MONAI Deploy

MONAI Deploy aims to become the de-facto standard for developing packaging, testing, deploying, and running medical AI applications in clinical production. MONAI Deploy creates a set of intermediate steps where researchers and physicians can build confidence in the techniques and approaches used with AI — allowing for an iterative workflow until the overall AI inference infrastructure is ready to move to clinical environments.


$ pip install monai-deploy-app-sdk

AI Deployment Workflow

MONAI Deploy provides all the pieces for an enterprise-ready deployment pipeline. You can also use each piece that you need and integrate it in to your own workflow.

1. App Development

Develop a MONAI Application Package

A Pythonic SDK to build deploy-ready AI Apps in Healthcare

2. Inference Service

Application Server to run your MAPs

RESTful service which will allow other users to make inference requests with our MAP using HTTP

3. Workflow Manager

Orchestrates based on the clinical workflow

Central hub for the MONAI Deploy Platform

4. Informatics Gateway

Facilitates I/O for DICOM and FHIR

Connects AI Applications to Healthcare Information Systems

Used Around the World

MONAI Deploy is used throughout the world and at some of the largest and well-known Medical Research Centers. Learn more about how those companies are using MONAI Deploy in their workflow today.

Use Cases:

AI Centre for Value Based Healthcare


AIDE, the AI Deployment Engine, is an intelligent tool that allows healthcare providers to deploy AI models safely, effectively, and efficiently by enabling the integration of AI models into clinical workflows.

Read More

AI Centre for Value Based Healthcare


FLIP, Federated Learning Interoperability Platform, ensures a high level of fidelity in AI output models compared to traditional aggregative data strategies because the data it trains on does not need to be anonymized before use.

Read More

Mayo Clinic


CAII, the Center for Augmented Intelligence in Imaging, at Mayo Clinic Florida has developed compatible infrastructure and software packages for seamless integration of imaging AI models into Radiology workflows with MONAI.

Read More


mercure, an open-source DICOM orchestrator that seamlessly integrates MONAI Application Packages (MAPs), streamlining the deployment of AI models for clinical integration.

Read More

Get Involved in the Community

Below are ways that you can start using, contributing, and interacting with other members of the MONAI Core community!


Start contributing to the MONAI Core repo by submiting a bug, requesting a feature, or starting a discussion today!


We have Jupyter Notebooks on how to get started with MONAI Deploy App SDK, creating your first classifier, setting up and deplying on MONAI Inference Service, and creating a segmentation app that consumes a MONAI Bundle.


Having trouble? Trying to find out where to contribute? Wnat to share your cool project? Join our MONAI Slack and chat with the community.


Ready to get started using MONAI Core? You can find all of our documentation to help get you started or answer any of your questions!