Code generators are powerful tools to boost developer productivity. But they are quite unpopular, because hard to create, maintain, and customize. aicodoo changes this by providing an easy and flexible "code generation by example" technology.
Low-code and no-code platforms are effortful to create, limited in customizability, and associated with vendor lock-in. With aicodoo, everyone who can provide example code can also easily create and maintain highly powerful, customizable, and independent low-code and no-code tools.
Start the demo tool, enter a domain model, and AI will accordingly generate the source code of a new application.
Under the hood: AI has been trained on existing example code and composes new application code from the learned scaffolding and boilerplates.
The following clip showcases an experimental IDE extension for adding artifacts to existing applications.
It's like an extremely powerful "code completion": Programmers just write very simple domain code and AI generates all the scaffolding and boilerplates from it.
The created code perfectly matches your existing architecture, programming stack, and coding style.
aicodoo is taught through Machine Learning on Source Code (MLonCode) to write scaffolding and boilerplate code.
The learned knowledge is used to write new code for already existing applications or to generate new programs.
Some AI technologies used by aicodoo: Code2Vec (Code to Vector Transformation), ML Algorithms, WEKA Machine Learning Toolkit, Apache Spark.
aicodoo learns and writes code by a given domain model. In the current status, only Entity-Relationship-Models are used.
aicodoo is language agnostic. It learns and writes any programming language and technology stack.
Current status: Research is done and AI technology is ready. Now trying to make some suitable tool out of it.