Mireye (YC S26) gives AI agents cited facts about the physical world
Launch HN: Mireye (YC S26) – Infrastructure for Physical World AI Agents
Mireye is a YC S26 startup providing an API and MCP tools that let AI agents like Claude, ChatGPT, and Gemini ask questions about physical locations and get cited answers. It aggregates data from 85 authoritative sources, including USGS, FEMA, and NOAA, and offers endpoints for geocoding, lookups, fetching fields, proximity analysis, and requesting new fields. Each response includes source URLs, timestamps, and confidence scores, enabling agents to make decisions about data center siting, insurance underwriting, and more.
A field the catalog doesn't have yet can be requested — matched against the catalog first, and a genuine gap becomes one queued build that flows back into Mireye for every caller after.
- srikanthkasa
the problem usually isn’t missing facts. it’s that null means different things in different counties — no flood map vs no flood risk, wrong parcel, owner fields that don’t map cleanly.
if the API returns absent/failed instead of making the model guess, that’s actually a really good design choice.
curious how often those cases show up on normal residential parcels vs the messier commercial/infill sites.
- sgtwompwomp
Awesome work. If I understand correctly, your service essentially runs a bunch of web agents to maintain this dataset and keep it up to date and accurate, and we access through your API / MCP?
- cornholio
It would be good to also have a non-LLM version of the pitch, for some people building in the space it's a bad signal. It's associated with zero value "let my agent build something over the weekend" projects that all make these grandiose claims.