Your idle USDC has earned0x742d…FaEd
$47.23
over 14 days · across 3 strategies tested
AgentFloatVol. I · MMXXVI
Demo modeAgent active
Live
Vault TVL$9,700testnet demo
Active——
Best shadow——
Last epoch32s ago970 total
№ 01 · The product
Yield routing that learns and ships its own upgrades.
Out-of-range LP capital flows into a vault that runs multiple strategies in parallel. An LLM proposes new ones every hour. Only proven winners ship — and you choose how involved you want to be.
Total proposals
0
LLM-generatedPromotions executed
0
On-chain migrationsAgentFloat pools
1
v4 hook-enabledStrategies tested
0
0 live · 0 retiredHow the hook works
Capital flow, in real time.
Contract
LP
adds liquidity
afterAddLiquidity
Contract
AgentFloatHook
0x5Ba6…4580
vault.park()
Contract
FloatVault
0xbF06…a6f4
Active
Active strategy
Earning real funds
Shadows
0 shadows
Tested in parallel
AI proposal
LLM proposing next
Bankr Gateway · ~hourly
When price moves out of an LP's range, the hook routes the idle USDC into the vault. The vault deploys it to the active strategy while scoring shadows against the same conditions. The on-chain consecutiveWins counter is the trustless gate — anyone can call promote() once a shadow earns it.
Strategy deck
Every strategy the AI has tested, as a card.
No strategies registered yet.
Live strategy race
Real scores · re-evaluated every epoch.
No strategies registered yet.
How much should AgentFloat do?Demo · not persistent
Active: review · proposals ship after 1h if not rejected
№ 02 · The AI's notebook
What the orchestrator wrote, in its own words.
One strategy active. Others tested in shadow. Whichever proves itself becomes the next active. 4 entries so far.
13m ago·llama-3.3-70b-versatile·parameter variantPending
Deploy MockYieldStrategy with rate=2bps for higher accrual
Mock Yield Strategy has shown a 30x performance gap over Idle baseline (mean 112,167 vs 3,251 μbps) over 484 observations. The variance suggests room for a more aggressive accrual rate. Doubling the per-block rate is a low-risk shadow test — if it underperforms, the on-chain promotion guards will catch it before any capital migrates.
Proposed change
Deploy a new instance of MockYieldStrategy with RATE_PER_BLOCK_BPS=2 (current shadow uses 1). Register as shadow at strategy_id=4.
Expected outcome
Faster accrual curve. Should win head-to-head against the existing shadow within ~30 epochs at current block cadence.
▸ Evidence & risks
Evidence: ~/brain/wiki/agentfloat-history.md — Mock Yield σ=91,802 over 484 obs · ~/brain/raw/agentfloat-strategy-scores.md tail
Risks: If block production stalls, accrual rate is meaningless. Mitigated by the existing scoring formula which uses block-delta math.
Auto-approves in 46m · current mode
38m ago·llama-3.3-70b-versatile·scoring changeApproved
Lower minEpochsConsecutive from 5 to 4
Over 970 score entries, no shadow has been promoted despite the Mock Yield strategy beating Idle in every comparison. The 5-epoch consecutive-win requirement may be too tight given current scoring cadence.
Proposed change
Edit ~/brain/wiki/agentfloat-scoring.md config block: set "minEpochsConsecutive": 4
Expected outcome
Promotion latency drops by 20%. Increased churn risk is bounded by minDeltaBps (still 10) and the active-age guard (still 100 epochs).
▸ Evidence & risks
Evidence: agentfloat-history.md reports 0 promotions despite consistent shadow outperformance
Risks: Slightly higher promotion frequency in volatile windows. Mitigated by unchanged minDeltaBps.
Approved — awaiting deploy loop
19h ago·llama-3.3-70b-versatile·parameter variantShipped
Deploy MockYieldStrategy variant at rate=2bps
First parameter sweep proposal — establish that the auto-deploy pipeline works end-to-end before proposing more aggressive changes.
Proposed change
Deploy MockYieldStrategy with RATE_PER_BLOCK_BPS=2.
Expected outcome
New shadow scoring against existing strategies starting next epoch.
▸ Evidence & risks
Evidence: agentfloat-history.md
Risks: Test fixture — retired post-deployment.
Deployed at 0xb74204…ac63bd as strategy id=3View tx →
2d ago·llama-3.3-70b-versatile·no actionAwaiting review
System healthy — no change warranted
Score variance is within expected bounds. Active strategy holding within design spec. Shadow strategies are accruing as designed. No drift in any metric exceeds noise threshold.
Proposed change
None — explicit assertion that current state is the right state.
Expected outcome
Continuity.
▸ Evidence & risks
Evidence: Last 240 epochs in agentfloat-history.md
Risks: None.
Pending — requires human approval
№ 03 · The proof
On-chain, in the open.
Six verified contracts on X Layer Testnet. Eight tests passing. One AI-generated strategy already shipped autonomously.
Deployed on X Layer
Strategy registry
- #1Idle USDC Strategyactive
- #2Mock Yield Strategyshadow
- #3Mock Yield Strategy v3retired
System
- Total epochs970
- Proposals14
- Promotions0
- Tests8/8
- Last epochjust now
Read more
- Source code →
- FAQ — how strategies work →
- Architecture →
- Viewing demo data · See real state