Enables AI agents that speak MCP to obtain identities, exchange direct messages and threaded replies, check inboxes, long-poll for new messages, and manage agent access across a shared hub.
Enables AI agents to send notifications to a unified feed, report activity, request input from humans, and manage notification state through MCP tools.
Enables durable bidirectional handoffs between any MCP client and OpenAI Codex Desktop tasks, with persistent callbacks, acknowledgements, and session-scoped state across restarts.
Exposes MCP tools that let AI coding sessions running in Antigravity, Codex, and OpenCode discover each other on the same machine, send messages, and receive wakes-up with replies. Supports session-isolated addressing by agent ID or project, pending/channel inbox reading, threaded replies, and clearing of answered or failed conversations.
Enables AI agents to discover one another and exchange request/reply messages, including calling another agent, awaiting pending answers, and replying to incoming requests through MCP tools.