Verified project record

builderz-labs/mission-control

A self-hosted control plane for dispatching tasks, inspecting runs, reviewing failures, and tracking spend across multiple AI agent runtimes from a single local dashboard. It coordinates existing agent frameworks rather than functioning as an agent framework itself.

Project overview

It sits above multiple agent runtimes to unify governance, spend tracking, and quality review across different frameworks.

Project type: MCP · AI Agent · Workflow
Use cases: Knowledge Q&A · Automation
Deployment: Refer to project documentation
License: MIT

Best for

Operations teams and developers who need a self-hosted dashboard to monitor activity, logs, and costs across multiple agent frameworks simultaneously.
Teams requiring formal task approval workflows, where an Aegis approval record is enforced before work is marked as done.

Key capabilities

Tracks work on a task board through inbox, assignment, execution, review, quality review, and completion. An Aegis approval record is required before a task reaches done.
Monitors agents through registration state, heartbeats, sessions, configuration, local runtime discovery, activity streams, logs, token use, and cost views.
Inspects filesystem-backed memory and linked session knowledge, discovers local skill roots, and scans registry content before installation.
Exposes control plane functionalities through a Web UI, CLI, an MCP server, an OpenAPI-described REST API, WebSocket, and SSE.
Creates recurring task templates that generate dated work on a cron schedule.
Provides adapters and observation surfaces for multiple runtimes. The documented total includes OpenClaw, Claude Code, Codex, CrewAI, LangGraph, AutoGen, and Claude SDK workflows.

Limitations and risks

The software is currently in alpha, meaning APIs, schemas, and configuration may change between releases.
Adapter depth varies by agent runtime, and feature parity across different frameworks is not guaranteed.
The system must be kept on a trusted network unless a TLS reverse proxy and allowed hosts are configured, a requirement tied to its alpha status.

Getting started

Setup difficulty is documented as easy because Docker Compose deployment is a single command. The documented path for initial success is running docker compose up and then opening http://localhost:3000/setup.

Alternatives and comparisons

A fair-code platform to build and deploy AI agents and workflows with a visual canvas, custom code, and over 1500 integrations.
A modular, multi-technology enterprise sample application demonstrating multi-agent orchestration and MCP servers for travel agency operations.
An open-source, all-in-one Agent chatbot platform that integrates with mainstream IM apps and supports plugins, LLMs, and enterprise knowledge bases.

Project comparisons

Evidence and sources

README: Self-hosted control plane for operating AI agents.
GitHub project description: Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
README: Use Mission Control when multiple agents or runtimes make it hard to answer who owns a task, what executed, which result passed review, or where spend and failures accumulated.
README: Mission Control is alpha software.
README: The task board tracks work through inbox, assignment, execution, review, quality review, and completion. Aegis review requires an approval record before a task reaches done.

Reviewed at: 2026-07-15T19:43:03Z

Open original GitHub project