Skip to content
Back to search

command-center

Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in one place.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/jontsai/openclaw-command-center with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/jontsai/openclaw-command-center'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/jontsai--openclaw-command-center/badge.svg)](/listings/jontsai--openclaw-command-center)

HTML

<a href="/listings/jontsai--openclaw-command-center"><img src="/api/listings/jontsai--openclaw-command-center/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npx clawhub@latest install command-center
cd skills/command-center
node lib/server.js

**Dashboard runs at http://localhost:3333** ๐ŸŽ‰

<details> <summary>Alternative: Git clone</summary>

git clone https://github.com/jontsai/openclaw-command-center
cd openclaw-command-center
node lib/server.js

</details>

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md ยท Manifest ยท 69 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. ---
  2. name: command-center
  3. version: 1.5.0
  4. description: Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in one place.
  5. metadata:
  6. openclaw:
  7. requires:
  8. node: ">=18"
  9. install:
  10. - id: start
  11. kind: shell
  12. command: "node lib/server.js"
  13. label: "Start Command Center (http://localhost:3333)"
  14. ---
  15. # OpenClaw Command Center
  16. Mission control for your AI workforce.
  17. ## Quick Start
  18. ```bash
  19. npx clawhub@latest install command-center
  20. cd skills/command-center
  21. node lib/server.js
  22. ```
  23. Dashboard runs at **http://localhost:3333**
  24. ## Features
  25. - **Session Monitoring** โ€” Real-time view of all AI sessions with live updates
  26. - **LLM Fuel Gauges** โ€” Track Claude, Codex, and other model usage
  27. - **System Vitals** โ€” CPU, Memory, Disk, Temperature
  28. - **Cron Jobs** โ€” View and manage scheduled tasks
  29. - **Cerebro Topics** โ€” Automatic conversation organization
  30. - **Cost Tracking** โ€” Per-session costs, projections, savings estimates
  31. - **Privacy Controls** โ€” Hide sensitive topics for demos
  32. ## Configuration
  33. The dashboard auto-detects your OpenClaw workspace. Set `OPENCLAW_WORKSPACE` to override.
  34. ### Authentication
  35. | Mode | Use Case |
  36. | ------------ | ----------------- |
  37. | `none` | Local development |
  38. | `token` | Remote access |
  39. | `tailscale` | Team VPN |
  40. | `cloudflare` | Public deployment |
  41. ```bash
  42. DASHBOARD_AUTH_MODE=tailscale node lib/server.js
  43. ```
  44. ## API
  45. | Endpoint | Description |
  46. | ----------------- | ---------------------------- |
  47. | `GET /api/state` | All dashboard data (unified) |
  48. | `GET /api/events` | SSE stream for live updates |
  49. | `GET /api/health` | Health check |
  50. ## Links
  51. - [GitHub](https://github.com/jontsai/openclaw-command-center)
  52. - [ClawHub](https://www.clawhub.ai/jontsai/command-center)
  53. - [Documentation](https://github.com/jontsai/openclaw-command-center#readme)
README.md ยท README ยท 464 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # ๐Ÿฆž OpenClaw Command Center
  2. English | [็ฎ€ไฝ“ไธญๆ–‡](README.zh-CN.md)
  3. <div align="center">
  4. **Mission control for your AI agents**
  5. [![CI](https://github.com/jontsai/openclaw-command-center/actions/workflows/ci.yml/badge.svg)](https://github.com/jontsai/openclaw-command-center/actions/workflows/ci.yml)
  6. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
  7. [![Node](https://img.shields.io/badge/node-%3E%3D18-brightgreen)](https://nodejs.org)
  8. [![ClawHub](https://img.shields.io/badge/ClawHub-command--center-blue)](https://www.clawhub.ai/jontsai/command-center)
  9. [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](https://github.com/jontsai/openclaw-command-center/pulls)
  10. [Features](#features) โ€ข [Quick Start](#quick-start) โ€ข [Security](#-security) โ€ข [Configuration](#configuration)
