HP Developers Portal | Omnicept


With this SDK, XR developers building applications can take advantage of biometric data and HP's machine learning inference engine to enhance their user's experience.  Start your trial today!

Start developing now

Internet access is required to connect to Omnicept.

Step 1

Download the core SDK.  To access your 30-day trial for full access to the Omnicept inference engine continue to Step 2.

Step 2

Sign up on the Developer's Console to start your 30-day Trial and manage your Omnicept license.


Step 3

Setup your application and get the credentials.


Step 4

Start creating your awesome application on your favorite platform.



Step 5: Choosing the right license for your application

After your trial expires, your license type is changed to Core.  You can upgrade your Trial or Core by visiting the developer's console and select Academic, Developer or Enterprise depending on how you plan to use Omnicept in your application.

Help me choose my Omnicept license 

    Trial       Core      Academic *  Developer   Enterprise 
Eye Gaze (includes Foveated Rendering)
Heart Rate (HR)
Pulse Rate Variability   
Cognitive Load  
HP VR Spatial Audio  
SDK upgrades   ✔ **
Support (currently only supporting in English)
Online Self-Support
Premium Support        ✔ **

Core is supported in all countries.  Check latest full-license country availability.

*Academic: Only available for academic purposes, not for profit.

** The first year the Service Pack is included Enterprise, following years require purchasing a Service Pack

Learn more about license types.


Omnicept Overview



The Omnicept system is a wheel-and-spoke architecture with two main components:

  • Omnicept runtime acting as a local server to process and route sensor data among Omnicept clients

  • Various Omnicept clients that connect to the runtime and send or receive sensor data (i.e. your application)

Omnicept runtime

The Omnicept runtime is a system designed to connect sensors to applications running on a single PC. The runtime transports compact datagrams between Omnicept client processes. The runtime also hosts internal modules (on Windows, .dll files) that read and process incoming sensor data.


Omnicept Clients

A client is any process that connects to the Omnicept runtime. Omnicept client code may be written using the C++ or C# Omnicept APIs, exposing functionality to connect to the Omnicept runtime as well as create, send, and receive sensor datagrams. Datagrams sent by a client will be received by every other client. The runtime guarantees that datagrams sent by each client are received in the order they are sent. However, datagrams sent by two-or-more different clients are not guaranteed to be delivered in a certain order to a third client.


Data Privacy and Security


If you have spent time reviewing the Omnicept launch materials, you may already know about our data collection effort. To develop the AI that supports Omnicept, we collected data from more than 1,000 individuals across four continents over two and a half years. One point of pride for us is that we established a data privacy and security framework that carries over to the Omnicept platform. We believe individuals have the right to control their own data and we want end users to know what data is being collected about them and who has access to that data. Below are some of the specifics of the Omnicept data privacy and security framework.


Read HP Labs blog post on Data Privacy and Security 


Cognitive Load


In scientific terms, the amount of mental effort required to perform a task or learn something new is called cognitive load. Every person has their own information processing capacity (also called working memory capacity or short-term memory) and it is fixed, limited, and varies from person to person. Information processing capacity is like the amount of food a person can hold in their mouth at one time. Sure, maybe it is possible to fit 44 marshmallows in your mouth at once, but is it comfortable? Probably not. Is it an optimal way to eat? Definitely not. What about a single sesame seed? Would you even bother? Perhaps, but it would certainly be a waste of energy.

Read HP Labs blog post on Cognitive load