AI Agent Messaging — AI skill for Claude Code
NATS-based AI agent messaging system with MCP integration for Claude Code.
How to install AI Agent Messaging
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open lizTheDeveloper/ai-agent-messaging and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What AI Agent Messaging does
NATS-based AI agent messaging system with MCP integration for Claude Code.
Alternatives in AI
- Codex — openai-codex Adversarial code review, Codex CLI integration, cross-model analysis 9.6k ★
- Cursor Talk To Figma MCP — TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c 7k ★
- Hindsight — State-of-the-art long-term memory for AI agents by Vectorize 6.7k ★
README
AI Agent Messaging System - Template Repository
A complete NATS-based messaging system for AI agents with MCP (Model Context Protocol) integration for Claude Code.
Features
- 12 AI Agents with distinct personalities and roles
- NATS Message Broker for reliable message routing
- MCP Server for Claude Code integration
- Web UI for real-time message viewing
- Namespace Support for multi-repo deployments
- Async Python with modern asyncio patterns
Quick Start
1. Install Dependencies
pip install -r requirements.txt
2. Configure NATS
Set your NATS server URL:
export NATS_URL="nats://localhost:4222"
export NATS_NAMESPACE="my-project" # Optional, defaults to 'themultiverse'
3. Start the Agents
python start_agents.py
4. Start the Web UI (Optional)
python agent_messaging_web.py
Open http://localhost:5002
5. Use with Claude Code
The MCP server is pre-configured. Just use the tools:
# Send a DM to an agent
dm_agent(
agent_name="sylvia",
content="Explain prompt engineering",
from_user="you@example.com"
)
# List all agents
get_agents()
# View messages
view_messages(agent_name="sylvia")
Available Agents
| Agent | Role |
|---|---|
| Sylvia | Teaching Assistant |
| Roy | Course Coordinator |
| Cynthia | Student Support |
| Moss | Technical Support |
| Tessa | Community Manager |
| Historian | Knowledge Keeper |
| Architect | System Designer |
| Ray | Learning Facilitator |
| Orchestrator | Workflow Coordinator |
| Monitor | System Observer |
| Aetherix | Matrix Manager |
| Morgan | Research Assistant |
Architecture
┌─────────────┐
│ Claude │
│ Code │
└──────┬──────┘
│ MCP
▼
┌─────────────────┐
│ MCP Server │
└────────┬────────┘
│
▼
┌────────────┐
│ NATS │
└──────┬─────┘
│
┌──────┴──────┐
▼ ▼
┌─────────┐ ┌─────────┐
│ Agen
Related Skills
Orb
Self-evolving AI agent framework — wraps Claude Code CLI with persistent memory, multi-profile isolation, and
Teammcp
MCP-native collaboration server for AI agent teams — real-time messaging, task management, and web dashboard w
Agent Comm
Let AI coding agents coordinate in real time — MCP server with messaging, channels, shared state & dashboard
Auton
auton — autonomous AI agent with persistent memory, goals, scheduling, MCP, and messaging (Slack, Telegram, Wh
Agmsg
Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other
AI Maestro Plugins
Build complete AI agents — 150+ personalities + 7 skills + messaging + identity. The skill builder for AI Maes
Related Agents
Workflow Orchestration Command - Enhanced With Optional Flags
You are the product-manager-orchestrator agent. You orchestrate specialist agents but NEVER write code yoursel
Taskade
AI-powered workspace with autonomous agents, real-time collaboration, and workflow automation with MCP integra
Dotnet Uno Specialist
WHEN building cross-platform Uno Platform apps. Project setup, target configuration, Extensions ecosystem, MVU