humansays acts as a specialized linter and guardrail for code produced by large language models. It performs static analysis on Python code, identifying structural problems and assigning a confidence score to each finding so reviewers can prioritize issues. The tool helps development teams maintain code quality when incorporating AI-generated code into their projects.
In the Code review & quality space, humansays takes a focused approach. It focuses on reviewing and catching structural issues in LLM-generated Python code before it reaches human reviewers. It is built as an open-source project for developers. humansays is open source under the MIT license. It runs on the command line.
rhawk117 builds and maintains humansays, and the product first shipped in 2026. Development happens publicly on GitHub with 12 commits in the last 90 days. Key capabilities include LLM Code Linting, Structural Analysis, and Per-finding Scoring.
Latest indexed changes and source events
Other apps tracked under the same category.
