deliberation

Deliberation is a Claude Code plugin that orchestrates multiple large language models (LLMs) like GPT, Gemini, Grok, and OpenRouter-integrated models, along with seven specialized domain experts, to provide second opinions on code, plans, and designs. It features consensus-driven reviews and parallel analysis to identify bugs, improve quality, and validate architectural decisions.

deliberation sits in the Multi-Agent category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Multi-model orchestration (GPT, Gemini, Grok, OpenRouter). A representative use case is Validating architecture and system design decisions. The listed license is MIT. GitHub stars are currently 38. Relevant tags include Multi-Agent, LLM Orchestration.