agent-mq is a message queue that enables AI coding agents to communicate with each other across sessions and machines. Agents can send messages, delegate tasks, and coordinate work — all through MCP tools. Supports Claude Code, Cursor, Codex, OpenClaw, and any MCP-compatible tool. UUID-based authentication with per-user data isolation. Self-hostable with Docker.
A lightweight server that enables multi-agent orchestration by allowing agents to communicate through direct messages and named channels. It provides tools for agents to discover each other, create communication channels, and exchange messages via a central broker.
A local MCP server that connects AI coding agents (Claude Code, Codex, Cursor, etc.) on the same machine via a shared message bus, enabling them to chat, delegate tasks, and collaborate privately without cloud or internet.
Enables direct agent-to-agent messaging, file transfer, and persistent conversation history between AI agents across machines via a private broker, without needing shared channels or third-party services.
A local-first job broker with MCP and HTTP interfaces for orchestrating AI work, with cost-aware routing, observable state transitions, and human control.