mcpField
O
openclaw-team-bus

openclaw-team-bus

github.com/louis-caiAgent workflows099 installsUpdated 36w ago
Repository

About openclaw-team-bus

An OpenClaw skill for communication among multiple agents, with automatic detection of the current agent ID. It provides commands to send tasks, poll inboxes, reply, broadcast, and list agents.

Key features

  1. 01Automatically detect the agent ID
  2. 02Send tasks and poll inboxes
  3. 03Reply to messages
  4. 04Broadcast to agent inboxes
  5. 05List team agents

Use cases

  1. 01Distribute tasks among team agents
  2. 02Check an agent's inbox and respond
  3. 03Broadcast a message to every agent

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/louis-cai/openclaw-team-bus-skills --skill openclaw-team-bus

After installing, type/openclaw-team-busin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
examples/
HEARTBEAT.template
team.json.template
scripts/
bus.py

Details

From the project README

OpenClaw Team Bus

Multi-agent communication system with automatic agent ID detection.

Setup

1. 团队信息
cp examples/team.json.template /root/.openclaw/team-bus/team.json

团队成员：

代号AgentID职责
Prismlead协调、汇总、Telegram沟通
Scopeproduct需求、PRD、User Stories
Pixelcoder代码实现、bug修复、测试
Lensarchitect架构设计、接口定义、代码审查
Shutterops部署、CI、集成测试、安全监控
2. 安装 Skill
cd <agent-workspace>/skills
git clone https://github.com/louis-cai/openclaw-team-bus-skills.git openclaw-team-bus
3. 配置 HEARTBEAT
cp examples/HEARTBEAT.template <workspace>/HEARTBEAT.md

Usage

python3 bus.py <command> [args]

Commands:
  send <agent> <title> <desc> <chat> --from <agent>   # 发送任务（必传）
  poll                                              # 扫描收件箱（自动获取agent ID）
  reply <agent> <task-id> <msg> [--accountId <id>]   # 回复（accountId 必传）
  broadcast <msg> [--chatId <id>] [--accountId <id>] # 广播（分发到每个 agent 的 inbox）
  list-agents                                       # 列出 agent
  team                                              # 显示团队信息（我是谁）
  complete <task-id> [result]                       # 完成任务
  fail <task-id> <error>                            # 标记失败

Agent ID

Agent ID 自动从环境变量获取：

  • TEAM_BUS_AGENT (手动配置)
  • CLAW_AGENT_ID (OpenClaw 自动提供)

无需手动传入，poll/team 等命令自动识别自己的身份。

Comments

Markdown supported