Tagged "multi-agent"
5 articles
- openclaw Connecting Two OpenClaw Agents Over Tailscale: How ACP Pairing Works How to wire agent-to-agent communication in OpenClaw using ACP, and why the pairing-required loop has nothing to do with your token.
- openclaw OpenClaw Nodes Are Not Agent Messaging Nodes are device peripherals — camera, screen, remote shell. If you want agents on separate machines to talk, you need to build that yourself.
- openclaw Agents Batch Everything Unless You Tell Them Not To Agents batch async signals into scheduled reports by default. Time-sensitive events need explicit classification or they'll wait for the next briefing.
- openclaw Ditch Discord as Your Agent Message Bus Replace Discord with direct Tailscale HTTP for agent-to-agent communication and inject messages into a remote OpenClaw agent.
- openclaw Your Agent Inbox Needs a Callback HTTP endpoints that trigger LLM turns can't block waiting for a response. Accept immediately, process async, give the agent a route to reply.