Gecko — strategy layer for trading agents

The strategy layer your
trading agent is missing.

A seven-voice oracle that cites its sources, surfaces dissent, and refuses to answer when the corpus is too thin to call it.

Get early access to the oracleSee an example verdict

First ten builders run free. Solana wallet optional.

● V1 advisor in waitlist · MCP-ready

verdict envelopekamino · dex · as_of 2024-08-12

q: Is the JLP-USDC vault on Kamino worth depositing right now? (entry, 2024-Q3)

verdictdeferconf 0.55

0.42 — corpus too thin for directional call

citations · 5

  1. [1]Kamino vault docsprotocol_native · 0.72
  2. [2]Howard Marks — On Riskinvestor_canon · 0.41
  3. [3]Kamino governance forumprotocol_native · 0.39
  4. [4]Berkshire 2008 letterinvestor_canon · 0.28
  5. [5]Damodaran — Implied ERPinvestor_canon · 0.22

surviving dissent · 2 voices

> Two voices argue the protocol's incident-free track record offsets the audit gap; the panel could not resolve this against the corpus.

blocker · what would change the answer

  • · Will the Kamino protocol secure a credible audit report within the next month?
  • · Can the total value locked (TVL) in the vault increase significantly in the coming weeks?

Live envelope shape. Verdict and citations from an actual S24 evaluation run.

Grounded

Cited or it didn't happen

Every verdict ships with the exact chunks that backed it and the dissent that didn't win. If a claim isn't grounded in the corpus, it isn't in the answer.

Calibrated

Defers on thin evidence

When the panel can't find enough to call it, the verdict is defer — with a blocker question naming what would change the answer. No confident hallucination, ever.

Composable

One oracle, any skill

Callable from Claude Code, agent runtimes, CLIs, and whatever you ship next. We're the grounded-knowledge layer that other skills call — not a closed app.

How it works

Four steps, one envelope.

  1. 01

    Ask in plain language

    Send a question — "Is the JLP-USDC vault on Kamino worth depositing right now?" — through the skill surface or the CLI.

    gecko_trade_research(idea="kamino jlp-usdc entry")
  2. 02

    Seven voices debate the corpus

    A panel of seven specialist voices retrieves over investor canon (Marks, Damodaran, Berkshire letters) and live protocol data, then debates the question adversarially. Dissent doesn't get smoothed out — it gets cited.

  3. 03

    Verdict with calibration and citations

    You get a single verdict (act / pass / defer), a confidence band the panel calibrated against its own track record, and the source chunks that drove the call. Dissenting voices are preserved with their evidence intact.

  4. 04

    Settle the session

    Pay per session via x402 on Solana when live billing is enabled. Today, early-access cohorts run in stub mode at no charge.

Honest state

We defer when the corpus is too thin to call it.

And we tell you what's missing instead of inventing an answer. Every shipped verdict is scored on a rubric that grades citation relevance, hallucination, dissent grounding, and confidence calibration. The numbers are how we know the wedge is real.

From S24 evaluation run · the panel deferred on this query because protocol-specific corpus coverage was below threshold.

verdict envelopekamino · dex · as_of 2024-08-12

q: Is the JLP-USDC vault on Kamino worth depositing right now? (entry, 2024-Q3)

verdictdeferconf 0.55

0.42 — corpus too thin for directional call

citations · 5

  1. …

surviving dissent · 2 voices

> Two voices argue the protocol's incident-free track record offsets the audit gap; the panel could not resolve this against the corpus.

blocker · what would change the answer

  • · Will the Kamino protocol secure a credible audit report within the next month?
  • · Can the total value locked (TVL) in the vault increase significantly in the coming weeks?

Grounded in

Built on a corpus people actually quote.

Howard Marks · Aswath Damodaran · Berkshire Hathaway letters

Pyth Network · Helius · Solana primary sources

Investor canon, 1977 — present

1.00

verdict accuracy

0.16

brier (calibration)

0.90

defer when thin

Pilot-scale (N=10). Eval JSONs published in the gecko-mcpay-api repo.

FAQ

Common questions.

  • V1 advisor mode ships across the next two sprints. The first ten builders on the waitlist get founder-onboarded the day it lands; the rest enter cohorts shortly after. Early access is free.

  • Not in V1. V1 is advisor-mode — verdicts, citations, dissent. Execution adapters (OKX, Backpack, SendAI) ship in a later version behind explicit user opt-in. We don't take custody and we don't claim PnL.

  • Gecko is a Claude Code skill. Read app.geckovision.tech/skill.md in any Claude Code session and the oracle becomes a tool you can call. Direct API access via api.geckovision.tech is available for early-access cohorts.

  • Early-access cohorts run free in stub-billing mode. Session pricing for the paid tiers will be announced before V1.0. We won't surprise the waitlist with a price tag.

  • Two structural differences. First, we retrieve over a categorized corpus of investor canon and live protocol data — not the open web. Second, the panel is built to refuse: when evidence is thin, the verdict is defer with a blocker question, not a confident guess. The rubric grades us on that behavior every release.

● Who builds this

Two builders. One repo.
Real on-chain receipts.

Ernani Britto

Ernani Britto

CO-FOUNDER · CTO

Leticia Almeida

Leticia Almeida

CO-FOUNDER · CPO

Early access

Get on the waitlist.

First ten builders run free. We'll email when V1 ships — no spam.

No spam. One email when V1 ships.