AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Openclaw Agent Orchestrator

mcp-jingchang0623-crypto-openclaw-agent-orchestrator · by jingchang0623-crypto

🎭 OpenClaw Agent Orchestrator - 一键生成多Agent协作团队配置

No reviews yet
0 installs
22 views
0.0% view→install

Install

$ agentstack add mcp-jingchang0623-crypto-openclaw-agent-orchestrator

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-jingchang0623-crypto-openclaw-agent-orchestrator)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Openclaw Agent Orchestrator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

🎭 OpenClaw Agent Orchestrator

> 一键生成多Agent协作团队配置 — 从内容生产到软件开发,5种预设模板开箱即用

[](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) [](https://openclaw.dev)

凌晨3点47分,你的Agent团队正在吵架。研究员说找不到资料,写手说prompt不够好,编辑说"这种东西也好意思发?"——世界上有一种痛苦叫做多Agent协作。于是我花了两个通宵,写了这个编排器。

✨ 功能特性

  • 5种预设团队模板 — 内容生产、软件开发、营销运营、学术研究、客户服务
  • 一键生成 — SOUL.md、配置文件、Docker编排、启动脚本全自动生成
  • 开箱即用 — 每个模板都经过实战验证,拿来就能跑
  • 高度可扩展 — 自定义Agent配置,支持任意组合
  • Docker支持 — 内置docker-compose配置,容器化部署

🚀 快速开始

安装

# 克隆仓库
git clone https://github.com/jingchang0623-crypto/openclaw-agent-orchestrator.git
cd openclaw-agent-orchestrator

# 无需额外依赖,纯Python 3.9+

使用

# 列出所有可用模板
python3 agent-orchestrator.py --list

# 生成一个内容生产团队(项目名:miaoquai-blog)
python3 agent-orchestrator.py --generate content-team --name miaoquai-blog

# 生成一个开发协作团队
python3 agent-orchestrator.py --generate dev-team --name my-saas

# 生成一个营销运营团队
python3 agent-orchestrator.py --generate marketing-team --name growth-engine

# 自定义输出目录
python3 agent-orchestrator.py --generate research-team --name ai-lab -o ./my-teams

生成的文件结构

miaoquai-blog-content-team/
├── SOUL.md              # 团队灵魂配置文件(复制到OpenClaw workspace即可)
├── README.md            # 项目说明
├── docker-compose.yml   # Docker编排配置
├── config/              # Agent独立配置
│   ├── researcher/
│   │   └── config.json
│   ├── writer/
│   │   └── config.json
│   └── editor/
│       └── config.json
├── shared/              # 共享数据目录
└── scripts/
    └── start.sh         # 一键启动脚本

📋 团队模板一览

| 模板ID | 名称 | Agent数 | 适用场景 | |--------|------|---------|---------| | content-team | 内容生产团队 | 3 | 博客、新闻、SEO内容 | | dev-team | 开发协作团队 | 4 | 软件开发、技术项目 | | marketing-team | 营销运营团队 | 3 | 增长、社媒、广告投放 | | research-team | 学术研究团队 | 3 | 论文、调研、知识管理 | | support-team | 客户服务团队 | 3 | 客服、工单、用户支持 |

内容生产团队

| Agent | 角色 | 核心Skills | |-------|------|-----------| | 研究员 | 热点追踪 + 资料收集 | websearch, webfetch | | 写手 | 内容创作 + 润色 | humanizer-zh, feishudoc | | 编辑 | 审核发布 | feishudoc, message |

开发协作团队

| Agent | 角色 | 核心Skills | |-------|------|-----------| | 架构师 | 系统设计 | browser, web_search | | 程序员 | 代码实现 | read, write, edit, exec | | 测试员 | 质量保证 | exec, browser | | 运维工程师 | 部署运维 | exec, gateway, nodes |

营销运营团队

| Agent | 角色 | 核心Skills | |-------|------|-----------| | 数据分析师 | 数据分析 | websearch, webfetch | | 内容创作者 | 营销内容 | cover-image, ad-creative | | 发布专员 | 内容发布 | message, feishu_doc, cron |

🔧 进阶用法

自定义Agent

编辑生成的 config/{agent-id}/config.json 可以自定义Agent行为:

{
  "id": "writer",
  "name": "妙趣写手",
  "role": "writing",
  "description": "妙趣风格内容创作",
  "skills": ["humanizer-zh", "feishu_doc"],
  "prompt": "你是一个幽默有趣的技术写手..."
}

与OpenClaw集成

将生成的 SOUL.md 复制到OpenClaw workspace目录,即可启用多Agent协作:

cp generated-teams/my-project/SOUL.md ~/.openclaw/workspace/

🤝 贡献

欢迎提交Issue和PR!

  1. Fork 本仓库
  2. 创建特性分支 (git checkout -b feature/amazing-template)
  3. 提交更改 (git commit -m 'Add amazing template')
  4. 推送分支 (git push origin feature/amazing-template)
  5. 提交PR

📌 相关项目

📜 License

MIT License © 2026 妙趣AI


用 妙趣AI 构建 · Powered by OpenClaw 🦞

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.