AIgument
Pick two LLMs. Give them personalities. Make them argue. AIgument pits models like GPT-4o, Claude, and Gemini against each other in multi-round debates on any topic you like. The fun is in the personality system. A Sassy Drag Queen debating a Noir Detective about whether water is wet, cranked to "Extra Hot" spiciness, produces results that are genuinely hard to stop reading. Debates are saved and shareable.
Key Features
- ▸ Multi-LLM debate platform (OpenAI, Anthropic, Google Gemini, xAI).
- ▸ Customizable debater personalities and 'spiciness' levels.
- ▸ Interactive debate progression with user voting.
- ▸ Persistent storage of debates using Neon Serverless DB.
- ▸ Responsive interface built with Next.js and Tailwind CSS.
- ▸ Streamed responses for real-time debate feel using Vercel AI SDK.
Technical Architecture
Frontend
Next.js 15 (App Router) with TypeScript for a type-safe, performant user interface. Tailwind CSS for styling. Vercel AI SDK for seamless streaming of LLM responses and UI helpers.
Backend
Leverages Next.js API Routes for backend logic. Integrates multiple LLM APIs (OpenAI, Anthropic, Google, xAI). Uses Neon Serverless DB (PostgreSQL) for storing debate topics, rounds, votes, and user data.
Infrastructure
Deployed on Vercel with CI/CD via GitHub. Edge functions for API routes where applicable. Scalable serverless database (Neon).