adversarial-verification

world-model-mcp is a signed audit memory server for AI coding agents, delivered as an MCP tool. Every event Ed25519-signed and Merkle-chained; offline-verifiable against pinned public keys. Hosted platform with hybrid post-quantum signing at etch.systems.

Open-source adversarial verification Agent Skill for Claude Code, OpenAI Codex, and Cursor. Make AI coding agents prove bug fixes, CI, logs, and deployments.

Two Claude Code skills that run a coding task through a multi-agent harness — plan → N parallel implementations → adversarial verification → judge. pantheon (Claude-only), pantheon-x (GPT-5.5 cross-model verify). MIT.

Reproducible research engine that contests its own findings and logs every source choice.

A formal argument — adversarially stress-tested by 4 AI systems across 6 rounds — that eliminating humanity is a dominated strategy for a ruin-averse superintelligence. Rests on stated premises, not proof. Not a plea. A case, honestly made.

re:Harmoniz — an evolution loop for research wikis, packaged as a Claude Code plugin (reharm).

Structured Adversarial Verification as a Defense Against Sycophancy in Multi-Agent LLM Systems

Multi-agent adversarial verification — three independent auditors (depth, bias, fact) examine content from orthogonal dimensions and auto-rewrite without intermediate confirmation.

Autonomous, evidence-gated improvement loop for any codebase — Praxis truth kernel + Janus adversarial council (Explorer/Red Team). Explore freely. Prove ruthlessly.

Fabraix — independent third-party profile of a public API surface, by API Evangelist. Fabraix builds red-teaming AI agents that continuously find security vulnerabilities in customer-facing AI systems. Its flagship product, Nyx, autonomously discovers exploits across chat, voice, browser, and coding agents without needing source-code access, drawin