/jivan

Experimental neural static analyzer for Java programs, based on ML and LLM

MIT LicenseMIT

JIVAN (stands for Java and Ivan) is an experimental static analyzer for Java programs, powered by LLM and ML techniques.

Motivation. Machine Learning and Large Language Model techniques offer promising results in the area of code understanding. In some cases it can outperform traditional tools like SpotBugs, PMD, and Infer. Moreover, our analyzer tries to analyze the social aspect of coding (code authorship in Git, team responses, etc.). Besides that, here are no publicly available and easy to use static analyzers for Java, which would be based on some LLM/ML models.

How to use?

TBD..

How to contribute?

Fork repository, make changes, send us a pull request. We will review your changes and apply them to the master branch shortly, provided they don't violate our quality standards. To avoid frustration, before sending us your pull request please run full Maven build:

mvn clean install -Pqulice

You will need Maven 3.3+, Java 8+, and Python 3.11+ installed