The problem you can’t see from your side
Your docs are written for humans — and they work for humans. But a growing share of your integrations are now attempted by AI agents, and for them the experience is different:- Agents mis-call you. Wrong parameter, wrong endpoint, an auth scheme inferred incorrectly from prose. On your side that’s malformed requests, retry storms, rate-limit pressure, and support tickets that read “your API doesn’t work” — when really, the agent guessed wrong.
- Agents can’t find you. An agent picks the API it can discover and call correctly today. If that’s your competitor, the traffic — and the integration — goes there. You never see the loss; it just never arrives.
- Your own changes break your integrators. A renamed field that no human would miss silently breaks every downstream agent. Their 2am incident becomes your support ticket and, eventually, your churn.
- A hand-rolled MCP server goes stale. Teams that ship their own agent surface cover a handful of endpoints, then drift out of date the next time the API ships.
What Gecko does about it
Gecko is the API comprehension layer for agents. Point it at your OpenAPI (or your docs — no spec needed) and your whole surface becomes question-shaped, first-call-correct agent tools: auth handled invisibly, operations an agent can’t satisfy hidden, everything provable offline first.See the problem on your own API — free, one session
We run the comprehension scorecard against your live spec: how an agent experiences
your API today (raw docs) vs comprehended. You get the mis-call picture you currently
can’t see. The engine that does this is open source — you can run it yourself:
uvx --from "gecko-surf[serve]" gecko <your-openapi-url>.Become discoverable to agents
Gecko emits your API’s own agent-native surface —
llms.txt, gecko.json,
/.well-known/gecko.json, tools.md — generated from your comprehended surface,
hosted by you or by Cloud. Agents find you instead of guessing at you. See
Agent discoverability.Stay correct as you ship (Cloud — building)
Drift-watch re-comprehends your API when it changes and regenerates the tools —
so your next release doesn’t silently break every downstream agent. Alert fires
before your integrators’ prod breaks — every silent change today is their
incident and your ticket.
Who pays, in one sentence
The engine is free forever for builders; API providers pay a flat per-API subscription for hosted, drift-watched, agent-ready surfaces.Flat fee. Never a percentage of your revenue, never a cut of what agents pay you, never a public catalog listing you didn’t ask for. Illustrative shape on the Cloud page — prices land when Cloud ships.
Why this is measurable (unlike docs spend)
Human-docs spend is famously unattributable. Agent comprehension isn’t: a first-call-correct fix turns a failed call into a completed one — and if your API is x402-metered, into a settled one. The delta is visible per API revision. That’s the difference between a cost center and an ROI line.Honest status
The comprehension engine, the scorecard, discoverability artifacts, and the free self-serve flow are live today. Drift-watch, access analytics, and the hosted provider plane are building — with the first design partners, now. See Status and Roadmap for the exact line.Bring your API
Get the free scorecard
Join the Discord and drop your OpenAPI URL — we’ll run the comprehension scorecard
on your API and show you what agents see.
Self-serve it now
Run the open-source engine against your own spec today — comprehend, serve over
MCP, emit your agent-native surface.