The Node

Your firm's AIruns in your office.

You own the machine, the model, and the record of every decision it touched. Privileged material, protected health information, trade secrets, and client files never leave the building — and you can prove exactly how the work got done.

ComputeApple silicon or NVIDIA GB10
Memory64 to 128 GB unified
Modelsgpt-oss-120b + Gemma 4 · Apache 2.0
OriginOpen weights, American, run locally
SizesMac mini, Mac Studio, GB10
FootprintFits on a shelf, runs on a wall outlet
NODE power no outbound path unified memory shelf-size
What you own

Three things, and none of them can be taken back.

Every AI arrangement a firm can buy today is access to someone else's machine, running someone else's model, under terms that can change. This is the other kind.

One

The hardware

It's in your building, in your cabinet, on your power. Nobody can raise its price, deprecate it, rate-limit it, or turn it off.

Two

The weights

Open-weight models under Apache 2.0, pinned to a version in the build recipe. The model that answered in March is the model you can point to in March.

Three

The record

Every consequential release is sealed and stays with you. It doesn't live in a vendor's log, and it doesn't disappear if we do.

Three sizes, one system.

The machine is sized to the firm at assessment. The software, the review step and the seal are the same on every size.

Small office

Mac mini

M5 Pro with 64 GB of unified memory. Runs Gemma 4 for drafting, routing and reading scanned documents.

Mid-size firm

Mac Studio

M5 Max with 128 GB of unified memory and 614 GB/s of bandwidth. Runs gpt-oss-120b alongside Gemma 4.

Larger firm

NVIDIA GB10

128 GB of unified memory on the NVIDIA software stack. One serves a firm of twenty-five; two, clustered over a 200 Gb/s link, handle considerably more.

The upgrade path is a second box, not a server room.

What runs on it

A query enters. Nothing leaves without a person.

A question comes in and routes to the vertical that governs its domain. It answers from documents your firm owns — which is why it can't cite a case that doesn't exist. The model isn't recalling a citation from training. It's retrieving a document that's actually in your library.

Legal
Juris
Accounting & Tax
Numera
Insurance
Insura
Healthcare
Clinica
01 · ROUTE

The question finds its domain

A small fast model classifies which briefcase governs the question. The classification is itself a judgment, so it's recorded — including when it's uncertain.

02 · RETRIEVE

From your library, not the internet

A local index returns the relevant passages from documents your firm owns, tagged at ingest with where each one came from.

03 · DRAFT

Grounded, with sources shown

The answer is written with the source documents displayed alongside it. Nothing has left the building at any point.

04 · REVIEW

A person of record

Nothing consequential is released until a named human reads it. Not a checkbox — a person whose name goes on the result.

05 · SIGN

The release is the moment

The signature captures who reviewed, when, how long they held it, and what was in front of them when they decided.

06 · SEAL

Bound under SHA-256

LedgerGuard binds the document, its sources, the model, the signer and the moment into one verifiable record.

Everything runs on the node by default. A frontier model is used only by the firm's written choice, per matter, and that choice is recorded with the result.

See the full walkthrough →

The seal

Change one byte and it breaks.

The seal isn't a logo on a PDF. It's a cryptographic hash over everything that mattered at the moment of release — and whoever receives it can verify it with standard tools, without asking us for anything.

  • The document — the exact bytes that were released
  • Its sources — which of your documents it drew on
  • The model — name, version, and weights hash
  • The signer — the person of record who released it
  • The moment — when, and how long they held it
Document Sources Model + version Signer Timestamp SHA 256 SEALED a3f9…7c21 Verifiable by anyone, with standard tools.
The question is no longer whether AI can help do the work. It's whether you can prove how the work got done.
Delivery

Built, loaded and verified before it ships.

Delivered and installed in weeks, not months. Professionally provisioned and operated — not sold and abandoned.

01

Staged at the bench

The build is assembled, your library loaded, and the whole system verified before it leaves. The golden artifact is a hashed, versioned build recipe.

02

Your carrier is notified

Before first activation, the deployment model is disclosed to your professional liability carrier. Ahead of installation, not after.

03

Physically installed

A technician racks it and connects power and local network. Physical access only — the installer never has logical access to the system or your library.

04

Verified against your documents

Retrieval is tested on your own material at commissioning. That result is part of the record, not a marketing claim.

05

Operated, then handed over

An operator runs it inside the firm, learns how the practice actually works, and builds the library around it — until your people can run it themselves.

Own the node. Own the proof.

We should talk about your firm — what it handles, what it can't afford to leak, and what you'd need to show if someone asked.

Start the conversation