Litmus
Litmus reads a scientific paper and tells you how much to trust it before you build on it.
Core trick
Runs statcheck, GRIM, and p-curve forensic checks in code, then Claude weighs them with citations linked back to source sentences.
Tags
Description
Litmus reads a scientific paper and tells you how much to trust it before you build on it. You give it a DOI, some pasted text, or a PDF, and it breaks the paper into its core claims, runs real statistical forensic checks in code (statcheck, GRIM, SPRITE, power, and a p-curve), searches the wider literature for work that supports or contradicts each claim, and then has Claude Opus weigh all of it into a calibrated replication likelihood. Every reason it gives is clickable straight back to the sentence it came from, and anything it can't ground, it throws away.
I started with preclinical cancer, where only 6 of 53 landmark studies famously reproduced, because that's where a wrong call costs the most: a bad target isn't caught until Phase II or III, years and hundreds of millions of dollars later. On a set of real papers with known outcomes, Litmus cleanly separates retracted, failed, and robust work, and it stays honest about its limits with confidence intervals. It also ships as an MCP server, so any AI agent can call it to check a result before trusting it. The goal is to make it the verification layer every AI scientist and human runs through.
README excerpt
<div align="center"> # 🔬 Litmus ### The trust layer for scientific evidence. *Litmus reads a scientific paper and tells you how likely its claims are to hold up, before a lab or a company spends years and millions building on them.* [](https://litmusresearch.org) [](LICENSE)     ### [▶ Try it live at litmusresearch.org](https://litmusresearch.org)  </div> --- ## The problem We're curing cancer on top of research we can't trust. When Amgen tried to reproduce 53 landmark cancer studies, **only 6 held up.** That's not a one-off: most published preclinical findings don't replicate, the US wastes an estimated **$28 billion a year** on research that won't reproduce, and roughly 90% of drugs entering clinical trials fail, with the number one reason being a lack of efficacy that often traces back to a target built on shaky biology. The worst part is *when* we find out. A result that was never real doesn't fail on day one. It fails in Phase II or III, years and hundreds of millions of dollars later, after patients have waited for a therapy that was nev