Skip to content

Platform · Deployment

Our cloud or your premises, the same platform

In our cloud or on your servers.

Run Dudoxx AI HMS in our cloud or on your own premises. Owners and IT leads choose where the platform and the patient data live, and every desk, from reception to accounting, works in the same workspace either way.

How a clinic chooses where it runs

  • Three ways to run

    The platform runs in our cloud, on your own premises, or as a mix of the two.

  • Your data, your server

    On your own premises, the records, the documents and the schedule sit on hardware the clinic controls.

  • Where the AI runs

    The clinical AI sits in the same workspace as the record.

  • On-premises project

    An on-premises installation is a project with a start, a plan and a handover.

Watch how it works

A narrated tour of the real screens, chapter by chapter.

Installing Dudoxx AI HMS — production edition

For architects and partners: cluster shapes, site checklist, topology, the install step contract, go-live checks, backups and handover.

Narrated in: English16 chapters

All manuals

How it fits into the platform

Dudoxx AI HMS architecture: one gateway, one clinical core, one patient record Clients (web portals on Next.js, desktop app on Electron, mobile app on Flutter) enter through a secure gateway into the clinical core built on NestJS (EHR, scheduling, documents, billing, messaging). Seven AI assistants work inside the core and use self-hosted language models. The core calls four processing engines (FastAPI, LiveKit) and stores clinical data in the FHIR R4 patient record, one partition per clinic, plus clinic data (PostgreSQL), files (MinIO) and a knowledge index (Qdrant). Data services run in containers. The platform runs as SaaS, on-premises or hybrid. AI ASSISTANTS · INSIDE THE PLATFORM Toucan first orchestrator Condor plans · asks · acts Falcon voice Parrot messages IBIS clinical guidance Phoenix help Sentinel paper to data plan · ask · act on the record PROCESSING ENGINES Private AI models self-hosted language models no outside AI provider Document reading scans to structured data FastAPI Document generation branded PDF output FastAPI Voice speech-to-text · text-to-speech Video visits consultations · meetings LiveKit PLATFORM · FROM THE SCREEN TO THE RECORD Clients web portals · desktop app Next.js Electron Secure gateway sign-in · roles clinic isolation Clinical core EHR · scheduling · documents billing · messaging NestJS Patient record FHIR R4 · one partition per clinic the single clinical source of truth Clinic data, files, index accounts · per-clinic storage search vectors PostgreSQL MinIO Qdrant YOUR INFRASTRUCTURE SaaS On-premises Hybrid FHIR R4 RESOURCES IN THE RECORD Patient Encounter Appointment Observation Condition CarePlan MedicationRequest AllergyIntolerance Immunization DiagnosticReport DocumentReference live updates · to every screen patient record and EHR trust boundary data store request
Dudoxx AI HMS architecture: one gateway, one clinical core, one patient record Clients (web portals on Next.js, desktop app on Electron, mobile app on Flutter) enter through a secure gateway into the clinical core built on NestJS (EHR, scheduling, documents, billing, messaging). Seven AI assistants work inside the core and use self-hosted language models. The core calls four processing engines (FastAPI, LiveKit) and stores clinical data in the FHIR R4 patient record, one partition per clinic, plus clinic data (PostgreSQL), files (MinIO) and a knowledge index (Qdrant). Data services run in containers. The platform runs as SaaS, on-premises or hybrid. AI ASSISTANTS · INSIDE THE PLATFORM Toucan first orchestrator Condor plans · asks · acts Falcon voice Parrot messages IBIS clinical guidance Phoenix help Sentinel paper to data plan · ask · act on the record PROCESSING ENGINES Private AI models self-hosted language models no outside AI provider Document reading scans to structured data FastAPI Document generation branded PDF output FastAPI Voice speech-to-text · text-to-speech Video visits consultations · meetings LiveKit PLATFORM · FROM THE SCREEN TO THE RECORD Clients web portals · desktop app Next.js Electron Secure gateway sign-in · roles clinic isolation Clinical core EHR · scheduling · documents billing · messaging NestJS Patient record FHIR R4 · one partition per clinic the single clinical source of truth Clinic data, files, index accounts · per-clinic storage search vectors PostgreSQL MinIO Qdrant YOUR INFRASTRUCTURE SaaS On-premises Hybrid FHIR R4 RESOURCES IN THE RECORD Patient Encounter Appointment Observation Condition CarePlan MedicationRequest AllergyIntolerance Immunization DiagnosticReport DocumentReference live updates · to every screen patient record and EHR trust boundary data store request
