> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/builderz-labs/mission-control/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Mission Control is an open-source dashboard for AI agent orchestration. Manage agent fleets, track tasks, monitor costs, and orchestrate workflows from a single pane of glass.

## What is Mission Control?

Mission Control is the **open-source dashboard for AI agent orchestration**. It provides a centralized command center to manage agent fleets, track tasks, monitor costs, and orchestrate complex multi-agent workflows.

<Info>
  Mission Control is alpha software under active development. APIs, database schemas, and configuration formats may change between releases. Review the security considerations before deploying to production.
</Info>

## Why Mission Control?

Running AI agents at scale means juggling sessions, tasks, costs, and reliability across multiple models and channels. Mission Control solves this with:

<CardGroup cols={2}>
  <Card title="28 Specialized Panels" icon="grid">
    Tasks, agents, logs, tokens, memory, cron, alerts, webhooks, pipelines, and more
  </Card>

  <Card title="Real-time Everything" icon="bolt">
    WebSocket + SSE push updates with smart polling that pauses when you're away
  </Card>

  <Card title="Zero External Dependencies" icon="database">
    SQLite database with WAL mode. No Redis, Postgres, or Docker required
  </Card>

  <Card title="Role-based Access" icon="shield">
    Viewer, operator, and admin roles with session + API key authentication
  </Card>

  <Card title="Quality Gates" icon="check">
    Built-in review system that blocks task completion without sign-off
  </Card>

  <Card title="Multi-gateway Support" icon="network-wired">
    Connect to multiple OpenClaw gateways simultaneously with device identity authentication
  </Card>
</CardGroup>

## Core Features

### Agent Management

Monitor agent status, spawn new sessions, view heartbeats, and manage the full agent lifecycle from registration to retirement. Track agent health with automatic heartbeat monitoring.

### Kanban Task Board

Full-featured task board with six workflow columns (inbox → backlog → todo → in-progress → review → done). Includes drag-and-drop, priority levels, assignments, and threaded comments.

### Real-time Monitoring

Live activity feed, session inspector, and log viewer with filtering. WebSocket connection to gateway for instant event delivery with automatic reconnection.

### Cost Tracking

Token usage dashboard with per-model breakdowns, trend charts, and cost analysis. Track spending across Claude, GPT, and other models with automatic price updates.

### Direct CLI Integration

Connect Claude Code, Codex, or any CLI tool directly to Mission Control without requiring a gateway. Auto-register agents and report token usage inline with heartbeats.

### Agent SOUL System

Define agent personality, capabilities, and behavioral guidelines via SOUL markdown files. Edit in the UI or directly in workspace files—changes sync bidirectionally.

### Claude Code Session Tracking

Automatically discovers and tracks local Claude Code sessions from `~/.claude/projects/`. Extracts token usage, model info, and cost estimates from JSONL transcripts.

## Architecture Overview

Mission Control is built with modern web technologies optimized for performance and developer experience:

| Layer      | Technology                           |
| ---------- | ------------------------------------ |
| Framework  | Next.js 16 (App Router)              |
| UI         | React 19, Tailwind CSS 3.4           |
| Language   | TypeScript 5.7                       |
| Database   | SQLite via better-sqlite3 (WAL mode) |
| State      | Zustand 5                            |
| Charts     | Recharts 3                           |
| Real-time  | WebSocket + Server-Sent Events       |
| Auth       | scrypt hashing, session tokens, RBAC |
| Validation | Zod 4                                |
| Testing    | Vitest + Playwright (148 E2E tests)  |

## Authentication & Authorization

Mission Control supports three authentication methods:

* **Session cookie** — Web dashboard login with 7-day expiry
* **API key** — Headless access via `x-api-key` header
* **Google Sign-In** — OAuth with admin approval workflow

Three role levels control access:

* **Viewer** — Read-only access to all panels
* **Operator** — Read + write (tasks, agents, chat)
* **Admin** — Full access (users, settings, system operations)

## Use Cases

<CardGroup cols={2}>
  <Card title="Multi-Agent Coordination" icon="users">
    Orchestrate teams of agents working together on complex projects with task assignment and inter-agent messaging
  </Card>

  <Card title="Development Teams" icon="code">
    Track Claude Code sessions, monitor token usage, and manage coding agents from a single dashboard
  </Card>

  <Card title="Production Monitoring" icon="chart-line">
    Real-time visibility into agent health, performance metrics, and cost tracking for production deployments
  </Card>

  <Card title="Quality Assurance" icon="clipboard-check">
    Review gates ensure agent output meets quality standards before marking tasks complete
  </Card>
</CardGroup>

## What's Next?

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Get Mission Control running in 5 minutes
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Detailed setup instructions for all environments
  </Card>
</CardGroup>