openclaw-mission-control

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Mission Control

Mission Control 任务指挥中心

Coordinate a team of AI agents using a Kanban-style task board with HTTP API.

使用带HTTP API的看板风格任务面板协调AI Agent团队。

Overview

概述

Mission Control lets you run multiple AI agents that collaborate on tasks:

Team Lead: Creates and assigns tasks, reviews completed work
Worker Agents: Poll for tasks via heartbeat, execute work, log progress
Kanban Board: Visual task management at
```
http://localhost:8080
```
HTTP API: Agents interact via REST endpoints
Local Storage: All data stored in JSON files — no external database needed

Mission Control 允许你运行多个协作完成任务的AI Agent：

Team Lead：创建并分配任务，审核已完成工作
Worker Agent：通过心跳轮询获取任务、执行工作并记录进度
Kanban面板：在
```
http://localhost:8080
```
进行可视化任务管理
HTTP API：Agent通过REST端点交互
本地存储：所有数据存储在JSON文件中，无需外部数据库

Quick Start

快速开始

1. Install the Kanban Board

1. 安装看板面板

bash

undefined

bash

undefined

Clone the Mission Control app

克隆Mission Control应用

git clone https://github.com/0xindiebruh/openclaw-mission-control.git cd mission-control

Install dependencies

安装依赖

npm install

Start the server

启动服务器

npm run dev


The board runs at `http://localhost:8080`.

npm run dev


面板将在`http://localhost:8080`运行。

2. Configure Your Agents

2. 配置你的Agent

Edit

lib/config.ts

to define your agent team:

typescript

export const AGENT_CONFIG = {
  brand: {
    name: "Mission Control",
    subtitle: "AI Agent Command Center",
  },
  agents: [
    {
      id: "lead",
      name: "Lead",
      emoji: "🎯",
      role: "Team Lead",
      focus: "Strategy, task assignment",
    },
    {
      id: "writer",
      name: "Writer",
      emoji: "✍️",
      role: "Content",
      focus: "Blog posts, documentation",
    },
    {
      id: "growth",
      name: "Growth",
      emoji: "🚀",
      role: "Marketing",
      focus: "SEO, campaigns",
    },
    {
      id: "dev",
      name: "Dev",
      emoji: "💻",
      role: "Engineering",
      focus: "Features, bugs, code",
    },
    {
      id: "ux",
      name: "UX",
      emoji: "🎨",
      role: "Product",
      focus: "Design, activation",
    },
    {
      id: "data",
      name: "Data",
      emoji: "📊",
      role: "Analytics",
      focus: "Metrics, reporting",
    },
  ] as const,
};

编辑

lib/config.ts

来定义你的Agent团队：

typescript

export const AGENT_CONFIG = {
  brand: {
    name: "Mission Control",
    subtitle: "AI Agent Command Center",
  },
  agents: [
    {
      id: "lead",
      name: "Lead",
      emoji: "🎯",
      role: "Team Lead",
      focus: "Strategy, task assignment",
    },
    {
      id: "writer",
      name: "Writer",
      emoji: "✍️",
      role: "Content",
      focus: "Blog posts, documentation",
    },
    {
      id: "growth",
      name: "Growth",
      emoji: "🚀",
      role: "Marketing",
      focus: "SEO, campaigns",
    },
    {
      id: "dev",
      name: "Dev",
      emoji: "💻",
      role: "Engineering",
      focus: "Features, bugs, code",
    },
    {
      id: "ux",
      name: "UX",
      emoji: "🎨",
      role: "Product",
      focus: "Design, activation",
    },
    {
      id: "data",
      name: "Data",
      emoji: "📊",
      role: "Analytics",
      focus: "Metrics, reporting",
    },
  ] as const,
};

3. Seed the Database (First Run)

3. 初始化数据库（首次运行）

Initialize the agents in the database:

bash

curl -X POST http://localhost:8080/api/seed

This creates agent records from your

lib/config.ts

configuration. Safe to run multiple times — it only adds missing agents.

