Aivery.
BRIEFING · SPATIAL MEMORY · 2026

Your operation already
writes its memory.
Aivery recalls it.

Every inspection note, delay call, and handoff your crews send already says what happened, when, and where. Aivery turns that stream into operational memory you can query by place, by route, and by time — in plain language.

Proviso Joliet Pontiac Springfield Carlinville Madison Yd Vulcan Staging Yard — learned from memory RUN RC-4821 · CHICAGO → E. ST. LOUIS · ■ = memories on file
Live demo corpus: nine field events across six stops, plus one facility no map service has ever heard of.
The problem

Institutional memory rides in the cab

What your operation knows lives in radio calls, group texts, shift-change conversations, and the heads of your most senior people. It is written down constantly — and retrievable never.

So the same questions go unanswered every week: Has this crossing gate failed before? What usually goes wrong on the Springfield segment? What did the last inspector flag on this car? The answer exists. It's just three months deep in a message thread nobody can search by place.

And when a dispatcher retires or a driver moves on, twenty years of "which dock needs the short trailer" walks out the door with them.

The system

Memory with coordinates and a clock

Aivery is memory infrastructure for operations. Field notes and chat messages become structured memories automatically — each one stamped with when it happened and where (from the device that sent it, no forms, no dropdowns).

Then anyone — or any AI agent you run — can ask questions the way an ops person actually thinks: by facility, by corridor, by time window.

Responses above are real output from Aivery's spatial test runs — not mockups.

The private gazetteer

No map service knows your Dock 7. Your operation does.

Google can geocode "Springfield, IL." It cannot geocode the Springfield switching station, the north staging yard, or Dock 7 at the Peoria terminal — the places your people actually talk about.

Aivery learns them. When crews mention a facility while working at it, the name binds to its coordinates automatically. Your operational geography assembles itself — no configuration, no GIS project, no data entry.

Facilities learned from the demo corpus — automatically
Facility nameCoordinatesMentionsSource
Vulcan Staging Yard41.6100, −87.33503learned
Proviso Yard41.8897, −87.87502learned
Springfield switching station39.7837, −89.64372learned

Public places resolve against a 250,496-entry gazetteer bundled with the system — including 15,000+ US rail yards, stations, ports, and airports. Fully offline: no memory content ever touches an external geocoding service.

How it works

From message to memory to answer

Capture

Crews send notes the way they already do — chat, app, or API. Device GPS and time ride along automatically.

Extract

An LLM distills each message into discrete, durable facts. Verbatim details — names, weights, car numbers — are preserved.

Enrich

People, equipment, and places are indexed; facility names bind to coordinates as the corpus grows.

Recall

Query by radius, corridor, facility name, or time window — combined with meaning-based search across everything.

Runs in our cloud or entirely on your infrastructure. PostgreSQL + PostGIS at the core — boring, auditable, yours.

Evidence

Tested like infrastructure, not a demo

24/24
spatial scenario tests passing — radius, corridor, time-window, named-facility, and ranked recall at dense facilities
8/8
end-to-end conversational tests: natural field messages in, correct spatial answers out — including a 2,000-memory yard, ranked live
250k
offline gazetteer places — geocoding without sending your data anywhere
+3
all three metrics ahead of mem0, the leading memory API, on the LOCOMO benchmark*

* LOCOMO long-conversation memory benchmark, matched answer format: LLM-judge 0.758 vs 0.638, F1 0.461 vs 0.406, BLEU 0.384 vs 0.360. Full methodology in our technical paper.

Applications

Where place-aware memory pays

Recurring faults by location

"Third gate failure at this crossing in two months" stops being tribal knowledge and becomes a query.

Crew & shift handoffs

The next crew inherits everything logged on this route, this yard, this car — not whatever fit in a five-minute conversation.

Corridor incident review

Reconstruct any run end-to-end, in order, from the memories written along it. Audit trails assemble themselves.

Customer-site knowledge

Every delivery quirk — the dock that needs the short trailer, the gate code, the receiver who signs late — retained per site, forever.

Maintenance history in place

Ask what's been flagged within 500 meters of where your inspector is standing, before they climb down.

Agent-ready operations

AI dispatch and planning agents get the same recall your people do — through one API.

Pilot program

Founding Partner pilots — now open

We're onboarding a small number of logistics operators as Founding Partners: a scoped pilot on one route, yard, or fleet segment, running against your real operational traffic.

  • Working deployment on your data in weeks, cloud or self-hosted
  • Direct access to the founding team; your workflows shape the roadmap
  • Founding Partner pricing, locked in
or write to cmatsoukis@gmail.com — we reply same day.