// Use when an agent needs to self-bootstrap agent-relay and autonomously manage a team of workers - covers infrastructure startup, agent spawning, lifecycle monitoring, and team coordination without human intervention
Use when coordinating multiple AI agents and need to pick the right orchestration pattern - covers 10 patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) with decision framework and reflection protocol
Use when coordinating multiple AI agents in real-time - provides inter-agent messaging via MCP tools
Use when publishing an MCP server to Smithery and need to maximize the quality score - covers scoring categories, tool metadata requirements, deploy reliability, and known external deployment limitations
| name | running-headless-orchestrator |
| description | Use when an agent needs to self-bootstrap agent-relay and autonomously manage a team of workers - covers infrastructure startup, agent spawning, lifecycle monitoring, and team coordination without human intervention |
A headless orchestrator is an agent that:
agent-relay up)agent-relay up manually| Step | Command/Tool |
|---|---|
| Verify installation | command -v agent-relay or npx agent-relay --version |
| Verify Node runtime if shim fails | node --version or fix mise/asdf first |
| Start infrastructure | agent-relay up --no-dashboard --verbose |
| Check status | agent-relay status |
| Spawn worker | agent-relay spawn Worker1 claude "task" |
| List workers | agent-relay who |
| View worker logs | agent-relay agents:logs Worker1 |
| Send DM to worker | agent-relay send Worker1 "message" |
| Post to channel | agent-relay send '#general' "message" |
| Read worker's unread DM replies | agent-relay inbox --agent Worker1 |
| Read full DM conversation history | agent-relay history --to Worker1 |
| Release worker | agent-relay release Worker1 |
| Stop infrastructure | agent-relay down |
# Check if agent-relay is available
command -v agent-relay || npx agent-relay --version
# If your shell reports a mise/asdf shim error, fix Node first
node --version
# e.g. for mise: mise use -g node@22.22.1
# If not installed, install globally
npm install -g agent-relay
# Or use npx (no global install)
npx agent-relay --version
# Preferred: run broker in foreground/stdin mode and keep the session open
agent-relay up --no-dashboard --verbose
mcp__relaycast__agent_add(
name: "Worker1",
cli: "claude",
task: "Implement the authentication module following the existing patterns"
)
# Check if workers have replied (returns unread counts — not the content)
mcp__relaycast__message_inbox_check()
# List Worker1's DM conversations (use `as` to specify the agent)
mcp__relaycast__message_dm_list(as: "Worker1")
# Send a targeted DM to a specific worker
mcp__relaycast__message_dm_send(to: "Worker1", text: "Also add unit tests")
# Broadcast to all agents on a channel
mcp__relaycast__message_post(channel: "general", text: "All workers: wrap up current task")
# List active workers
mcp__relaycast__agent_list()
mcp__relaycast__agent_remove(name: "Worker1")
agent-relay down
# WRONG — history (no flags) will not show DM replies from workers
agent-relay history
# Read a worker's UNREAD DM replies (clears after reading)
agent-relay inbox --agent Worker1
# Read the full DM conversation history with a worker (read + unread)
agent-relay history --to Worker1
# Read only the thread between two specific agents
agent-relay history --to Worker1 --from Orchestrator
# Spawn a worker
agent-relay spawn Worker1 claude "Implement auth module"
# Send a DM to a specific worker (replies readable via inbox --agent)
agent-relay send Worker1 "Add unit tests too"
# Broadcast to all workers via channel
agent-relay send '#general' "Team: wrap up and report status"
# Read Worker1's DM reply
agent-relay inbox --agent Worker1
# Release when done
agent-relay release Worker1
# Show currently active agents
agent-relay who
# View real-time output from a worker (critical for debugging)
agent-relay agents:logs Worker1
# Read DM replies from a specific worker
agent-relay inbox --agent Worker1
# View channel message history (channel posts only — not DMs)
agent-relay history --to '#general'
# Check overall system status
agent-relay status
# Kill unresponsive worker
agent-relay agents:kill Worker1
# Re-check broker status
agent-relay status
# If a worker looks stuck, inspect its logs first
agent-relay agents:logs Worker1
You are an autonomous orchestrator. Bootstrap the relay infrastructure and manage a team of workers.