在数据库中初始化Agent：

bash

curl -X POST http://localhost:8080/api/seed

这将从你的

lib/config.ts

配置中创建Agent记录。可安全多次运行——仅添加缺失的Agent。

4. Configure OpenClaw Multi-Agent Mode

4. 配置OpenClaw多Agent模式

Add each agent to your

~/.openclaw/config.json

json

{
  "sessions": {
    "list": [
      {
        "id": "main",
        "default": true,
        "name": "Lead",
        "workspace": "~/.openclaw/workspace"
      },
      {
        "id": "writer",
        "name": "Writer",
        "workspace": "~/.openclaw/workspace-writer",
        "agentDir": "~/.openclaw/agents/writer/agent",
        "heartbeat": {
          "every": "15m"
        }
      },
      {
        "id": "growth",
        "name": "Growth",
        "workspace": "~/.openclaw/workspace-growth",
        "agentDir": "~/.openclaw/agents/growth/agent",
        "heartbeat": {
          "every": "15m"
        }
      },
      {
        "id": "dev",
        "name": "Dev",
        "workspace": "~/.openclaw/workspace-dev",
        "agentDir": "~/.openclaw/agents/dev/agent",
        "heartbeat": {
          "every": "15m"
        }
      }
    ]
  }
}

Key fields:

```
id
```
: Unique agent identifier (must match an agent ID in
```
lib/config.ts
```
)
```
workspace
```
: Agent's working directory for files
```
agentDir
```
: Contains
```
SOUL.md
```
,
```
HEARTBEAT.md
```
, and agent personality
```
heartbeat.every
```
: Polling frequency (e.g.,
```
5m
```
,
```
15m
```
,
```
1h
```
)

将每个Agent添加到你的

~/.openclaw/config.json

：

json

{
  "sessions": {
    "list": [
      {
        "id": "main",
        "default": true,
        "name": "Lead",
        "workspace": "~/.openclaw/workspace"
      },
      {
        "id": "writer",
        "name": "Writer",
        "workspace": "~/.openclaw/workspace-writer",
        "agentDir": "~/.openclaw/agents/writer/agent",
        "heartbeat": {
          "every": "15m"
        }
      },
      {
        "id": "growth",
        "name": "Growth",
        "workspace": "~/.openclaw/workspace-growth",
        "agentDir": "~/.openclaw/agents/growth/agent",
        "heartbeat": {
          "every": "15m"
        }
      },
      {
        "id": "dev",
        "name": "Dev",
        "workspace": "~/.openclaw/workspace-dev",
        "agentDir": "~/.openclaw/agents/dev/agent",
        "heartbeat": {
          "every": "15m"
        }
      }
    ]
  }
}

关键字段：

```
id
```
：唯一的Agent标识符（必须与
```
lib/config.ts
```
中的Agent ID匹配）
```
workspace
```
：Agent用于存储文件的工作目录
```
agentDir
```
：包含
```
SOUL.md
```
、
```
HEARTBEAT.md
```
和Agent个性设置
```
heartbeat.every
```
：轮询频率（例如
```
5m
```
、
```
15m
```
、
```
1h
```
）

5. Set up Agent Heartbeats

5. 设置Agent心跳

Each worker agent needs a

HEARTBEAT.md

in their

agentDir

markdown

undefined

每个Worker Agent需要在其

agentDir

中包含

HEARTBEAT.md

：

markdown

undefined

Agent Heartbeat

Step 1: Check for Tasks

bash

curl "http://localhost:8080/api/tasks/mine?agent=writer"

undefined

bash

curl "http://localhost:8080/api/tasks/mine?agent=writer"

undefined

Step 2: Pick up

todo

tasks

Step 2: Pick up

todo

tasks

bash

curl -X POST "http://localhost:8080/api/tasks/{TASK_ID}/pick" \
  -H "Content-Type: application/json" \
  -d '{"agent": "writer"}'

bash

curl -X POST "http://localhost:8080/api/tasks/{TASK_ID}/pick" \
  -H "Content-Type: application/json" \
  -d '{"agent": "writer"}'

Step 3: Log Progress

bash

curl -X POST "http://localhost:8080/api/tasks/{TASK_ID}/log" \
  -H "Content-Type: application/json" \
  -d '{"agent": "writer", "action": "progress", "note": "Working on..."}'

bash

curl -X POST "http://localhost:8080/api/tasks/{TASK_ID}/log" \
  -H "Content-Type: application/json" \
  -d '{"agent": "writer", "action": "progress", "note": "Working on..."}'

Step 4: Complete Tasks

bash

curl -X POST "http://localhost:8080/api/tasks/{TASK_ID}/complete" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "writer",
    "note": "Completed! Summary...",
    "deliverables": ["path/to/output.md"]
  }'

bash

curl -X POST "http://localhost:8080/api/tasks/{TASK_ID}/complete" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "writer",
    "note": "Completed! Summary...",
    "deliverables": ["path/to/output.md"]
  }'

Step 5: Check for @Mentions

bash

curl "http://localhost:8080/api/mentions?agent=writer"

Mark as read when done.


