Someone Built an Open-Source 'Theoretical Mythos' to Reverse-Engineer Anthropic's Most Dangerous AI

In brief

• OpenMythos is a from-scratch reconstruction of the Claude Mythos architecture, built only from public research papers and educated guesses.
• Claude Mythos is Anthropic's most powerful model, locked away in Project Glasswing because it autonomously found 271 Firefox vulnerabilities and 32-step network attacks.
• The repo is theoretical scaffolding—code without trained weights. It mirrors a separate effort by Vidoc Security that reproduced Mythos's vulnerability findings using off-the-shelf models.

If Anthropic won't show you what's inside its most dangerous AI, somebody on GitHub will guess.

A developer named Kye Gomez has published OpenMythos, an open-source reconstruction of what he thinks Claude Mythos looks like under the hood. The repo has picked up over 10,000 GitHub stars in a few weeks upon release, and ships with an exhaustive “readme” file full of equations, citations, and a polite disclaimer that it has nothing to do with Anthropic.

It's speculation. But it's structured speculation, in code.

Here’s a quick refresher on what Mythos is: Mythos leaked into public view in late March, when Anthropic accidentally published draft materials describing it as the company's most capable model to date—a tier above Opus. The follow-up, Mythos Preview, turned out to be unreleasably good at cybersecurity.

Per Anthropic, Mythos found 271 vulnerabilities in Firefox during Mozilla testing. It became the first AI model to complete a 32-step corporate network attack simulation. Anthropic locked it inside Project Glasswing, a vetted coalition of about 40 partners, including Microsoft, Apple, Amazon, and the NSA.

The public never gets to touch it. So Gomez tried to figure out how it works.

OpenMythos's central guess is that Mythos is a Recurrent-Depth Transformer—also called a looped transformer. Standard models stack hundreds of unique layers. Looped models take a smaller stack and run it through itself many times per forward pass.

In other words, it’s the same weights going through more iterations. Deeper thinking, in continuous latent space, before any token gets emitted.

The repo argues this would explain Mythos's two strangest qualities: It reasons through novel problems no other model can crack, but its raw memorization is uneven. That's the architectural fingerprint of looping—composition over storage.

OpenMythos cites Parcae, an April 2026 paper from University of California San Diego and Together AI that solved the long-standing instability problem in looped models—a 770 million-parameter Parcae model matches a 1.3 billion fixed-depth transformer on quality, with predictable scaling laws for how many loops to run. The repo also borrows DeepSeek's Multi-Latent Attention to compress memory, and a Mixture-of-Experts setup to handle breadth across domains.