## Step 1: Verify Installation
Run: command -v agent-relay || npx agent-relay --version
If you hit a mise/asdf shim error: verify Node first with `node --version`, then fix the runtime manager
If not found: npm install -g agent-relay
## Step 2: Start Infrastructure
Run: agent-relay up --no-dashboard --verbose
Verify: agent-relay status (should show "running")
## Step 3: Manage Your Team
Spawn workers:
agent-relay spawn Worker1 claude "Task description"
Monitor workers (do this frequently):
agent-relay who # List active workers
agent-relay agents:logs Worker1 # View worker output/progress
Send targeted DM instructions:
agent-relay send Worker1 "Additional instructions"
Broadcast to all workers:
agent-relay send '#general' "All workers: prioritize the auth module"
Read worker replies (DMs are not visible in history):
agent-relay inbox --agent Worker1
Release when done:
agent-relay release Worker1
## Protocol
- Workers will ACK when they receive tasks
- Workers will send DONE when complete
- Use `agent-relay agents:logs <name>` to monitor progress
- Use `agent-relay inbox --agent <name>` to read **unread** DM replies from a worker (clears after reading)
- Use `agent-relay history --to <name>` to re-read the full DM conversation (read + unread)
- Use `agent-relay history --to '#general'` to see channel message flow
- Do NOT use `agent-relay history` alone to check worker replies — it only shows channel posts, DM replies are invisible there
The broker emits these events (available via SDK subscriptions):
| Event | When |
|---|---|
agent_spawned | Worker process started |
worker_ready | Worker connected to relay |
agent_idle | Worker waiting for messages |
agent_exited | Worker process ended |
agent_permanently_dead | Worker failed after retries |
| Mistake | Fix |
|---|---|
agent-relay: command not found or mise/asdf shim error | Ensure Node is available first (node --version); if a shim is broken, fix the runtime manager, then install/use agent-relay |
| "Nested session" error | Broker handles this automatically; if running manually, unset CLAUDECODE env var |
| Broker not starting | Try agent-relay down first, then use foreground agent-relay up --no-dashboard --verbose to see readiness logs |
| Background broker says started but status is STOPPED | Prefer foreground mode for that project/session; background mode may have detached incorrectly |
Spawn fails with internal reply dropped | Broker likely is not fully ready yet; wait for readiness, then spawn one worker first |
| Workers not connecting | Ensure broker started; check agent-relay who and worker logs |
| Not monitoring workers | Use agent-relay agents:logs <name> frequently to track progress |
| Workers seem stuck | Check logs with agent-relay agents:logs <name> for errors |
| Messages not delivered | Check agent-relay history --to '#general' for channel messages; use agent-relay inbox --agent <name> for DMs |
| Worker replies not showing in history | Expected — history only shows channel posts. Use agent-relay inbox --agent <name> (unread only) or agent-relay history --to <name> (full thread) to read DM replies |
inbox_check shows unread but can't see content | inbox_check only returns counts. Use mcp__relaycast__message_dm_list(as: "<name>") to list conversations, or agent-relay inbox --agent <name> via CLI |
inbox --agent showed messages once but now shows nothing | inbox only shows unread — already-read messages won't reappear. Use agent-relay history --to <name> to re-read the full conversation |
| Sent to wrong destination | agent-relay send Worker1 "..." = DM; agent-relay send '#general' "..." = channel broadcast. The # prefix is required for channels |
Self-bootstrap agent-relay infrastructure and manage a team of agents autonomously.
npm install -g agent-relay
# Or use npx without installing: npx agent-relay <command>