Repolode
Submit
builderz-labs

builderz-labs/mission-control

Self-hosted dashboard for dispatching tasks, reviewing agent runs, tracking spend, and coordinating AI agent runtimes like OpenClaw, Claude Code, and Codex.

View on GitHubWebsite
Stars
6,384
Forks
118
Open issues
55
Last commit
3 days ago

What is it?

Mission Control is a self-hosted control plane for operating AI agents. It gives operators one local dashboard, backed by SQLite, to see who owns a task, what executed, which result passed review, and where spend and failures accumulated. It sits above agent runtimes rather than replacing their reasoning or tool loops.

The project covers tasks (inbox, assignment, execution, review, and completion receipts), agents (registration, heartbeats, sessions, and workspace sync), operations (activity stream, schedules, alerts, webhooks, logs, and token and cost views), and a memory browser and skills registry. Access is available through a web UI, a CLI, an MCP server, a REST API described by OpenAPI, plus WebSocket and SSE.

It is built with Next.js, React, TypeScript, and SQLite, and can be installed locally with a script, run with Docker Compose, or deployed as a standalone build. The project is marked alpha, so APIs and schemas may change between releases.

Key features

  • 01Dispatch tasks to agents and track them through review and completion.
  • 02Register agents and monitor heartbeats, sessions, and runtime status.
  • 03Track token use and cost, plus logs, alerts, and webhooks.
  • 04Browse agent memory and manage a skills registry.
  • 05Control access with roles, API keys, and session login.
  • 06Interact through a web UI, CLI, MCP server, or REST API.

Use cases

  • Running several AI agents on one machine and needing to see which task each one owns.
  • Reviewing agent run results before marking work as done.
  • Tracking token spend and failures across multiple agent runtimes.
  • Giving an internal team a self-hosted dashboard for agent operations.

Quick start

  1. 1

    Pull the published Docker image

    docker pull ghcr.io/builderz-labs/mission-control:latest
  2. 2

    Run the container and open port 3000

    docker run --rm -p 3000:3000 ghcr.io/builderz-labs/mission-control:latest
  3. 3

    Open http://localhost:3000/setup and create the first admin account

Things to know

  • Mission Control is alpha software, so APIs, schemas, and configuration may change between releases.
  • A source install requires Node.js 22 or newer and pnpm.
  • Keep it on a trusted network unless a TLS reverse proxy and MC_ALLOWED_HOSTS are configured.

Topics

#ai-agents#agent-orchestration#self-hosted#task-management#observability#mcp#nextjs#typescript#agent-observability#agent-operations

FAQ

What is mission-control?
Self-hosted dashboard for dispatching tasks, reviewing agent runs, tracking spend, and coordinating AI agent runtimes like OpenClaw, Claude Code, and Codex. Mission Control is a self-hosted control plane for operating AI agents. It gives operators one local dashboard, backed by SQLite, to see who owns a task, what executed, which result passed review, and where spend and failures accumulated. It sits above agent runtimes rather than replacing their reasoning or tool loops.
Is mission-control free to use? What license does it have?
mission-control is open source under the MIT license. Check the license terms before using it in commercial products.
Is mission-control still maintained?
Actively maintained. The last commit to mission-control was on Oct 19, 2026.
What can I use mission-control for?
Running several AI agents on one machine and needing to see which task each one owns. Reviewing agent run results before marking work as done. Tracking token spend and failures across multiple agent runtimes. Giving an internal team a self-hosted dashboard for agent operations.
How do I install mission-control?
Pull the published Docker image: docker pull ghcr.io/builderz-labs/mission-control:latest Run the container and open port 3000: docker run --rm -p 3000:3000 ghcr.io/builderz-labs/mission-control:latest Open http://localhost:3000/setup and create the first admin account
Where can I get mission-control?
The source code and installation instructions are on GitHub: https://github.com/builderz-labs/mission-control

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects