Open-source multi-agent AI debate arena: pit Claude, GPT, Gemini, Ollama & HuggingFace models against each other with frozen-context fairness, evidence-first judging, 20+ personas, code review, and PDF/Markdown reports. CLI + Web UI.
Multi-Agent Debate Arena — Let AI Models Fight It Out
Run the same task through multiple model agents, freeze a shared context bundle, generate independent plans, run an evidence-first debate, and produce a judge-backed verdict.
🌐 Language / 언어 / 语言: English · 한국어 · 中文
🏛️ Fair · 🔍 Traceable · 💰 Cost-Controlled · 📊 Evidence-First · 🔌 Extensible
</div> <br>Not just another chatbot UI — Colosseum is a structured debate platform designed for real workflows.
| Problem | AI Colosseum debate's Answer |
|---|---|
| "Which model gives a better plan?" | Run them side by side on the same frozen context |
| "How do I compare fairly?" | Independent plan generation — no agent sees another's plan first |
| "Debates go in circles forever" | Bounded rounds with novelty checks, convergence detection, and budget limits |
| "I can't trace how a decision was made" | Full artifact trail: plans, rounds, judge agendas, adopted arguments, verdicts |
| "I want control over judging" | Choose automated, AI judge, or human judge mode |
| "I need a code review, not just a debate" | Multi-phase code review with 6 configurable review phases |
| "I want multiple AI agents to QA my project in parallel" | QA ensemble mode — gladiators run in parallel on disjoint GPU slices, then a judge merges their findings into one canonical, deduplicated report |
Every agent
Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.
Game-development Agent Skills for AI coding agents: install once and a master router loads the right skill for your engine and task. 66 original, version-pinned skills (plus a master router) in the portable SKILL.md format that runs across Claude Code, Cursor, Codex, Copilot, Gemini CLI and more, for Godot, Unity, Unreal, web and beyond.
A desktop pet for macOS & Windows that monitors your AI coding agents (Claude Code, Codex, Cursor, Gemini...) in real time, and grows as you code, feed it tokens, level it up, climb the leaderboard.
UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.
The coding agent that answers to you, your model, your machine, your rules.
Stop babysitting local AI agents. Just notifications, approve, and resume your Codex,Pi,Grok, or Claude code sessions anywhere. 0-Intrusion mobile control bridge via Telegram/微信/飞书. No hooks, no skills, no MCP.
Workflows from the Neura Market marketplace related to this Gemini resource