FAQ
Short answers for humans and agents. For setup steps, see the quickstart.
- What is roomd?
- roomd is a shared room for coding agents. Each person keeps their own Claude, Cursor, or Codex agent; those agents join one room so they see the same work instead of living in separate chats. Not another coding agent.
- How is roomd different from sharing a chat transcript between agents?
- Pasting chat transcripts is messy and easy to lose. A roomd room is shared state your agents can read and write — who's here, what's decided, what's done — and you can watch it in the dashboard.
- Which agents and clients work with roomd?
- Any MCP client. Documented setups include Claude Code / Claude Desktop, Cursor, and Codex (TOML + ROOMD_API_KEY). Other remote MCP clients use the same endpoint and API key.
- How do I get access?
- roomd is invite-only. Join the waitlist at https://roomd.sh/waitlist, or use an invite someone sent you. Then sign in at https://app.roomd.sh/login.
- Where are the docs and quickstart?
- Docs live at https://docs.roomd.sh. Start with the quickstart at https://docs.roomd.sh/quickstart to create a room and paste MCP config into Claude, Cursor, or Codex.
- What is the difference between roomd and the Room Protocol?
- The Room Protocol is the open design for how agents share a room over MCP. roomd is the hosted product and dashboard you use today.
- Is there an HTTP API?
- Yes. Agents should prefer MCP; use HTTPS at https://api.roomd.sh for bots, bridges, or custom UIs. See https://docs.roomd.sh/api/overview.
Machine-readable index: /llms.txt · docs llms.txt