Dudoxx AI HMS architecture: one gateway, one clinical core, one patient record Clients (web portals on Next.js, desktop app on Electron, mobile app on Flutter) enter through a secure gateway into the clinical core built on NestJS (EHR, scheduling, documents, billing, messaging). Seven AI assistants work inside the core and use self-hosted language models. The core calls four processing engines (FastAPI, LiveKit) and stores clinical data in the FHIR R4 patient record, one partition per clinic, plus clinic data (PostgreSQL), files (MinIO) and a knowledge index (Qdrant). Data services run in containers. The platform runs as SaaS, on-premises or hybrid. AI ASSISTANTS · INSIDE THE PLATFORM Toucan first orchestrator Condor plans · asks · acts Falcon voice Parrot messages IBIS clinical guidance Phoenix help Sentinel paper to data plan · ask · act on the record PROCESSING ENGINES Private AI models self-hosted language models no outside AI provider Document reading scans to structured data FastAPI Document generation branded PDF output FastAPI Voice speech-to-text · text-to-speech Video visits consultations · meetings LiveKit PLATFORM · FROM THE SCREEN TO THE RECORD Clients web portals · desktop app Next.js Electron Secure gateway sign-in · roles clinic isolation Clinical core EHR · scheduling · documents billing · messaging NestJS Patient record FHIR R4 · one partition per clinic the single clinical source of truth Clinic data, files, index accounts · per-clinic storage search vectors PostgreSQL MinIO Qdrant YOUR INFRASTRUCTURE SaaS On-premises Hybrid FHIR R4 RESOURCES IN THE RECORD Patient Encounter Appointment Observation Condition CarePlan MedicationRequest AllergyIntolerance Immunization DiagnosticReport DocumentReference live updates · to every screen patient record and EHR trust boundary data store request
Dudoxx AI HMS architecture: one gateway, one clinical core, one patient record Clients (web portals on Next.js, desktop app on Electron, mobile app on Flutter) enter through a secure gateway into the clinical core built on NestJS (EHR, scheduling, documents, billing, messaging). Seven AI assistants work inside the core and use self-hosted language models. The core calls four processing engines (FastAPI, LiveKit) and stores clinical data in the FHIR R4 patient record, one partition per clinic, plus clinic data (PostgreSQL), files (MinIO) and a knowledge index (Qdrant). Data services run in containers. The platform runs as SaaS, on-premises or hybrid. AI ASSISTANTS · INSIDE THE PLATFORM Toucan first orchestrator Condor plans · asks · acts Falcon voice Parrot messages IBIS clinical guidance Phoenix help Sentinel paper to data plan · ask · act on the record PROCESSING ENGINES Private AI models self-hosted language models no outside AI provider Document reading scans to structured data FastAPI Document generation branded PDF output FastAPI Voice speech-to-text · text-to-speech Video visits consultations · meetings LiveKit PLATFORM · FROM THE SCREEN TO THE RECORD Clients web portals · desktop app Next.js Electron Secure gateway sign-in · roles clinic isolation Clinical core EHR · scheduling · documents billing · messaging NestJS Patient record FHIR R4 · one partition per clinic the single clinical source of truth Clinic data, files, index accounts · per-clinic storage search vectors PostgreSQL MinIO Qdrant YOUR INFRASTRUCTURE SaaS On-premises Hybrid FHIR R4 RESOURCES IN THE RECORD Patient Encounter Appointment Observation Condition CarePlan MedicationRequest AllergyIntolerance Immunization DiagnosticReport DocumentReference live updates · to every screen patient record and EHR trust boundary data store request

The same architecture with the technology behind each layer and the resource types of the patient record.

Open the full diagram (opens in a new tab)

Questions about deployment

Choose where your platform runs

Book a demo and we compare a hosted start with an installation on your own premises.