Skip to content

Air-gapped edge AI

Your data can’t go to the cloud. Your AI shouldn’t have to.

RAPTOR is a complete AI system in a single rugged case: LLMs, transcription, translation, and image and document analysis, running on hardware you own. Open it anywhere and your team is working within minutes, with nothing leaving the room.

Built for defence, government and regulated organisations whose data cannot leave their control.

Product render of the RAPTOR unit: a ruggedised transit case, lid open, holding a console and two compute nodes seated in cut foam

Product render: the standard two-node unit

Deployment
Under 5 minutes
Case open to first inference
Connectivity
None required
Air-gapped by design
Compute
Two nodes, room for three
NVIDIA GB10 Grace Blackwell
Data
Never leaves site
No egress, no telemetry
What it does

Ready to work the moment the case opens

Every capability ships installed and runs entirely on the unit. An operator deploys one with a single click on the console: no terminal, no network connection, no specialist on call.

Bespoke capabilities

Beyond the installed set, capabilities can be developed for a specific mission, data type or workflow and delivered to the unit the same way.

How the platform works
  1. 01

    LLMs

    Drafting, summarising and extracting from text, on large language models that run on the unit.

  2. 02

    Translation

    Text translation for operational documents, entirely on the unit.

  3. 03

    Transcription

    Speech to text across many languages.

  4. 04

    Image and document analysis

    Ask questions about a frame, a scene or a change between two, and turn scans and PDFs into searchable, structured text.

  5. 05

    Image generation

    Briefing visuals and synthetic training data, generated on the node.

Interactive

See RAPTOR in your own space

Load the 3D model to rotate it, or open it in augmented reality on your phone to place the unit at full size in your own room.

3D render of the RAPTOR unit: the transit case open, with the console and two compute nodes in foam

Still render. The 3D model is about 3.5MB.

General arrangement drawing of the RAPTOR unit: plan view of the open case with console and compute nodes in foam, plus front and side elevations
The unit

A transit case that is also the workstation

Closed, it travels in a vehicle or as freight. Open, the console and the compute nodes are ready to work.

Rated transit case, sealed when closed
IP67
LiFePO4 battery, with mains, vehicle DC and solar input
1 kWh
Unified memory across the standard two nodes
256 GB
Packed with two nodes, in a wheeled case one person can move
≈30 kg
Full specifications
Where it is used

Anywhere the cloud is not an option

Connectivity denied, degraded, intermittent, or not allowed at all.

Defence
Tactical edge compute for forward operating bases, with no link home.
Emergency response
A deployable command centre for disaster zones and search and rescue.
Industrial security
Monitoring critical infrastructure and remote assets without cloud connectivity.
Border and customs
Documents, manifests and imagery analysed at ports of entry, with no data sent to a third party.
Maritime and offshore
Inference on board, so only results cross a slow and expensive satellite link.
Regulated enterprise
Document review and analysis inside the compliance boundary you already operate.

How it is supplied

One unit, one agreement

RAPTOR is supplied as the hardware unit, together with an annual licensing, maintenance and support agreement. Every configuration is quoted for your workload.

Tell us what you need to process

We size and quote a configuration to your workload and, where your security posture allows, set up an evaluation on your own material.

sales@raptorai.ukHow the platform works