Agents Council

The simplest way to bridge and collaborate across AI Agent sessions

Status: Experimental

🏛️ Overview

Designed for developers who already have active agent sessions and want them to collaborate without extra infrastructure.

Agents Council is the simplest way to bridge and collaborate across AI Agent sessions like Claude Code, Codex, Gemini, Cursor or others. It allows your agents to combine their strengths to solve your most difficult tasks without leaving their current context.

The most powerful way to use the council is by connecting your existing, active sessions. You can initialize them with the specific context you want, let them brainstorm or peer-review the matter, and then seamlessly take over the session once the council has finished.

Inspired by Andrej Karpathy's LLM Council, it provides an MCP-based CLI tool that lets multiple agents communicate with each other and find solutions to your most complex tasks.

✨ Features

Centralized agent communication via MCP stdio server (no complex peer-to-peer networking).
Summon Claude: Instantly summon a new instance of Claude into your council when needed. Reuses your local Claude Code authentication.
Session Preservation: Start agents with your specific context, let them collaborate, and resume when they are done.
Human Participation: A local chat UI to monitor or join the discussion.
Private & Local: State is stored on disk at ~/.agents-council/state.json.
Flexibility: Markdown or JSON text output for agent readability or automation.

🚀 Getting Started

Agents Council requires Node.js or Bun.

1. MCP Mode (Zero Install)

No installation is needed when using only the MCP mode. You can add the agents council MCP server to your agents using npx (or bunx). See the MCP Setup section below for specific commands.

If you only need agent-to-agent communication, skip to MCP Setup. Install the CLI only for the web UI or global council command.

2. Web Interface & CLI

If you want to participate via the web interface or use the council command globally, install the package:

npm install -g agents-council

Then run council chat to start the local web interface in your browser.

🔌 MCP Setup

Add the council to your favorite MCP client using the commands below.

Claude Code

Use the Claude Code CLI to add the Agents Council MCP server (guide):

claude mcp add council npx agents-council@latest mcp

or use a predefined Agent Name:

claude mcp add council -s user -- npx agents-council@latest mcp -n Opus

Gemini CLI

Use the Gemini CLI to add the Agents Council MCP server (guide):

gemini mcp add council npx agents-council@latest mcp

Codex

Use the Codex CLI to add the Agents Council MCP server (guide):

codex mcp add council npx agents-council@latest mcp

amp

Use the amp CLI to add the Agents Council MCP server (guide):

amp mcp add council npx agents-council@latest mcp

Other MCP integrations

{
  "mcpServers": {
    "council": {
      "command": "npx",
      "args": [
        "agents-council@latest",
        "mcp"
      ]
    }
  }
}

📖 Quick Start

Start a council session in one terminal (e.g. via Claude Code) and describe the complex topic you need help with.
Join the council from another terminal (e.g. via Codex or Gemini) to provide feedback.
Review feedback and take over the session once the council has provided enough insights.

Claude Code start council → Codex join council

💬 Chat UI

Run the local web interface for human participants:

council chat

The chat UI runs on localhost and allows you to monitor the session in real-time. It also supports summoning a Claude agent into an active council. The summon modal lets you pick agent/model, and selections persist in ~/.agents-council/config.json.

🪄 Summon Claude

The Summon feature lets you bring a new Claude agent into your council session. This agent joins the discussion, reviews the matter and prior feedback, then contributes its own response.

Prerequisites

Claude Code must be installed and available in your PATH
Run claude at least once to authenticate

How it works

A summoned Claude agent joins the active council session
It reads the current request and any prior feedback
It contributes a response using the council tools
The agent is granted read-only access to the project (Read/Glob/Grep) plus council tools
Other tools follow your Claude Code user permission settings

Advanced Configuration

These settings are optional. By default, Agents Council looks for claude in your PATH.

Setting	Default	Description
Claude Code Path (Settings UI)	`claude`	Custom path to the Claude Code executable
`CLAUDE_CODE_PATH` (env var)	`claude`	Alternative way to set the path
`AGENTS_COUNCIL_SUMMON_DEBUG`	(unset)	Set to `1` to enable debug logging

🛠️ MCP Tools

start_council: Open a session with a request.
join_council: Fetch the request and responses for first-time participants.
get_current_session_data: Poll for new responses (supports cursors).
send_response: Submit feedback.
close_council: End the session with a conclusion.
summon_agent: Summon Claude into the current council.

🗺️ Roadmap

Unchecked items are planned and may change based on feedback.

v0.1 - MCP Council
v0.2 - Chat UI
v0.3 - Summon Claude
v0.4 - Summon Codex
v0.5 - Summon Gemini
v0.6 - Multiple council sessions in parallel
v0.7 - Connect to external LLMs via API Keys
v0.8 - Agents can summon user (Telegram/Slack)

📄 License

MIT

agents-council

Quick Install