Build cognitive agents and environments
with Language-Driven Spatial Reasoning.

Titan SDK (Atlas)

The Titan SDK enables developers to build cognitive agents and environments for applications that require spatial capability.

The SDK provides the ability to customize the Titan graph when there is a need to convert the representation from abstract to concrete (3D).

To get started with Titan SDK, download Demo/SDK Package and follow the installation instructions.

Demo installation instructions

The MyHouse Demo release Beta v004 includes:

  • Atlas Documentation
  • Demo Environment Package
  • Demo Source Code Package

Atlas Documentation

To get started, please familiarize yourself with these step by step guides:

Demo Environment Package

The demo environment package contains the files needed to run the Atlas cognitive agent and environment.
In addition it also hosts an accompanying domain representing a rudimentary home kitchen setting.
This demo is not intended to show the full capabilities of Atlas, rather gradually familiarize the developer with the Atlas cognitive system.
Over time, more Atlas features will be unlocked to allow more comprehensive domains and capabilities.

Minimum Platform Requirements

  • Windows 10 (64-bit)
  • 2GB RAM
  • OpenGL capable graphics card
  • Mouse
  • Keyboard


Installing the demo environment package as a user:

To get started, decompress the demo environment package into any folder and run:


Installing the demo environment package as a developer:

Developers need to decompress the demo environment package into the root folder of the intended drive, so that the TitanVX folder is a direct child of the root.
For example: d:\TitanVX

Note that the current version of Atlas does not use any environment variables.


The MyHouse Demo is intended to demonstrate states, state changes, and state relationships. More features will be unlocked regularly.
Note: It is important to differentiate what Atlas can do from what the Kitchen domain, included in this demo, offers.

The following NLP statements are examples that are relevant to the Kitchen domain only. The more concepts Atlas learns the more statements it can process.

Turn off the main light
Turn off the light directly above the stove
open the fridge door
open the cabinet doors
close all the doors
make the table flat
the flat object is tan
move the chair on the other side of the tan object

Demo Source Code Package

The Demo Source Code Package contains the files needed to build the MyHouse portion of the demo.

We highly recommend reviewing the Atlas documentation to get started.

About the Demo Source Code

The source code is written in Visual C++ 2017.
If you plan on developing for Atlas, Visual C++ 2017 or 2019 is recommended.

Installing the Demo Source Package

Under normal circumstances, the demo source code package can be stored anywhere on the drive hosting the TitanVX (demo environment package).

There are build steps in the Visual Studio projects that copy the generated DLLs into their appropriate \TitanVX locations.

Developers can modify the post-build events in Visual Studio to point to an alternative folder should they install the environment in a location other than root.


The following describes the folder structure for the demo and corresponding source code:

/TitanVX                 <- Atlas and demo environment
~/OpenSource/Lib         <- Output libraries
~/OpenSource/MyApp       <- MyApp.exe solution
~/OpenSource/MyClient    <- Client codex solution
~/OpenSource/MyGLAPI     <- Rendering API headers
~/OpenSource/MyKitchen   <- Kitchen codex solution
~/OpenSource/Titan       <- Titan SDK header files and libraries
~/Externals/glm          <- GLM files


This demo uses g-truc GLM for matrix manipulation. It will need to be downloaded and installed in order to build the MyKitchen solution.

Installing GLM

GLM version is referenced within the demo source and needs to be extracted to the Externals folder as shown in the environment section above.

The demo source code package installation is complete and your system should be able to compile and run the software.

Getting Started

Welcome to the Titan API demo,

You have access to a cognitive agent with a pre-configured session timeout of 60 minutes. If you wish to continue testing after your session expires, you need to reload your web browser tab to access a new agent.

After your session expires or your browser is reset, we will automatically discard your previously loaded content.

Getting started with the Titan API Demo

Your agent does not have any information and does not know anything.

You can teach your agent by adding content (in the form of text) to its knowledge base.

Your agent will learn your content in real-time.

You can ask your agent questions regarding the content you provided.

  • If the answer is in the agent knowledge base, the agent will answer your question.
  • If the answer is not in the agent knowledge base, the agent will respond “I don’t know.”

The agent will continuously learn and answer more questions as you add content.

More Content –> Deeper Inference.


  • PoS:

Part-Of-Speech (PoS) tagger labels words as one of several categories to identify the word’s function in a given language.

  • Actions:

Titan Action System produces a table to identify the intents and actions in a given language.

  • Facts:

Titan Fact System produces a table to identify factual information in a given language.

  • Relations:

Titan graph Engine automatically constructs semantic representations from textual data sources.

  • Search:

Titan Cognitive Search Engine provides answers to inquiries about upload text. The questions should be in the form of: Who, What, When Where, and Why?

  • Instruct:

Titan Instruction System allows you to setup rules to govern and manage your Agent’s actions.

  • Insight:

Titan Insight System produces a report to identify knowledge either directly the provided text or inferred a combination of different content sources.