Agent Debate Consensus — AI skill for Claude Code

Agent Debate Consensus

**Put 4+ AI models in one room and make them debate any topic. You moderate. They argue, challenge each other, and find consensus — live, in real time.**

**[Try the live demo at lryq.com](https://lryq.com)** — no signup needed, works instantly.

🇬🇧 [English](README.md) | 🇷🇺 [Русский](README.ru.md) | 🇺🇦 [Українська](README.uk.md)

    

**v2.5.2** — Rewrote every line of welcome-screen copy in EN/UA/RU to sound like a human wrote it. No more "multi-agent platform" / "unified gateway" / abstract bullet lists — concrete examples, plain words, and a voice you'd actually use in conversation.

---

What Is This?

When you ask ChatGPT or Claude a question, you get **one answer from one model**. That's one perspective, one set of biases, one reasoning style. You have no idea what you're missing.

Agent Debate Consensus changes that. You pick a topic, select 2–8 AI models (like Claude, Gemini, Grok, Kimi), and they **debate each other in real time** — arguing, challenging weak points, and building on each other's ideas. You watch the conversation unfold token by token, and you can jump in at any moment to steer the discussion.

**Think of it as a roundtable of AI experts that you moderate.**

What can you use it for?

• Making better decisions — Before committing to a strategy, let 4 AI models stress-test it from different angles. Weak assumptions get exposed fast.
• Exploring complex topics — Ethics, politics, technology trade-offs — see all sides in one conversation instead of asking each model separately.
• Understanding where AI disagrees — When models can't reach consensus,