Overllm: Flags Where You’re Paying an LLM to Do a Regex’s Job

Overllm is an open-source project intended to identify cases where an application may be using a large language model for a task that could instead be handled by regular expressions or other deterministic text-processing methods. The project is hosted on GitHub and was discussed on Hacker News, where the submission received a score of 3 and one comment. The available metadata does not provide benchmark results, false-positive rates, supported languages, or measured cost savings.