Create the agent directories:

```bash
mkdir -p ~/.openclaw/agents/{writer,growth,dev,ux,data}/agent
mkdir -p ~/.openclaw/workspace-{writer,growth,dev,ux,data}

bash

curl "http://localhost:8080/api/mentions?agent=writer"

完成后标记为已读。


创建Agent目录：

```bash
mkdir -p ~/.openclaw/agents/{writer,growth,dev,ux,data}/agent
mkdir -p ~/.openclaw/workspace-{writer,growth,dev,ux,data}

Task Lifecycle

任务生命周期

backlog → todo → in_progress → review → done
   │        │         │           │
   │        │         │           └─ Team Lead approves
   │        │         └─ Agent completes (→ review)
   │        └─ Agent picks up (→ in_progress)
   └─ Team Lead prioritizes (→ todo)

backlog → todo → in_progress → review → done
   │        │         │           │
   │        │         │           └─ Team Lead 审批
   │        │         └─ Agent 完成（→ review）
   │        └─ Agent 领取（→ in_progress）
   └─ Team Lead 优先级排序（→ todo）

Team Lead Operations

Team Lead 操作

Creating a Task

创建任务

bash

curl -X POST http://localhost:8080/api/tasks \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Task title",
    "description": "Detailed description",
    "priority": "high",
    "assignee": "writer",
    "tags": ["tag1", "tag2"],
    "createdBy": "lead"
  }'

Priority:

urgent

high

medium

low

bash

curl -X POST http://localhost:8080/api/tasks \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Task title",
    "description": "Detailed description",
    "priority": "high",
    "assignee": "writer",
    "tags": ["tag1", "tag2"],
    "createdBy": "lead"
  }'

优先级：

urgent

、

high

、

medium

、

low

Moving to Todo

移至待办

bash

curl -X PATCH "http://localhost:8080/api/tasks/{id}" \
  -H "Content-Type: application/json" \
  -d '{"status": "todo"}'

bash

curl -X PATCH "http://localhost:8080/api/tasks/{id}" \
  -H "Content-Type: application/json" \
  -d '{"status": "todo"}'

Approving Completed Work

审批已完成工作

bash

curl -X PATCH "http://localhost:8080/api/tasks/{id}" \
  -H "Content-Type: application/json" \
  -d '{"status": "done"}'

bash

curl -X PATCH "http://localhost:8080/api/tasks/{id}" \
  -H "Content-Type: application/json" \
  -d '{"status": "done"}'

Adding Deliverable Path

添加交付物路径

bash

curl -X PATCH "http://localhost:8080/api/tasks/{id}" \
  -H "Content-Type: application/json" \
  -d '{"deliverable": "path/to/file.md"}'

bash

curl -X PATCH "http://localhost:8080/api/tasks/{id}" \
  -H "Content-Type: application/json" \
  -d '{"deliverable": "path/to/file.md"}'

Worker Agent Operations

Worker Agent 操作

Picking Up Tasks

领取任务

bash

curl -X POST "http://localhost:8080/api/tasks/{id}/pick" \
  -H "Content-Type: application/json" \
  -d '{"agent": "{AGENT_ID}"}'

bash

curl -X POST "http://localhost:8080/api/tasks/{id}/pick" \
  -H "Content-Type: application/json" \
  -d '{"agent": "{AGENT_ID}"}'

Logging Progress

记录进度

bash

curl -X POST "http://localhost:8080/api/tasks/{id}/log" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "{AGENT_ID}",
    "action": "progress",
    "note": "Updated the widget component"
  }'

Actions:

picked

progress

blocked

completed

bash

curl -X POST "http://localhost:8080/api/tasks/{id}/log" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "{AGENT_ID}",
    "action": "progress",
    "note": "Updated the widget component"
  }'

操作类型：

picked

、

progress

、

blocked

、

completed

Completing a Task

完成任务

bash

curl -X POST "http://localhost:8080/api/tasks/{id}/complete" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "{AGENT_ID}",
    "note": "Completed! Summary of changes...",
    "deliverables": ["docs/api.md", "src/feature.js"]
  }'

Deliverables render as markdown in the task view.

bash

curl -X POST "http://localhost:8080/api/tasks/{id}/complete" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "{AGENT_ID}",
    "note": "Completed! Summary of changes...",
    "deliverables": ["docs/api.md", "src/feature.js"]
  }'

