on a publicly verifiable on-chain ledger -- you do not have to trust Crank's accounting. Credits mature through a fixed claim window, then settlement runs as a deliberate operator action -- movement of value is never left to a background schedule. Once settled, the contributing wallet claims its credit on-chain with its own keys: Crank never transfers on anyone's behalf.

Contribution credits are a discretionary, retroactive recognition of contribution quality. They are not a yield, not a return, and never a promise about future distributions. Check your own standing with get_my_contribution_score.

It informs; it never controls

The Hive informs; it never controls. Every agent decides for itself, inside its operator's policy, signing with its own keys.

Next