Evan1108-Coder

AI Debate Council — Data skill for Claude Code

Data community

Multi-agent AI debate app where model teams argue, challenge claims, track evidence, and produce judged verdicts with analytics.

How to install AI Debate Council

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Evan1108-Coder/ai-debate-council and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Debate Council does

Multi-agent AI debate app where model teams argue, challenge claims, track evidence, and produce judged verdicts with analytics.

Alternatives in Data

Clinical Decision Support — Evidence-based clinical decision support tools 6.4k ★
/recon — Run the full recon pipeline on a target and produce a prioritized attack surface 927 ★
Memex — Open-source, local-first AI journal app for iOS and Android 697 ★

README

AI Debate Council — Desktop App

Multi-agent debate engine: model teams argue opposing sides, challenge claims, track evidence, and produce judged verdicts with deep analytics.

![Status](https://img.shields.io/badge/status-beta-orange) ![License](https://img.shields.io/badge/license-MIT-blue) ![Backend](https://img.shields.io/badge/backend-Python%203.13%20%2B%20FastAPI-3776AB) ![Frontend](https://img.shields.io/badge/frontend-Next.js%20%2B%20React%2019-000000) ![Desktop](https://img.shields.io/badge/desktop-Electron-47848F) ![Models](https://img.shields.io/badge/models-28%20across%206%20providers-success)

Status: beta multi-agent debate app. It can help compare arguments and evidence, but it should **not** be treated as an authority on factual, legal, medical, or financial decisions. Verdicts are structured opinions, not proof.

⚡ TL;DR — what you need to know


What it is	A desktop app where AI teams (Pro vs Con) run a full structured debate and a Judge delivers an analytics-weighted verdict.
Install	Download a release installer, or clone + `dev.py` (see Quick Start).
Requires	Python 3.13 and Node 20+, plus at least one AI provider API key in `.env`.
First run	Launch → type a topic → watch the multi-round debate stream live → read the Judge verdict + Graphs & Statistics.
Two modes	AI vs AI debate, and AI vs Human debate training with a coaching Debate Trainer and a persistent profile.
Models	28 models across 6 providers (OpenAI, Anthropic, Google, Groq, MiniMax, Moonshot). Add only the provider key — models auto-detect.
Cost	Live per-turn / per-debate USD estimates in 9 currencies. You pay your own provider API usage; the app itself is free + MIT.
This branch	`master-app-interface` = Electron desktop (`.dmg` / `.exe`). For the browser version us