Skip to content

Multi-model debate interface inspired by Andrej Karpathy Pro/Con/Judge agents with memory, uncertainty signals, and OpenRouter + Ollama support

License

Notifications You must be signed in to change notification settings

sjsreehari/debate-engine

Repository files navigation

LLM-Council

Multi-Agent Adversarial Debate System

Beyond single-model AI — structured argumentation for balanced, well-reasoned decisions

InspirationFeaturesQuick Start


A multi-model debate interface inspired by Andrej Karpathy's LLM Council.

Instead of querying a single LLM, this system routes one prompt to multiple models, lets them review each other's responses, and produces a final answer through structured synthesis.


Inspiration

The original LLM Council by Andrej Karpathy is a lightweight experiment for:

  • Comparing multiple LLM outputs
  • Peer-review between models
  • Consensus-based answers

This project builds on that idea and adds structure and extensibility.


What's Added Here

  • Explicit roles: Pro, Con, Judge
  • Optional multi-round debate instead of single pass
  • Memory support (PostgreSQL + FAISS) for past debates
  • Uncertainty & confidence signals in final answers
  • LLM routing with OpenRouter and local Ollama fallback
  • Basic governance hooks (audit, rollback-ready design)

Basic Flow

User Query
 → Pro Agent
 → Con Agent
 → Judge Agent
 → Final Response

Requirements

  • Python 3.10+
  • Node.js 18+ (UI)
  • OpenRouter API key (optional if using Ollama)

Run

git clone https://github.com/yourusername/llm-council.git
cd llm-council
pip install -r requirements.txt
python -m src.api.main

Notes

  • Local-first, not a hosted service
  • Models are interchangeable
  • Cost depends on selected LLMs
  • Intended for experimentation and system design exploration

License

MIT License — See LICENSE

About

Multi-model debate interface inspired by Andrej Karpathy Pro/Con/Judge agents with memory, uncertainty signals, and OpenRouter + Ollama support

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published