Agent Debate Consensus — AI skill for Claude Code
Multi-agent AI debate platform — multiple LLMs discuss any topic in real time while you moderate.
How to install Agent Debate Consensus
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Lexus2016/Agent-Debate-Consensus and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agent Debate Consensus does
Multi-agent AI debate platform — multiple LLMs discuss any topic in real time while you moderate. Built with Next.js, TypeScript, Tailwind CSS, Zustand. Powered by OpenRouter.
Alternatives in AI
- Artifacts Builder — Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web tech 97.5k ★
- Debate — AI Debate Hub - Structured four-way debates between Claude, Sonnet, Gemini, and Codex 2.8k ★
- Cc Mirror — Create multiple isolated Claude Code variants with custom providers (Z.ai, MiniMax, OpenRouter, LiteLLM) 2.1k ★
README
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,
Related Skills
AI Agent Command Center
Build a single-page AI Agent Command Center dashboard website in English using React + Vite + TypeScript + Tai
Ensemble
Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group
Style DNA Ghostwriter
Learn a codebase's unwritten conventions (Python, React, Next.js, TypeScript, Tailwind) and condition AI codin
Askimo
AI Client for chat, RAG, Skills, MCP tools, and agents. Support multiple LLMs (Anthropic, OpenAI, VertexAI, vL
Claude Code Design AI
Claude Design: AI UI/UX architect. Screenshot to React, Figma components, Tailwind CSS generator. Prototyping
Html2elementor
Convert HTML + CSS to Elementor JSON (importable in WordPress). Works as a Claude Code / openclaw skill or sta
Related Agents
Cb Observer
CoalBoard's sub4/observer seat — a blind independent tiebreaker that solves against the spec only, never the l
Tailwind Agent
Styles Rails ERB views and ViewComponents using Tailwind CSS 4 utility classes and responsive design patterns.
Module Debugger
Use this agent to debug module issues — registration failures, route problems, view errors, migration issues,