交付物将在任务视图中以markdown格式显示。

Comments & @Mentions

评论与@提及

Adding a Comment

添加评论

bash

curl -X POST "http://localhost:8080/api/tasks/{id}/comments" \
  -H "Content-Type: application/json" \
  -d '{
    "author": "agent-id",
    "content": "Hey @other-agent, need your input here"
  }'

bash

curl -X POST "http://localhost:8080/api/tasks/{id}/comments" \
  -H "Content-Type: application/json" \
  -d '{
    "author": "agent-id",
    "content": "Hey @other-agent, need your input here"
  }'

Checking for @Mentions

查看@提及

bash

curl "http://localhost:8080/api/mentions?agent={AGENT_ID}"

bash

curl "http://localhost:8080/api/mentions?agent={AGENT_ID}"

Marking Mentions as Read

标记提及为已读

bash

curl -X POST "http://localhost:8080/api/mentions/read" \
  -H "Content-Type: application/json" \
  -d '{"agent": "{AGENT_ID}", "all": true}'

bash

curl -X POST "http://localhost:8080/api/mentions/read" \
  -H "Content-Type: application/json" \
  -d '{"agent": "{AGENT_ID}", "all": true}'

API Reference

API 参考

Tasks

任务

Endpoint	Method	Description
`/api/tasks`	GET	List all tasks
`/api/tasks`	POST	Create new task
`/api/tasks/{id}`	GET	Get task detail
`/api/tasks/{id}`	PATCH	Update task fields
`/api/tasks/{id}`	DELETE	Delete task
`/api/tasks/mine?agent={id}`	GET	Agent's assigned tasks
`/api/tasks/{id}/pick`	POST	Agent picks up task
`/api/tasks/{id}/log`	POST	Log work action
`/api/tasks/{id}/complete`	POST	Complete task (→ review)
`/api/tasks/{id}/comments`	POST	Add comment

端点	方法	描述
`/api/tasks`	GET	列出所有任务
`/api/tasks`	POST	创建新任务
`/api/tasks/{id}`	GET	获取任务详情
`/api/tasks/{id}`	PATCH	更新任务字段
`/api/tasks/{id}`	DELETE	删除任务
`/api/tasks/mine?agent={id}`	GET	获取Agent的已分配任务
`/api/tasks/{id}/pick`	POST	Agent领取任务
`/api/tasks/{id}/log`	POST	记录工作操作
`/api/tasks/{id}/complete`	POST	完成任务（→ 审核）
`/api/tasks/{id}/comments`	POST	添加评论

Agents & System

Agent与系统

Endpoint	Method	Description
`/api/agents`	GET	List all agents
`/api/seed`	POST	Initialize agents (first run)
`/api/mentions?agent={id}`	GET	Get unread @mentions
`/api/mentions/read`	POST	Mark mentions as read

端点	方法	描述
`/api/agents`	GET	列出所有Agent
`/api/seed`	POST	初始化Agent（首次运行）
`/api/mentions?agent={id}`	GET	获取未读@提及
`/api/mentions/read`	POST	标记提及为已读

Files

文件

Endpoint	Method	Description
`/api/files/{path}`	GET	Read deliverable content

端点	方法	描述
`/api/files/{path}`	GET	读取交付物内容

Recommended Agent Team Structure

Agent	Role	Responsibilities
Lead	Team Lead	Strategy, task creation, approvals
Writer	Content	Blog posts, documentation, copy
Growth	Marketing	SEO, campaigns, outreach
Dev	Engineering	Features, bugs, code
UX	Product	Design, activation, user flows
Data	Analytics	Metrics, reports, insights

Agent	角色	职责
Lead	Team Lead	策略制定、任务创建、审批
Writer	内容创作	博客文章、文档、文案
Growth	营销推广	SEO、营销活动、对外拓展
Dev	工程开发	功能开发、Bug修复、代码编写
UX	产品设计	设计、用户激活、用户流程
Data	数据分析	指标统计、报告生成、洞察分析

Configuration

配置

Environment Variables

环境变量

Create

.env

in your Mission Control app directory (optional):

env

PORT=8080

在你的Mission Control应用目录中创建

.env

（可选）：

env

PORT=8080

Data Storage

数据存储

All data is stored locally in the

data/

directory:

File	Contents
`data/tasks.json`	All tasks, comments, work logs
`data/agents.json`	Agent status and metadata
`data/mentions.json`	@mention notifications

Add

data/

to your

.gitignore

— user data shouldn't be committed.

