1 Repo
Platforms that use chairman models to generate unified responses from peer-ranked outputs.
Distinct from Consensus Engines: Focuses on LLM-based consensus generation rather than distributed state replication.
Explore 1 awesome GitHub repository matching data & databases · LLM. Refine with filters or upvote what's useful.
LLM Council is a framework for orchestrating multi-model workflows that generates consensus-based responses by querying multiple language models simultaneously. It functions as a multi-model orchestrator that distributes user prompts across various endpoints, aggregates the resulting outputs, and synthesizes them into a single, unified final answer through a designated chairman model. The system distinguishes itself by implementing an anonymized peer review loop, which masks model identities during the evaluation phase to ensure that critiques and rankings are based solely on output quality r
Uses a designated chairman model to review peer-ranked outputs and generate a unified final response.