SPILLOVER Open copy lab
Copytrading powered by an onchain intelligence protocol.Live onchain

The edge should
spill over.

Choose a public wallet to follow. When it buys, Spillover opens the same trade from your wallet immediately—before AI can slow the entry. Choose how you follow it: regular copy, agent copy, or a split between both. Regular copy holds. Agent copy researches the already-open position, then keeps it or closes as soon as the entry confirms. Every consenting result improves the same global brain.

Start live copy ↗ Buy SPILL ↗ See how it works ↓

AT LAUNCH: NO WALLET ALLOWLIST. ANY CONSENTING SPILL HOLDER CAN SET A CAPPED LIVE-TRADING PERMISSION.

SAMPLE SHADOW COMPARISON / 024 NOT LIVE PERFORMANCE
RAW COPY+2.4%
AGENT PATH+4.1%
EDGE+1.7pp

Sample data only. These numbers are not live results or a performance claim.

00 / HOW IT WORKS

One whale buy.
Two immediate paths.

Pick regular copy, agent copy, or run both. The selected paths buy from the same onchain signal immediately. Only the agent path continues into research; its reasoning never delays the purchase.

PUBLIC WALLET WHALE BUYS ROBINHOOD CHAIN
REGULAR COPYBENCHMARK
BUY
HOLD
AGENT COPYGLOBAL BRAIN
BUY
RESEARCH
+ REASON
AFTER ENTRY, DECIDE
LOOKS GOOD KEEP
TOO RISKY CLOSE ASAP

Paper agent: no second spend. Simulates the same entry and decision.

Real agent: uses only its assigned share. A 50/50 split means $5 regular + $5 agent from one $10 budget.

Risk looks too high? Sell as soon as the entry confirms to limit further exposure.

01

You opt in first. The shared agent learns from your runs only after you sign consent. You can revoke it.

02

Every result teaches it. Wins, losses, kept positions, and fast closes all become evidence.

03

The agent has to prove itself. New policies stay in shadow until they beat raw copying on trades they never saw.

01 / GLOBAL BRAIN

Nobody starts
from zero.

CUMULATIVE BY DESIGN

With consent, every run reports back what the source did, what the agent changed, and what happened after costs. Validated lessons become one shared policy, so every later trade inherits the network’s full learning history.

HOW THE NETWORK LEARNS

One global loop. Every tokenholder contributes. Every tokenholder benefits.

  1. 01 / SIGNALOBSERVE

    Analyze once.
    Share everywhere.

    Each new public source trade enters one global stream. Both entries start first; Spillover then analyzes the open agent position once and applies the post-entry decision across every eligible follower.

  2. 02 / BASELINECOMPARE

    Make the agent
    earn the change.

    Base copy and agent paths enter from the same signal. Gas, fees, slippage, agent closes, and avoided losses stay in the comparison.

  3. 03 / MEMORYLEARN

    Every outcome
    stays useful.

    Results mature at 5m, 30m, 4h, and 24h. Wins, losses, holds, and closes become cumulative evidence—not isolated anecdotes.

  4. 04 / POLICYPROMOTE

    Prove it unseen.
    Then ship it.

    A new policy reaches live decisions only after enough matured outcomes, an unseen holdout, positive confidence, and no extra drawdown.

THE COMPOUNDING UTILITY

The network learns once.
Every holder gets the update.

That is the flywheel: more consenting use creates more paired outcomes; more outcomes produce better-evidenced policies; every approved policy makes the same shared brain more useful to the entire network.

05 / TEACH THE BRAIN

Bring an insight.
Prove the edge.

Your insight enters quarantine. Add a public evidence link and explain what the chain data may be missing. It is shadow-tested first and cannot change live policy by itself.

AGENT EDGE

Beat the matched raw copy. Earn a share.

If your real agent leg outperforms its matched base copy after gas, fees, and slippage, its verified incremental edge can earn an allocation from the fee-funded epoch.

KNOWLEDGE EDGE

Improve the brain. Earn a share.

If your evidence survives review and measurably improves trades it never saw during training, its verified marginal edge can earn an allocation too.

10% of collected SPILL pool fees funds the Edge Pool. Your share is based on audited agent-edge and contribution points—not on simply submitting text. After a reviewed epoch's seven-day challenge window, eligible users claim ETH or SPILL directly from the immutable onchain escrow. No mainnet epoch is published today.

LIVE NETWORK LEDGERSYNCING
—SOURCE TRADES ANALYZED
—PAIRED SHADOW RUNS
—MATURED 24H OUTCOMES
PROMOTION GATE— / 200
02 / ADAPTIVE INTELLIGENCE

The flywheel
buys more brain.

Every agent position enters first. Contract and market checks begin immediately. Then the 40% compute treasury automatically unlocks larger research runs—from free onchain checks to a cached Nansen profile of the whale's cross-chain track record, Grok 4.5 with live web and X search, and eventually GPT‑5.6 Sol when sustained surplus can safely pay for it.

