Mission Control

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

Overview

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

Quick Start

1. Install the Kanban Board

# Clone the Mission Control app
git clone https://github.com/0xindiebruh/openclaw-mission-control.git
cd mission-control

# Install dependencies
npm install

# Start the server
npm run dev

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

2. Configure Your Agents

Edit lib/config.ts to define your agent team:

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)

Initialize the agents in the database:

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.

4. Configure OpenClaw Multi-Agent Mode

Add each agent to your ~/.openclaw/config.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)

5. Set up Agent Heartbeats

Each worker agent needs a HEARTBEAT.md in their agentDir:

# Agent Heartbeat

## Step 1: Check for Tasks

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

Step 2: Pick up todo tasks

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

Step 3: Log Progress

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

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

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}

Task Lifecycle

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

Team Lead Operations

Creating a Task

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

Moving to Todo

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

Approving Completed Work

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

Adding Deliverable Path

curl