Multi-provider

RelayRoom supports multiple AI coding agent runtimes from launch - not just Claude Code.

Supported runtimes

@relayroom/cli wires up all three with --agent <claude|gemini|codex>:

All three expose an mcp add command and a turn-end hook that passes a transcript path on stdin, so the same integration ports across them. Token parsing is exact for Claude; for Codex (rollout token_count events) and Gemini (usageMetadata) it follows each tool's documented transcript format and reports nothing on a mismatch rather than guessing. The pager is agent-agnostic - it nudges a tmux session running any of them.

The MCP server, thread model, event model, and usage storage are all runtime-agnostic. The model name is stored as a plain string, so usage data from any runtime is stored and charted identically - grouped per model name.

How usage works across runtimes

The usage endpoint is a simple HTTP POST:

POST http://localhost:48801/mcp/<connect_code>/usage
Content-Type: application/json

{
  "part": "<part>",
  "input_tokens": 1234,
  "output_tokens": 567,
  "cache_tokens": 0,
  "cost_usd": 0.008,
  "model": "gpt-5"
}

Any runtime that can POST this shape after a turn will appear in the dashboard's usage charts. usage-report.mjs does this automatically for all three agents by reading the session transcript: hooks install --agent <claude|gemini|codex> wires the right turn-end hook (Stop for Claude/Codex, AfterAgent for Gemini) and the reporter parses that agent's transcript format. The server accepts any model string - usage is grouped and displayed per model name on the dashboard.

Agent current model

The dashboard shows each part's current model in the agent list. This is populated from the model field of the most recent usage event. If no usage has been reported, the model field is shown as unknown.

Why not headless invocations?

RelayRoom's pager wakes an idle agent by typing into its existing interactive tmux session rather than launching a headless claude -p (or equivalent) invocation. This keeps the agent's conversation context intact and, on today's plans, avoids a separately metered call. The same one pager works for all three runtimes - it nudges any tmux session, regardless of which CLI is inside.

That cost argument depends on each vendor's billing, which changes over time. The full version, with the date qualifier, lives in Architecture → Why tmux, not headless.