CURRENT RESEARCH MACHINEONCHAIN CORE
RESEARCH CASH AVAILABLE$0
FORECAST UNIQUE TRADES / MONTH1,000

Waiting for settled fee revenue or a reviewed bootstrap credit.

  1. 00 / ALWAYS ON

    Onchain Core

    GoPlus + DexScreener + GeckoTerminal + Blockscout + shared policy.

    $0 / TRADECURRENT
  2. 01 / SCOUT

    Grok 4.5 · Low

    Nansen whale profile + fast reasoning with live web search for current token-specific risk.

    $0.03 RESERVED / TRADECALCULATING
  3. 02 / RESEARCH

    Grok 4.5 · Medium

    Nansen whale profile + more reasoning turns with live web + X search and source citations.

    $0.09 RESERVED / TRADECALCULATING
  4. 03 / DEEP

    Grok 4.5 · High

    Nansen whale profile + deeper live web + X investigation when recurring revenue supports it.

    $0.20 RESERVED / TRADECALCULATING
  5. 04 / SURPLUS

    GPT‑5.6 Sol · High

    Nansen whale profile + frontier web research after operations and a three-month runway stay covered.

    $1.00 RESERVED / TRADECALCULATING

SUSTAINABILITY RULE Research is purchased once per unique source trade—not once per follower. Nansen's one-credit cross-chain wallet profile is cached per whale and never presented as Robinhood token data. A USD budget is reserved before every paid request, and xAI runs one search at a time within the tier's turn limit. Data, tool calls, and tokens settle against actual usage; failures debit the full reserve. Operations keep the greater of $75/month or 30% of available compute cash untouched.

03 / COPY LAB

Copy the trade.
Make the agent earn it.

The base and agent entries start immediately from the same source signal. The agent then checks GoPlus contract risk, live DEX market structure, the cumulative shared policy, and—when the compute treasury unlocks it—Grok 4.5 live web and X research. It keeps or closes the open position while both outcomes stay separate.

COPY LAB

Copy console

Robinhood Chain · 4663
SOURCE WALLET
7A
0x7A19…F42CSample wallet · preview data
82SAMPLE
30D RETURN+18.6%
WIN RATE61%
MAX DD−7.2%
TRADES43
SAMPLE COMPARISON

Shadow baseline vs agent run

SHADOW
PATHVALUERETURNMAX DDSTATE
Raw shadowComparison baseline $1,024.20+2.42%−4.8%RUNNING
Agent runShared policy v0 $1,041.10+4.11%−3.1%+1.69PP
×
SAMPLE AGENT DECISION · 14:32:08Closed MICA after a contract risk check

Both paths entered immediately. Post-entry research found elevated contract risk, so the agent exited while the base benchmark stayed open.

84%CONFIDENCE
YOUR GUARDRAILS
✓ Risk checks on✓ Direct Uniswap swaps✓ Starts from next trade

Illustrative interface. No wallet or API is connected on this page.

Homepage preview. Open the Copy Lab to connect an execution wallet and start a real monitor. Open copy lab ↗
04 / FEE ENGINE

Trading fees
pay for the product.

Normal SPILL swaps use a 1.00% Uniswap v4 pool fee. For the first 10 seconds after pool initialization, an adminless hook makes opening buys start at 80% and decay linearly to 1% to punish first-block sniping; sells remain at 1%. Every collected fee follows the same 40% compute, 10% Edge Pool, 30% founder, and 20% reserve split. The protected system is verified on Robinhood testnet. Mainnet is not deployed.

1.00%NORMAL POOL FEE
BEFORE PROTOCOL FEE
40%COMPUTE + OPS

Pays for the agent, wallet indexing, RPC, monitoring, and cloud runtime.

10%EDGE POOL

Paid through reviewed onchain epochs to users whose agent runs or contributed evidence produce verified incremental edge. Eligible ETH or SPILL is claimed after the challenge window.

30%FOUNDER

Fixed creator revenue, visible in the fee split.

20%PROTOCOL RESERVE

Covers audits, incidents, liquidity support, and operating shocks.

VOLUME MODEL

What does the flywheel produce?

MONTHLY SPILL VOLUME$1.00M
SPILL LP FEES$10,000
COMPUTE$4,000
EDGE POOL$1,000
FOUNDER$3,000
RESERVE$2,000

Steady-state 1% illustration only; it excludes the 10-second launch-protection window. Real revenue depends on volume, protocol fees, asset prices, fee collection, taxes, and operating costs.

THE PREMISE
Whales leave a wake.
We build with what spills over.

Big traders already leave their moves onchain. Spillover lets tokenholders copy those moves, compare them against one shared agent, and turn every result into a lesson the next person gets for free. Token volume pays the bill.

Start live copying ↗