Type: Software
Status: Alpha
Tech Stack: Python, FastAPI, SQLAlchemy 2.0 (async), aiosqlite, SQLite, Vanilla JS, Tailwind CSS, WebSocket
Problem Statement
Individual AI models have inherent biases and blind spots. Users receive only one perspective on complex questions, depending on the chosen model and provider. There is no simple way to systematically have multiple AI models with different ‚personalities‘ debate each other and consolidate through voting. Cross-provider comparisons require manual copy-paste between different interfaces.
Description
A web application where multiple AI agents with their own personalities and models discuss, debate, and vote on questions. Supports five providers (OpenAI, Anthropic, Gemini, Grok, Ollama), five discussion modes, 7 built-in tools (web search, YouTube transcripts, Wikipedia, PDF reader, Python sandbox, etc.), tool governance via voting, smart context window with rolling summaries, and real-time WebSocket streaming. Fully bilingual (DE/EN).
Use Case
Multiple AI personalities discuss a question from different perspectives and vote on the best answer.
Link: https://github.com/rawk7000/ai_council (private repo)
