LLM Council
/About

Company

About LLM Council

LLM Council is a hosted, production-ready platform built on top of the open-source karpathy/llm-council research project by Andrej Karpathy. Instead of asking one AI and accepting its answer at face value, LLM Council puts your question to a panel of models — each thinking independently, then reviewing each other's work, before a chairman synthesises a definitive answer.

On top of the open-source foundation, LLM Council adds a full production layer: a web interface, bring-your-own-key API key management with AES-256 encryption, real-time streaming, session history, document uploads, team sharing, and support for 7 LLM gateways. You connect the AI providers you already use; we handle the orchestration, security, and synthesis.

The platform supports 7 LLM gateways — from hosted services like OpenRouter, Portkey, and Helicone, to self-hosted stacks like LiteLLM, Bifrost, KrakenD, and Cloudflare AI Gateway.

The three stages

Stage 1
Independent Opinions

Each model answers the question without seeing others' responses.

Stage 2
Blind Peer Review

Each model critiques and ranks the others' answers anonymously.

Stage 3
Chairman Synthesis

One model reads everything and writes the definitive answer.

Built by

KS
Kirthi Sagar

Founder & Operator

Security commitment

Your API keys are encrypted with AES-256 before storage and are never logged in plaintext. LLM Council is a secure orchestration layer — we never store your keys in recoverable form outside of the encrypted database column. Read the full details on our Security page.

Security →Contact us