  11. </div>
  12. ---
  13. ## Standalone monitoring, recommended companion
  14. ### Human-readable costs and channels
  15. Click **Est. API Cost** to enter a monthly spend baseline for the savings scenario.
  16. The baseline is stored only in this browser and dashboard path; no plan price is
  17. assumed. The selected calendar-day average is projected to 30 days and compared
  18. with your baseline. Include subscription and API spending for the same scope.
  19. Incomplete pricing stays marked partial, and negative differences are displayed.
  20. This is a what-if comparison, not realized savings or a billing forecast.
  21. Channel names come from OpenClaw's native directory, cached per provider/account
  22. for five minutes. Channel IDs remain in session-title and cost-breakdown tooltips.
  23. Unknown channels have an explicit generic label; stale cached names retain their
  24. status in the tooltip. No workspace-specific channel map or provider credentials
  25. are embedded in the dashboard. Directory reads are bounded and asynchronous.
  26. Cron Jobs lists OpenClaw automations through its read-only CLI API, cached for
  27. 30 seconds. Loading, partial and stale catalogs are labeled; missing legacy JSON
  28. files no longer imply zero automations. AI Jobs is a separate optional provider:
  29. without it the page shows "not connected", not an empty successful job catalog.
  30. **Command Center works out of the box without Spacesuit.** It owns OpenClaw
  31. sessions, health, jobs, usage and the common dashboard. For a minimal core-only
  32. view, run `COMMAND_CENTER_MODE=core npm start`.
  33. **Spacesuit is the highly recommended companion** for per-agent flavors, domain
  34. panels and workflows. Spacesuit can scaffold a workspace and collect data by itself,
  35. but it has **no graphical humanโ€“agent interaction surface of its own**; Command
  36. Center provides the dashboard and supported controls. The extension system does
  37. not add a chat composer.
  38. The [read-only extension API](docs/architecture/extension-api-v1.md) loads explicit,
  39. profile-bound Spacesuit snapshots through the existing state feed. Legacy built-in
  40. domain panels remain the default compatibility mode until you select a flavor or
  41. core-only mode; existing panels and data are not silently removed. See the
  42. [ownership and migration plan](docs/architecture/core-and-flavors.md).
  43. ## Why Command Center?
  44. Your AI agents are running 24/7. You need to know what they're doing.
  45. Command Center gives you **real-time visibility** into your OpenClaw deployment โ€” sessions, costs, system health, scheduled tasks โ€” all in one secure dashboard.
  46. ### โšก Fast
  47. - **Single API call** โ€” unified state endpoint, not 16+ separate requests
  48. - **2-second updates** โ€” real-time SSE push, not polling
  49. - **5-second cache** โ€” backend stays responsive under load
  50. - **Instant startup** โ€” no build step, no compilation
  51. ### ๐Ÿชถ Lightweight
  52. - **Zero dependencies** for users โ€” just Node.js
  53. - **~200KB total** โ€” dashboard + server
  54. - **No webpack/vite/bundler** โ€” runs directly
  55. - **No React/Vue/Angular** โ€” vanilla JS, works everywhere
  56. ### ๐Ÿ“ฑ Responsive
  57. - **Desktop & mobile** โ€” works on any screen size
  58. - **Dark mode** โ€” easy on the eyes, Starcraft-inspired
  59. - **Live updates** โ€” no manual refresh needed
  60. - **Offline-friendly** โ€” graceful degradation
  61. ### ๐Ÿ”ง Modern
  62. - **ES Modules** โ€” clean component architecture
  63. - **SSE streaming** โ€” efficient real-time updates
  64. - **REST API** โ€” integrate with your tools
  65. - **TypeScript-ready** โ€” JSDoc types included
  66. ### ๐Ÿ”’ Security (Most Important)
  67. Command Center takes security seriously:
  68. | Feature | Description |
  69. | ------------------------ | --------------------------------------------------- |
