Coordinate AI agent teams via a Kanban task board with local JSON storage. Enables multi-agent workflows with a Team Lead assigning work and Worker Agents executing tasks via heartbeat polling. Perfect for building AI agent command centers.

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 The board runs at http://localhost:8080 . 2. Configure Your Agents Edit lib/config.ts to define your agent team: 3. Seed the Database (First Run) Initialize the agents in the database: 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 : 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 : bash curl "http://localhost:8080/api/tasks/mine?agent=writer" Step 2: Pick up todo tasks Step 3: Log Progress Step 4: Complete Tasks Step 5: Check for @Mentions Mark as read when done. bash mkdir p ~/.openclaw/agents/{writer,growth,dev,ux,data}/agent mkdir p ~/.openclaw/workspace {writer,growth,dev,ux,data} backlog → todo → in progress → review → done │ │ │ │ │ │ │ └─ Team Lead approves │ │ └─ Agent completes (→ review) │ └─ Agent picks up (→ in progress) └─ Team Lead prioritizes (→ todo) 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" }' 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": "done"}' bash curl X PATCH "http://localhost:8080/api/tasks/{id}" \ H "Content Type: application/json" \ d '{"deliverable": "path/to/file.md"}' 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}/log" \ H "Content Type: application/json" \ d '{ "agent": "{AGENT ID}", "action": "progress", "note": "Updated the widget component" }' 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"] }' 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 "http://localhost:8080/api/mentions?agent={AGENT ID}" bash curl X POST "http://localhost:8080/api/mentions/read" \ H "Content Type: application/json" \ d '{"agent": "{AGENT ID}", "all": true}' env PORT=8080 bash curl X POST http://localhost:8080/api/tasks \ H "Content Type: application/json" \ d '{"title": "Write Q1 Report", "assignee": "writer", "priority": "high"}' bash curl X PATCH http://localhost:8080/api/tasks/123 \ d '{"status": "todo"}' bash curl X POST http://localhost:8080/api/tasks/123/pick \ d '{"agent": "writer"}' bash curl X POST http://localhost:8080/api/tasks/123/complete \ d '{"agent": "writer", "deliverables": ["reports/q1.md"]}' bash curl X PATCH http://localhost:8080/api/tasks/123 \ d '{"status": "done"}' Tips 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 Resources GitHub : https://github.com/0xindiebruh/openclaw mission control Demo : See example agent setups in /examples

openclaw-mission-control