Multi-Agent conversation management platform with Gemini-style UI. Manage all your OpenClaw agents in one place with image upload, chat history, and message isolation.
Scanned 9/9/2026
Install to Claude Code
npx -y skills add Lord1Egypt/awesome-skill-forge --skill agent-manager --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Agent Manager?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/lord1egypt-agent-manager)More formats (shields.io, HTML) on the badges page.
---
name: agent-manager
description: Multi-Agent conversation management platform with Gemini-style UI. Manage all your OpenClaw agents in one place with image upload, chat history, and message isolation.
version: 1.0.0
author: MSK
license: MIT
tags: agent,management,chat,ui,gemini,multi-agent
homepage: https://clawhub.com
category: productivity
---
# Agent Manager - 多 Agent 对话管理平台
统一管理多个 OpenClaw Agent 的对话平台,支持文字 + 图片输入,对话历史自动保存。
## 🎯 功能亮点
- **多 Agent 管理** - 统一管理所有 Agent
- **Gemini 风格界面** - 现代化左右分栏设计
- **图片输入** - 支持拖拽上传、按钮选择
- **对话历史** - 自动保存,切换 Agent 不丢失
- **消息隔离** - 每个 Agent 独立对话历史
- **本地存储** - 数据保存在浏览器
## 🚀 快速开始
### 1. 安装依赖
```bash
cd agent-manager
npm install
```
### 2. 启动服务
```bash
node server-gemini.js
```
### 3. 访问界面
```
http://localhost:3000
```
## 📋 使用说明
### 与 Agent 对话
1. 左侧选择 Agent
2. 右侧输入消息
3. 按 Enter 或点击发送
### 上传图片
1. 点击 📎 按钮
2. 或拖拽图片到输入框
3. 点击发送
## 💰 付费说明
**价格:** $10 USD(一次性购买)
**支付:** PayPal (396554498@qq.com)
**包含:**
- ✅ 完整源代码
- ✅ 永久使用授权
- ✅ 基础技术支持
## 📄 许可
- ✅ 个人使用
- ✅ 商业使用
- ❌ 转售技能本身
---
**详细文档请查看 CLAWHUB.md**
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.