"embeddif.[ai]" is changing the way we think about AI. With the help of embeddif.ai, complex machine learning applications can be run locally on embedded systems - without the need for a cloud.

embeddif.[ai] represents a product portfolio developed by Fraunhofer IIS. The implementation enables fast development and low-power execution of AI algorithms directly on embedded hardware.

By implementing "embeddif.[ai] applications", it is possible to reduce downtime costs and increase service efficiency in various areas, for example, ranging from condition monitoring in Industrie 4.0 applications to sports applications. 

  • embeddif.[ai] Joint Lab: A quick collaboration to your executable AI
  • embeddif.[ai] Software Suite: We offer you a tool set for a quick start into development of embedded AI.
  • embeddif.[ai] Seminar: We provide you with comprehensive AI know-how in seminars tailored to your needs.
  • embeddif.[ai] Benchmark: We offer you well-founded selection options on combinations of hardware and AI that suit your needs.

Want the most efficient and fastest AI algorithms? - With the help of our product portfolio, you can develop unique AI applications specifically for your embedded hardware.

Benefits at a glance

Energy efficiency & resource conservation

The TinyML needs up to a thousand times less power to run ML applications compared to a standard GPU. The reason for this is, among other things, the local execution of the models instead of sending the data back and forth. For this reason, the TinyML devices can run for years without batteries, depending on the use case.

The size of the batteries required and thus the use of valuable resources is also reduced due to the considerable energy savings.


Since the model is run locally, in order to perform inference, the raw data does not need to be sent to the cloud first and then sent back when processed. This reduces output latency as well as communication bandwidth requirements, which in turn enables rapid response.

Independence, Privacy & Security

The user is not dependent on a cloud service provider. Since the data does not have to be shared with external parties, this point ultimately also contributes to the protection of privacy.

In addition, there is no dependence on a communication link. The risk of possible interference during transmission between the embedded system and the cloud is therefore eliminated.


The goal of "embeddif.[ai]" is to offer companies the possibility and ways to integrate AI technologies into their innovative products.

The following advantages result:



unique optimization local AI simple integration low hardware costs 
multi-criteria auto-ML for generating optimal AI pipelines. sensor-based AI runs on the device, cloud connection not required fast integration into existing systems, e.g. for additional features can be used on low-cost standard hardware


You want to run an AI based project and already know that the execution will take place on embedded hardware?   

You want to save energy when running your AI models and thus extend the runtime of your sensor system?

You have an idea for a battery-powered sensor system with AI functionality and need support?


On our tinyML page, you will find an overview of our offer.

Overview of concrete services

We offer complete packages that can be used as a whole or in components according to your requirements. All components can be combined in any way and adapted to your needs.

Joint Lab

We have very good experience with our customers in so-called "Fast Track Joint Labs": Together with you we develop a first solution for your embedded AI application within one month.

Typically the process is as follows:

  • Kick-Off
  • Selection of the required components of the solution
  • Fast Proof-of-Concept 
  • Box stop
  • Joint development of the final AI application

As a result, an executable solution is created and the know-how is exchanged during the project.

What do you get?

  • We guide you quickly through a joint project to the finished AI pipeline in C/C++ or Python
  • Jointly developed software components enable you to replicate the development process

If you already have a data set, a proof-of-concept can emerge after just a few days.

Your benefits

  • Know-how transfer happens during the project, not afterwards
  • Your employees become AI experts for processing your applications (integrated training)

Software Suite

Some of our customers increasingly rely on AI functions in their products. To enable them to act independently, we provide a software suite with which our customers can develop, evaluate and deploy embedded AI pipelines themselves.

What do you get?

  • Software suite in the form of coordinated Jupyter notebooks and libraries developed by Fraunhofer in the background.
  • Export of final AI pipelines for embedded systems.
  • Adaptation of the software suite to your problems, e.g. processing of specific data sources (sensor data, audio, video)
  • A half-day introductory workshop, if possible on the basis of your own data


  • We recommend the combination with the seminar to build up extended know-how.
  • Support for one year, if necessary also incl. development hours
  • We are also happy to support you during the final integration, e.g. in the form of a joint lab (see on the right side).

Your benefits

  • Enormous know-how transfer through best practices implemented in the software suite
  • Immediate ability to act in your AI projects
  • We do not leave you alone in your projects.


We offer a two-day Zero-to-Hero seminar in order to be able to implement the basics of machine learning in a practical way. The seminar can be tailored to you with the help of your data, if you want further training for your organizational unit.

What do you get?

  • With your data and wishes, we create an adapted version of our proven ML Seminar.
  • Your participating employees will learn the basics of machine learning including best practices in theory and with practical examples.
  • You will receive the seminar materials including the source code used (Jupyter notebooks).

Your benefits

  • Quickly build up knowledge in your own team
  • Knowledge that can be put into practice immediately

Potential analysis of your problem / your data set.

What do you get?

  • Report als PDF:
    • How well is your problem solvable?
    • Which AI processing chains meet your requirements?

What do you get?

  • Overview of power requirements / computational demand vs. achievable performance of AI pipelines on embedded hardware.
  • The report contains an overview of Pareto-optimal solutions with both classical ML and Deep Learning.
  • → How to decide:
    • Is there a compelling need for Deep Learning?
    • On which hardware does a solution fit best?

Your benefits

  • Quick assessment of the feasibility on your hardware
  • Early information on hardware decisions

Edge AI – small, private, energy-efficient

Intelligent and self-learning systems are becoming increasingly important in corporate processes, for example for the automation of processes or the analysis of large volumes of data. Until now, these intelligent systems have always had to be connected to a cloud, as this provides the large computing power for the mathematical algorithms. With Edge AI, short for Edge Artificial Intelligence, the next generation of intelligent systems is now coming into the house: The intelligence is being shifted directly into the end devices.

Privacy warning

With the click on the play button an external video from www.youtube.com is loaded and started. Your data is possible transferred and stored to third party. Do not start the video if you disagree. Find more about the youtube privacy statement under the following link: https://policies.google.com/privacy

Applications and demos

"embeddif.[ai] can be applied to many application areas. Some of these application areas are listed below. Through machine learning in embedded sensor modules, embeddif.[ai] is able to recognize, monitor and detect processes. Click on the links for more information about the applications.


embeddif.[ai] Tools

Machine learning in embedded sensor modules for cognitive hand tools to detect assembly processes and ensure quality.


embeddif.[ai] Sports

Machine learning in embedded systems, e.g. "wearables" for sports applications such as fitness, soccer, boxing or basketball.


embeddif.[ai] Condition Monitoring

Use machine learning in embedded systems to monitor states of plants and machines.


embeddif.[ai] Audio

Machine learning in embedded sensor modules for cognitive speech and audio analysis. embeddif.[ai] recognizes audio commands without cloud connection.