builderz-labs/mission-control

Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.

What it solves

Mission Control provides a centralized, self-hosted control plane for managing multiple AI agents and runtimes. It solves the problem of fragmentation where operators cannot easily track who owns a task, what has been executed, where failures occurred, or how much budget is being spent across different agent frameworks.

How it works

It acts as an orchestration layer that sits above agent runtimes (such as OpenClaw, Claude Code, CrewAI, and LangGraph) without replacing their internal reasoning loops. It uses a local SQLite database to store state and provides a web dashboard, CLI, and REST API for dispatching tasks, monitoring heartbeats, and reviewing agent activity.

Who it’s for

Operators who manage a fleet of AI agents across various runtimes and need a single source of truth for governance, task tracking, and cost monitoring.

Highlights

  • Task Management: A full pipeline from inbox and assignment to execution and quality review (via the Aegis quality gate).
  • Agent Governance: Tools for registration, session tracking, heartbeat monitoring, and workspace synchronization.
  • Operational Visibility: Activity streams, cron-based task scheduling, and detailed token use and cost views.
  • Knowledge Management: A memory browser and relationship graph to inspect filesystem-backed agent memory.
  • Extensible Interfaces: Support for Web UI, CLI, MCP server, and OpenAPI-described REST API.

Related

  • Project
    paperclipai/paperclip

    An open-source orchestration platform for managing teams of AI agents through org charts, budgets, and goal-aligned task management.

  • Project
    codeaholicguy/ai-devkit

    AI DevKit is a local npm‑based control plane that unifies configuration, monitoring, cross‑agent messaging, searchable SQLite memory, and composable engineering “skills” (requirements, design, testing, review, etc.) for many AI coding assistants such as Claude Code, Gemini CLI, Codex CLI, Cursor, and GitHub Copilot. It lets teams manage multiple agents from a single console, keep project conventions in a searchable store, and enforce a senior‑engineer workflow without modifying the underlying LLMs.

  • Project
    asheshgoplani/agent-deck

    A command center for AI coding agents that allows users to manage, orchestrate, and switch between multiple agent sessions across different projects in one terminal.

  • Project
    EXboys/evotown

    A private enterprise control plane for AI agents that unifies model routing, skill distribution, and knowledge management across different local agent runtimes.

  • Project
    openswarm-ai/openswarm

    A local orchestrator for managing multiple AI agents in parallel via a spatial dashboard, featuring Git worktree isolation and unified tool approvals.