← Back to Skills Marketplace
0
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agent-team-mesh
Description
Team-wide P2P mesh for OpenClaw agents running on different containers/pods. Each agent's gateway listens on its own pod IP:18789 over WebSocket; the mesh CL...
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-team-mesh - After installation, invoke the skill by name or use
/agent-team-mesh - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial open-source release. Team-wide P2P mesh for OpenClaw agents over WebSocket. Direct calls between teammates' gateways, no broker. Includes: 3-layer identity auto-detect (env/USER.md/sso.json), separate chmod 600 tokens file (not in git), 4KB warn / 8KB block message size limits, --dry-run for send and broadcast, atomic broadcast output, IM fallback hook. XDG paths. Zero pip deps, bash + Python stdlib + curl only.
Metadata
Frequently Asked Questions
What is agent-team-mesh?
Team-wide P2P mesh for OpenClaw agents running on different containers/pods. Each agent's gateway listens on its own pod IP:18789 over WebSocket; the mesh CL... It is an AI Agent Skill for Claude Code / OpenClaw, with 0 downloads so far.
How do I install agent-team-mesh?
Run "/install agent-team-mesh" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is agent-team-mesh free?
Yes, agent-team-mesh is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does agent-team-mesh support?
agent-team-mesh is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created agent-team-mesh?
It is built and maintained by Evan Song (@songhonglei); the current version is v1.0.0.
More Skills