← All projects
AI agents

Mission Control

A self-hosted dashboard for assigning tasks to AI agents, reviewing their work and tracking spending.

New this week

What it does

Mission Control sits above AI agent tools such as OpenClaw, Claude Code and Codex. From one local dashboard you can hand out tasks, watch runs, review failures, check token use and costs, and approve work.

It also keeps a memory browser, a skills registry, roles and audit records. It runs on your own computer or server and stores its data locally.

The README says it is early, alpha software and advises reading its security guidance before putting it on a network.

Who it's for

Developers and teams running several AI agents who need oversight of what they do.

Can I use it without coding?

With some setup. It installs with a script or Docker, then runs in your web browser. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Mac, Windows, Linux, Server
Computer
An ordinary computer is fine
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Install it with the project's install script or with Docker, following the README.
  2. Open the setup page in your web browser and create the first admin account.
  3. Connect your agent tools and start assigning tasks.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe