I kept rewriting the same regex passes against LLM output. So I made a library.

I've been working on a few LLM-based projects over the last year. Sakhi , a Hindi voice-to-form pipeline for community health workers in India. A resume parser for engineering candidates. A couple of smaller things. Different domains, different models, different prompts. But there's a pattern: at the bottom of every pipeline, right before the model's output became "data we trust," I'd find the same kind of code. Strip markdown fences. Repair half-broken JSON. Trim runaway repetitions. Normalize