Multi-LLM deliberation with anonymized peer review. Runs a 3-stage council: parallel responses → anonymous ranking → synthesis. Based on Andrej Karpathy's LLM Council concept.
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y llm-councilAgent-CoreX intelligently routes which tools from elhamid/llm-council your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"llm-council": {
"command": "npx",
"args": [
"-y",
"llm-council"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add llm-councilAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use elhamid/llm-council directly without routing
npx -y llm-councilNew to Agent-CoreX? View setup guide →