GitHub - codeintegrity-ai/mutahunter: Open Source Language Agnostic LLM-based mutation testing tool
github.com
Open Source Language Agnostic LLM-based mutation testing tool - codeintegrity-ai/mutahunter

Check out our open-source, language-agnostic mutation testing tool using LLM agents here: https://github.com/codeintegrity-ai/mutahunter

Mutation testing is a way to verify the effectiveness of your test cases. It involves creating small changes, or “mutants,” in the code and checking if the test cases can catch these changes. Unlike line coverage, which only tells you how much of the code has been executed, mutation testing tells you how well it’s been tested. We all know line coverage is BS.

That’s where Mutahunter comes in. We leverage LLM models to inject context-aware faults into your codebase. As the first AI-based mutation testing tool, Mutahunter surpasses traditional “dumb” AST-based methods. Our AI-driven approach provides a full contextual understanding of the entire codebase, enabling it to identify and inject mutations that closely resemble real vulnerabilities. This ensures comprehensive and effective testing, significantly enhancing software security and quality.

We’ve added examples for JavaScript, Python, and Go (see /examples). It can theoretically work with any programming language that provides a coverage report in Cobertura XML format (more supported soon) and has a language grammar available in TreeSitter.

Check it out and let us know what you think! We’re excited to get feedback from the community and help developers everywhere improve their code quality.

  • Killing_Spark@feddit.de
    0·
    5 months ago

    As the first AI-based mutation testing tool, Mutahunter surpasses traditional “dumb” AST-based methods. Our AI-driven approach provides a full contextual understanding of the entire codebase,

    This is where I call bullshit. The AST is a precise representation of the code which should be easier to analyse and modify instead of the raw text. If you only rely on processing the text I have a hard time believing your AI has a deep understanding of the contextual interdependencies of the different parts of the code.

    Edit: it kinda does use the AST if one of the preconditions is a treesitter grammar? Maybe the marketing wording is just very unfortunate?