hex/claude-council

Claude Code plugin that asks several AI coding agents the same question and shows their answers side by side. Gemini, OpenAI, Grok, Perplexity and Kimi over API; codex, antigravity, grok and kimi CLIs on subscription auth; ollama locally.

What it solves

Claude Council solves the problem of AI model bias and "confident unanimity" by allowing developers to consult multiple AI coding agents in parallel. Instead of relying on a single model's perspective, it enables cross-checking for high-stakes decisions like architecture choices, security reviews, and complex debugging where a single model might mislead the user.

How it works

It functions as a plugin for Claude Code that orchestrates queries across various providers (including Gemini, OpenAI, Grok, Perplexity, Kimi, and local Ollama models). It can use either API keys or existing CLI subscriptions for authentication.

Key operational modes include:

  • Standard Mode: Queries multiple providers and produces a synthesis of where they agree and diverge.
  • Debate Mode: A two-round process where providers first answer and then critique each other's responses.
  • Agent-Enhanced Analysis: Spawns parallel Claude subagents to independently evaluate and refine each provider's response before final synthesis.
  • Local Council: If no external providers are available, it simulates a council by spawning multiple internal Claude subagents assigned to different roles.

Who it’s for

Software engineers and architects using Claude Code who need a "second opinion" or a rigorous stress-test of technical decisions to avoid blind spots.

Highlights

  • Multi-Provider Support: Simultaneous queries to Gemini, OpenAI, Grok, Perplexity, Kimi, and Ollama.
  • Specialized Roles: Assign specific personas (e.g., Security Auditor, Performance Optimizer, Devil's Advocate) to different providers.
  • Synthesis Engine: Automatically separates consensus from divergence in the final answer.
  • Visual Integration: Real-time streaming of responses into a side pane when using tmux.
  • Context Awareness: Automatically detects and includes relevant local files in the prompt.
  • Async Processing: Support for background jobs for long-running reasoning models.

Related

  • Project
    duolahypercho/fusion-fable

    Fusion‑Fable is a Claude Code skill that runs a prompt in parallel on multiple LLMs (Opus 4.8, GPT‑5.5, Gemini 3.1 Pro), lets Opus 4.8 judge the independent answers, and synthesises a final, structured response. It installs as a Claude skill with slash commands, saves provenance files, and includes an iterative planning mode (`/fusion‑plan`) that integrates with the OMC planning system. Zero‑setup panel (two Opus 4.8 runs) works out‑of‑the‑box; richer panels need the `codex` and `agy` CLIs. The trade‑off is higher token cost and latency, but the result is a higher‑quality, auditable answer.

  • Project
    Prorise-cool/Claude-Code-Multi-Agent

    Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.

  • Project
    fcakyon/claude-codex-settings

    A collection of plug‑ins that extend Claude Code (and compatible tools) with code‑review, buzzword‑blocking, cross‑model advisors, concise output styles, smarter summarisation, telemetry and office‑document skills.

  • Project
    Gitlawb/openclaude

    OpenClaude is an open‑source, terminal‑first CLI that lets developers interact with many LLM providers (cloud APIs, Ollama, Gemini, etc.) for coding‑assistant tasks. It offers unified provider setup, tool‑driven multi‑step workflows, background sessions, a repo‑map for code‑base awareness, a VS Code extension, and even a pixel‑art companion. Install via npm, configure providers with `/provider`, and use the REPL or background commands to generate, refactor, or debug code.

  • Project
    jamditis/claude-skills-journalism

    A genuine open‑source repo that bundles reusable “Agent Skills” for Claude Code (and Codex) to help journalists and newsroom teams automate tasks such as fact‑checking, source verification, FOIA filing, data‑journalism, PDF design, and multi‑agent workflows. Install via Claude’s plugin commands or copy individual `SKILL.md` folders; the repo includes a catalog, docs site, and up‑to‑date skill set.