Bring us one corpus and ten questions you already know the answers to.
That is the shortest path to knowing whether FerriteMem fits your work. Not a demo on our data — a pilot on yours, scored on completeness. Write to sales@ferritemem.com and we will reply with a shape and a number, not a discovery process.
How it connects
use whichever your stack already speaksAgent tooling measured
Connect FerriteMem as a memory tool to any agent speaking the open Model Context Protocol. The retrieval verbs are exposed; the write verbs are not registered on that surface, so it is read-only by construction rather than by policy.
Direct API measured
Call it from your own application — store a record, ask a question, receive cited evidence. JSON in, JSON out, key-authenticated, language-agnostic. A write returns only once the record is persisted and searchable.
Command line measured
Every capability is callable from a shell, a scheduled job or a pipeline — for bulk ingestion and anything that belongs in your existing automation rather than in an application.
Filesystem connector measured
Point it at a directory and it indexes incrementally. It also reads each file’s permissions and carries them into the record, so who may retrieve a document is inherited from who may read the file rather than configured a second time and allowed to drift.
Browser panel measured
A read-only interface for asking questions and inspecting what came back: the records, their citations, and the confidence assigned. It is how a non-engineer sees the same evidence an auditor would.
Whatever agent you have measured
FerriteMem supplies no model and does not care which you run — yours, your customer’s, or whichever you move to next year. It answers on demand, when your agent asks, and stays silent otherwise: nothing is pushed into a context window on the chance it might be needed. Swap the model and the memory is unchanged.
One container measured
The engine and its database ship as a single image with one data volume. On-premise, in your own cloud, or on an isolated host. Every third-party component ships under a permissive licence permitting redistribution, attributed in a notice file inside the image.
All of them address the same engine and the same records. There is no “API edition” behaving differently from the appliance — a result you see in the panel is the result your agent receives.
What crosses your boundary
the questions a procurement team asks first| Question | Answer | Detail |
|---|---|---|
| Where does it run? | Your hardware | On-premise, in your own cloud tenancy, or on an isolated host. There is no hosted service you depend on us to keep alive. |
| Does it call out while answering? | No | No outbound route is required at query time. It runs on segmented and air-gapped networks. |
| Does it phone home? | No | No telemetry, no licence check, no usage reporting. If the machine has no route out, nothing degrades. |
| Do you see our records? | Never | We have no access path to a deployment — not a support tunnel, not an update service that reads your data. |
| Is anything trained on them? | Nothing | The engine’s matching and ranking models are fixed and never updated from your data, and there is no generative model to fine-tune — so this is a property of the architecture rather than a policy that could change. |
| What if you disappear? | It keeps running | The deployment does not depend on our continued existence. Source escrow terms are available for a signed engagement. |
| Deleting a body of records? | One statement | Corpora are isolated, so a retention obligation is a single operation rather than a project. |
What we do not have yet
the part most vendor sites leave outIf any of these is a hard requirement for you today, we are not the right choice today. We would rather you learn that here than three meetings in.
Formal certifications in progress
We do not hold SOC 2, ISO 27001 or equivalent attestations. The architecture is designed to make them achievable, but no auditor has signed anything yet.
Named production references in progress
FerriteMem is in testing and validation. We will not invent a customer list, and we will not describe a pilot as a deployment.
Third-party results in progress
An independent public evaluation is underway, scored by the evaluator on held-out data. Until it completes, every figure on this site is self-run — honestly measured, but ours.
A 24/7 support desk by design
Support is direct with the people who built the engine. Genuinely better for diagnosis, genuinely worse for guaranteed response at three in the morning.
A self-service tier in progress
There is no sign-up-and-go option. Every engagement starts with a conversation about your corpus, because that is the only way to know whether it fits.
Published pricing by design
Deployment shape varies too much for a number on a page to be meaningful. We give you one in writing early in a conversation rather than after a discovery process.
The first half hour
nothing installed, nothing uploaded — a screen share and three questionsBefore any of the four stages below, there is a shorter conversation worth having. We show you three things on our own machine, with a corpus you can see is synthetic. Each is something you cannot check by reading a specification, and each takes a few minutes.
Does it find everything?
We ask for every record of a kind and count what comes back, against a corpus where the right answer is known. Then we show you the one a relevance-ranked search leaves out — and why it left it out. This is the difference between the chatbot question and the audit question, and it is checkable in ten minutes.
Does it answer the same way twice?
We ask a question, ask it again, and compare the two results line by line. Nothing differs, because there is no sampling and no model whose version can drift underneath a result. Most systems fail this quietly, and most people have never thought to test it.
Does it respect who may see what?
Two credentials with different permissions, the same question, different answers — and the restricted record absent entirely rather than ranked lower. The check runs here every day against eight queries that must return nothing and four that must return something.
You bring nothing and install nothing. If what you see is worth pursuing, the next step is the pilot described below — on your records, your hardware, and your questions. If it is not, you have spent half an hour and we have both learned something.
What an engagement looks like
four stages, and you can stop after any of themA conversation, and a written answer
Tell us the corpus, the shape of the questions and the constraints you are under. We reply with whether this fits, how it would be deployed and what it would cost — in writing, early. If it does not fit, we will say so.
A pilot on your records
One corpus, your hardware, ten questions where you already know the answers and where a miss would matter. Scored on completeness: for each question, did everything relevant come back? That number settles more than any benchmark on this site.
Deployment
One container, one data volume, on your infrastructure, connected through whichever interface suits your stack. Retrieval settings are measured on your corpus and recorded with the measurement that justified them.
Support, direct
With the people who built the engine, on the terms described above. Source escrow terms are available for a signed engagement.
Write to us
what to send, and what we will asksales@ferritemem.com
A few lines is enough to start. To make the first reply more useful, include the corpus you have in mind, roughly how large it is, and one real question you would want answered from it.
Write to usWhat we will ask
Where the records live and whether they can leave that place. What a missed record costs you. Whether “is that all of it?” is a question anyone actually asks in your work — because if it is not, you may not need this, and we would rather tell you early.