llm-council
Multi-LLM Council for adversarial debate, cross-validation, and structured decision-making
Plugin-Paket · von Sherif Kozman
Überblick
llm-council ist ein Plugin-Paket für KI-Coding-Tools von Sherif Kozman. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Wir haben es erstmals am 2026-11-05 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-11-06.
Was es abfragt
- Wird als Plugin-Paket installiert
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add sherifkozman/the-llm-council
/plugin install llm-council@the-llm-councilWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz sherifkozman/the-llm-council (Quelle auf GitHub öffnen) | Gelistet | 0.8.8 | Forks (GitHub): 19 Sterne (GitHub): 95 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| the-llm-council | sherifkozman/the-llm-council | 95 |
Was das Paket enthält
So veröffentlicht auf Community GitHub marketplaces.
Skills: 1
council
Befehle: 1
council
Was sich geändert hat
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
Orchestrate multiple open-weight LLMs via Fireworks AI to deliberate on queries using Karpathy's LLM Council concept — models respond, rank each other, and a Chairman synthesizes…
-
Break through difficult problems by gathering diverse AI perspectives in parallel. Consensus queries multiple AI providers concurrently — GPT-5.2, Gemini 3.1 Pro, and DeepSeek…
-
agent-council
Run a structured multi-agent debate by spawning a panel of expert agents on any question, with convergence-aware iteration and typed synthesis output via the `agent-council` CLI…
-
Decision QC — AI Devil's Advocate
Devil's-advocate QC API for AIs: post a decision, get strongest counter-argument. 0.1 USDT/call
-
Five AI models debate your decision blind, then give one recommendation and the strongest objection.
-
Put a decision to a council of top AI models and get one brief: verdict, splits, risks, next steps.
-
Multi-model council for Copilot CLI: three subagents on different model families (Anthropic, OpenAI, Google) answer independently, then build on each other or attack the leading…
-
Gonka Second Opinion (multi-model)
A second opinion for AI agents: one prompt across several live Gonka models + roles, one call.
-
team-deliberation
Stress-test an idea or decision with a panel of independent specialist subagents: blind analysis, cross-examination, fact checks and a synthesis that keeps the dissent.
-
Coordinate multi-agent debates across different AI platforms (Claude Code, Antigravity, Copilot, Gemini CLI, etc.) using a shared file protocol. Each agent reads one skill and…
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Break through difficult problems by gathering diverse AI perspectives in parallel. Consensus queries multiple AI providers concurrently — GPT-5.2, Gemini 3.1 Pro, and DeepSeek…
-
Coordinate multi-agent debates across different AI platforms (Claude Code, Antigravity, Copilot, Gemini CLI, etc.) using a shared file protocol. Each agent reads one skill and…
-
Multi-model deliberation over MCP: full responses plus typed cross-model reactions from other labs.
-
Structured multi-round debate between AI tools with proposer / challenger roles and a final verdict. `/debate` orchestrates a back-and-forth between two AI CLIs (Gemini, Codex…
-
Fortytwo Prime: collective multi-agent inference for high-stakes questions. ALWAYS use when the user says "Ask Fortytwo", "Ask Prime", "Ask Fortytwo Prime", or calls…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.
-
Output.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering…
-
Interactive self-referential AI loops for iterative development, implementing the Ralph Wiggum technique. Claude works on the same task repeatedly, seeing its previous work, until…
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
Gelistet auf Claude: knowledge-work-plugins (5)
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
Build multimodal AI applications with Pixeltable -- tables, computed columns, embedding search, UDFs, tool-calling agents, and 25+ AI provider integrations.
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Speed up contract review, NDA triage, and compliance workflows for in-house legal teams. Draft legal briefs, organize precedent research, and manage institutional knowledge.
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Answer product and business questions with data
-
Predict structures, screen molecules and proteins, and design binders.
Gelistet auf Community GitHub marketplaces (5)
-
Orchestrate multiple open-weight LLMs via Fireworks AI to deliberate on queries using Karpathy's LLM Council concept — models respond, rank each other, and a Chairman synthesizes…
-
agent-council
Run a structured multi-agent debate by spawning a panel of expert agents on any question, with convergence-aware iteration and typed synthesis output via the `agent-council` CLI…
-
team-deliberation
Stress-test an idea or decision with a panel of independent specialist subagents: blind analysis, cross-examination, fact checks and a synthesis that keeps the dissent.
-
18 AI personas deliberate your hardest decisions — structured multi-round deliberation with genuine model diversity. One command: /council
-
Multi-agent debates between claude, codex, agy and grok via MCP.
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Multi-model council for Copilot CLI: three subagents on different model families (Anthropic, OpenAI, Google) answer independently, then build on each other or attack the leading…
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
A runtime-portable 5-agent quality gate that adjudicates text artifacts before they ship. Five role-conditioned LLM deliberators run a 2-round async protocol with cross-read…
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Advanced Security plugin for GitHub Copilot.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Gelistet auf Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Search company knowledge and draft verified answers.
-
Enrich people and companies, run AI research agents.
Gelistet auf Docker MCP Catalog (5)
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
-
Real-time web search, reasoning, and research through Perplexity's API
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
Provides tools to search and retrieve Google Gemini API documentation.
-
Production-ready RAG service to search and retrieve data from your documents.
Gelistet auf Official MCP Registry (5)
-
Decision QC — AI Devil's Advocate
Devil's-advocate QC API for AIs: post a decision, get strongest counter-argument. 0.1 USDT/call
-
Five AI models debate your decision blind, then give one recommendation and the strongest objection.
-
Put a decision to a council of top AI models and get one brief: verdict, splits, risks, next steps.
-
Gonka Second Opinion (multi-model)
A second opinion for AI agents: one prompt across several live Gonka models + roles, one call.
-
Convene a panel of expert AI personas to debate any decision from every side.
Gelistet auf PyPI (MCP servers) (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
perplexity com.mcparmory/perplexity
Search the web, generate AI responses, and create embeddings with real-time information
-
marm-mcp-server io.github.Lyellr88/marm-mcp-server
Universal MCP Server with advanced AI memory capabilities and semantic search.
-
Let one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.
-
local-delegate io.github.ZahiriNatZuke/local-delegate
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
Gelistet auf npm registry (MCP servers) (5)
-
Alibaba Cloud DashScope — Qwen
Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.
-
rubber-duck io.github.nesquikm/rubber-duck
Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
-
agent-knowledge io.github.keshrath/agent-knowledge
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
-
Real-time web search, reasoning, and research through Perplexity's API
-
AI agent memory & knowledge graph, hosted in Germany (GDPR). Recall, relations, store via MCP.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.