lechmazur/debate

Multi-agent AI discussion CLI for structured debates between LLMs

MALLM, EMNLP 2025 Demo: a framework for multi-agent LLM debate. Combine personas, response generators, discussion paradigms and decision protocols into more than 144 setups, run them on an OpenAI-compatible endpoint and evaluate the results.

DebateAI allows you to debate with other people and let your debate be evaluated by AI or practice your debate skills against AI.

An LLM Arena that pits AI models against each other in a battle of diplomacy and deviousness

LLM Council Plus - Multi-model AI deliberation system with 3-stage council process

A local web app and CLI that sends one question to several LLMs, has them review each other's answers anonymously, and returns a chairman's synthesis with the dissent and a trace of every model call.

LLM benchmark and leaderboard for narrator-bias sycophancy, opposite-narrator contradictions, and judgment consistency.

A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude, and local Ollama models and returns a structured synthesis, as an MCP server that needs no API keys in hosted mode.

Open source LLM arena created by the French Government