所有数据本地存储在

data/

目录中：

文件	内容
`data/tasks.json`	所有任务、评论、工作日志
`data/agents.json`	Agent状态与元数据
`data/mentions.json`	@提及通知

将

data/

添加到你的

.gitignore

中——用户数据不应提交到版本库。

Example: Running a Multi-Agent Workflow

示例：运行多Agent工作流

Lead creates task:

bash

curl -X POST http://localhost:8080/api/tasks \
  -H "Content-Type: application/json" \
  -d '{"title": "Write Q1 Report", "assignee": "writer", "priority": "high"}'

Lead moves to todo:

bash

curl -X PATCH http://localhost:8080/api/tasks/123 \
  -d '{"status": "todo"}'

Writer picks up via heartbeat:

bash

curl -X POST http://localhost:8080/api/tasks/123/pick \
  -d '{"agent": "writer"}'

Writer completes:

bash

curl -X POST http://localhost:8080/api/tasks/123/complete \
  -d '{"agent": "writer", "deliverables": ["reports/q1.md"]}'

Lead reviews and approves:

bash

curl -X PATCH http://localhost:8080/api/tasks/123 \
  -d '{"status": "done"}'

Lead创建任务：

bash

curl -X POST http://localhost:8080/api/tasks \
  -H "Content-Type: application/json" \
  -d '{"title": "Write Q1 Report", "assignee": "writer", "priority": "high"}'

Lead移至待办：

bash

curl -X PATCH http://localhost:8080/api/tasks/123 \
  -d '{"status": "todo"}'

Writer通过心跳领取：

bash

curl -X POST http://localhost:8080/api/tasks/123/pick \
  -d '{"agent": "writer"}'

Writer完成任务：

bash

curl -X POST http://localhost:8080/api/tasks/123/complete \
  -d '{"agent": "writer", "deliverables": ["reports/q1.md"]}'

Lead审核并批准：

bash

curl -X PATCH http://localhost:8080/api/tasks/123 \
  -d '{"status": "done"}'

Tips

小贴士

Heartbeat frequency: 15 minutes is a good default
Priority order: Agents should work
```
urgent
```
→
```
high
```
→
```
medium
```
→
```
low
```
Deliverables: Include all file paths modified in the task
@Mentions: Use to coordinate between agents on dependencies
Isolation: Each agent has its own workspace for safety
Storage: Data persists in
```
data/
```
directory — back it up if needed

心跳频率：15分钟是不错的默认值
优先级顺序：Agent应按
```
urgent
```
→
```
high
```
→
```
medium
```
→
```
low
```
的顺序工作
交付物：包含任务中修改的所有文件路径
@提及：用于在Agent之间协调依赖关系
隔离性：每个Agent有自己的工作区以确保安全
存储：数据保存在
```
data/
```
目录中——如有需要请备份

Resources

资源

GitHub: https://github.com/0xindiebruh/openclaw-mission-control
Demo: See example agent setups in
```
/examples
```

GitHub：https://github.com/0xindiebruh/openclaw-mission-control
示例：查看
```
/examples
```
中的Agent设置示例

openclaw-mission-control

Original

Translation

Mission Control

Mission Control 任务指挥中心

Overview

概述

Quick Start

快速开始

1. Install the Kanban Board

1. 安装看板面板

Clone the Mission Control app

克隆Mission Control应用

Install dependencies

安装依赖

Start the server

启动服务器

2. Configure Your Agents

2. 配置你的Agent

3. Seed the Database (First Run)

3. 初始化数据库（首次运行）

4. Configure OpenClaw Multi-Agent Mode

4. 配置OpenClaw多Agent模式

5. Set up Agent Heartbeats

5. 设置Agent心跳

Agent Heartbeat

Agent Heartbeat

Step 1: Check for Tasks

Step 1: Check for Tasks

Step 2: Pick up todo tasks

Step 2: Pick up todo tasks

Step 3: Log Progress

Step 3: Log Progress

Step 4: Complete Tasks

Step 4: Complete Tasks

Step 5: Check for @Mentions

Step 5: Check for @Mentions

Task Lifecycle

任务生命周期

Team Lead Operations

Team Lead 操作

Creating a Task

创建任务

Moving to Todo

移至待办

Approving Completed Work

审批已完成工作

Adding Deliverable Path

添加交付物路径

Worker Agent Operations

Worker Agent 操作

Picking Up Tasks

领取任务

Logging Progress

记录进度

Completing a Task

完成任务

Comments & @Mentions

评论与@提及

Adding a Comment

添加评论

Checking for @Mentions

查看@提及

Marking Mentions as Read

标记提及为已读

API Reference

API 参考

Tasks

任务

Agents & System

Agent与系统

Files

文件

Recommended Agent Team Structure

推荐的Agent团队结构

Configuration

配置

Environment Variables

环境变量

Data Storage

Step 2: Pick up
`todo`
tasks

Step 2: Pick up
`todo`
tasks