openclaw-mission-control

Coordinate a team of AI agents using a Kanban-style task board with HTTP API. Mission Control lets you run multiple AI agents that collaborate on tasks: The board runs at . Edit lib/config.ts to define your agent team: 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. Add each agent to your ~/.openclaw/config.json : Key fields: Each worker agent needs a HEARTBEAT.md in their agentDir : Mark as read when done. Priority: urgent , high , medium , low Actions: picked , progress , blocked , completed Deliverables render as markdown in the task view. Create .env in your Mission Control app directory (optional): All data is stored locally in the data/ directory: Add data/ to your .gitignore — user data shouldn't be committed. Lead creates task: Lead moves to todo: Writer picks up via heartbeat: Writer completes: Lead reviews and approves: - 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 API : Agents interact via REST endpoints - Local Storage : All data stored in JSON files — no external database needed - id : Unique agent identifier (must match an agent ID in lib/config.ts ) - workspace : Agent's working directory for files - agentDir...