Safir Zeka (Safir Intelligence) is a “Machine Learning as a Service” product that is one of the currently being developed and maintained projects of B3LAB. Safir Zeka offers the most basic machine learning libraries and customized out-of-box models for software developers. It is also optimized for data scientists and end-users to provide a development environment for Machine Learning applications. It uses the power of container-based virtual environments to provide high availability and portability. Through Safir Zeka, software developers and data scientists are able to create their own customized procedures and install any new software in their own.


Safir Zeka provides the following pipeline:

  • Providing data from external sources,
  • Uploading data from local sources,
  • Data preprocessing and normalization,
  • Data visualization tools,
  • Building, training anf testing of machine learning models,
  • Easy deployment of developed models.

Safir Zeka has also out-of-box machine learning models for end-users. These models can be accessed via their APIs.

Regarding Safir Zeka, research and development activities are continuing in B3LAB and it is aimed to maximize user experience by adding new features.

Safir Zeka has been forked as Safir Zeka Avionics in order to meet the machine learning requirements within the scope of the TF-X Aircraft project, which was initiated to meet Turkish Air Force (TurAF) needs.

Safir Zeka Avionics is a machine learning library development project specialized for avionic data analysis and avionic artificial intelligence use cases.