Show HN: Argot, a Rust AI guardrail based on your codebase AST patterns

We have lots of benchmarks for new frontier LLMs (SWE benchmarks etc) to make them score on the "best code". In large codebase, the best code is the one that matches the codebase own voice and conventions, because that's the mental model of the team.

Ingesting a full codebase explicit/implict patterns in an agent windows to make them match the codebase doesnt work: too much context, hallucinations, ...

So I built this free/open source project, your codebase is a golden mine of AST code patterns that makes its unique voice, Argot learns them and then allows you to enforce them proactively or defensively.

Show HN: Argot, a Rust AI guardrail based on your codebase AST patterns
argot.tmonier.com

Thank you very much ! :) The idea was indeed to not rely on LLM to watch LLMs, also making it pure stats allow ultra fast feedback loop. I tried a lots of different techniques, but well refined stats outperforms all neural network techniques