Mission Control
Self-hosted control plane to dispatch tasks, track spend, and operate AI agent runtimes.
Dispatch tasks, inspect runs, and coordinate OpenClaw, Claude Code, and Codex from one dashboard.
Mission Control is a self-hosted dashboard backed by SQLite for operating AI agents across multiple runtimes. It suits developers managing complex multi-agent workflows who need a single place to track tasks, review failures, and monitor spend.
What it is
It sits above agent runtimes like OpenClaw, Claude Code, and Codex to handle task dispatch, execution review, Aegis quality gates, and completion receipts. The interface provides a web UI, CLI, MCP server, and a REST API backed by local SQLite storage.
Who it's for
It suits developers running multiple AI agent squads who need centralized queues, execution logs, and governance. It is the wrong tool if you run a single agent from its native CLI or need a managed multi-tenant SaaS.
Key features
Multi-Runtime Support
Operate OpenClaw, Claude Code, Codex, and other agent runtimes from a single local dashboard.
Aegis Quality Gate
Require mandatory approval records and completion receipts before tasks reach done status.
Memory and Skills Hub
Inspect filesystem-backed memory graphs and discover local skill roots before installation.
Multiple Interfaces
Interact with tasks and agents using the web UI, CLI, MCP server, or REST API.
Up and running in 3 steps
Our honest verdict
What's great
- Coordinates multiple disparate AI agent runtimes from one local dashboard
- Includes built-in Aegis quality gates and mandatory review workflows
- Tracks token use, spend, and system events in an activity stream
- Provides a Model Context Protocol (MCP) server for Claude integration
Where it falls short
- Alpha software with APIs, schemas, and configurations subject to change
- Requires Node.js 22 or Docker with manual setup and security configuration
- Live session messaging requires a connected runtime gateway
Pricing & license
Free under its MIT licence, with the only cost being running the self-hosted software on your own infrastructure.
Open remote AI-training roles
767 open remote AI-training roles, updated November 14, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
What agent runtimes does Mission Control support?
It supports OpenClaw, Claude Code, Codex, CrewAI, LangGraph, AutoGen, and Claude SDK workflows with varying depth.
Is Mission Control an agent framework?
No, it sits above agent runtimes and does not replace their reasoning or tool loops.
How is data stored?
State is stored locally in SQLite using better-sqlite3 with WAL mode enabled.