  70. | **Auth Modes** | Token, Tailscale, Cloudflare Access, IP allowlist |
  71. | **No external calls** | Dashboard runs 100% locally โ€” no telemetry, no CDNs |
  72. | **Localhost default** | Binds to `127.0.0.1` by default |
  73. | **Read-only by default** | View your agents without exposing control |
  74. | **No secrets in UI** | API keys, tokens never displayed |
  75. | **Audit logging** | Know who accessed what, when |
  76. ```bash
  77. # Secure deployment example (Tailscale)
  78. DASHBOARD_AUTH_MODE=tailscale node lib/server.js
  79. # Only users on your Tailscale network can access
  80. ```
  81. ---
  82. ## Features
  83. | Feature | Description |
  84. | -------------------------- | ------------------------------------------- |
  85. | ๐Ÿ“Š **Session Monitoring** | Real-time view of active AI sessions |
  86. | โ›ฝ **LLM Fuel Gauges** | Token usage, costs, quota remaining |
  87. | ๐Ÿ’ป **System Vitals** | CPU, memory, disk, temperature |
  88. | โฐ **Cron Jobs** | View and manage scheduled tasks |
  89. | ๐Ÿง  **Cerebro Topics** | Automatic conversation tagging |
  90. | ๐Ÿ‘ฅ **Operators** | Who's talking to your agents |
  91. | ๐Ÿ“ **Memory Browser** | View agent memory files |
  92. | ๐Ÿ”’ **Privacy Controls** | Hide sensitive topics for demos/screenshots |
  93. | ๐Ÿ’ฐ **Cost Breakdown** | Detailed per-model cost analysis |
  94. | ๐Ÿ“ˆ **Savings Projections** | Monthly cost vs. manual estimates |
  95. ---
  96. ## Quick Start
  97. ```bash
  98. npx clawhub@latest install command-center
  99. cd skills/command-center
  100. node lib/server.js
  101. ```
  102. **Dashboard runs at http://localhost:3333** ๐ŸŽ‰
  103. <details>
  104. <summary>Alternative: Git clone</summary>
  105. ```bash
  106. git clone https://github.com/jontsai/openclaw-command-center
  107. cd openclaw-command-center
  108. node lib/server.js
  109. ```
  110. </details>
  111. ---
  112. ## Zero-Config Experience
  113. Command Center **auto-detects** your OpenClaw workspace:
  114. 1. `$OPENCLAW_WORKSPACE` environment variable
  115. 2. `~/.openclaw-workspace` or `~/openclaw-workspace`
  116. 3. Common names: `~/molty`, `~/clawd`, `~/moltbot`
  117. If you have `memory/` or `state/` directories, you're good to go.
  118. ---
  119. ## Optional System Dependencies
  120. Command Center requires **only Node.js** to run. However, some system vitals features benefit from optional packages. Without them, the dashboard still works โ€” those metrics simply show zeros or fall back gracefully.
  121. | OS | Package | Purpose | Install | Without It |
  122. | --------------------- | ------------------- | ---------------------------------- | ------------------------------------------------------------- | --------------------------------- |
  123. | Linux | `sysstat` | Disk I/O vitals (IOPS, throughput) | `sudo apt install sysstat` | Disk stats show zeros |
  124. | Linux | `lm-sensors` | Additional temperature sensors | `sudo apt install lm-sensors` | Uses thermal_zone (usually works) |
  125. | macOS (Intel) | `osx-cpu-temp` | CPU temperature | [Build from source](https://github.com/lavoiesl/osx-cpu-temp) | Battery temp fallback |
  126. | macOS (Apple Silicon) | passwordless `sudo` | CPU temperature via `powermetrics` | Configure in sudoers | Shows note in UI |
  127. Command Center logs hints for missing optional dependencies once at startup.
  128. ---
  129. ## Configuration
  130. ### Environment Variables
  131. | Variable | Description | Default |
  132. | -------------------- | -------------- | ----------- |
  133. | `PORT` | Server port | `3333` |
  134. | `OPENCLAW_WORKSPACE` | Workspace root | Auto-detect |
  135. | `OPENCLAW_PROFILE` | Profile name | (none) |
  136. ### ๐Ÿ”’ Authentication
  137. | Mode | Use Case | Config |
  138. | ------------ | ------------- | --------------------------------------------------------- |
  139. | `none` | Local dev | `DASHBOARD_AUTH_MODE=none` |
  140. | `token` | API access | `DASHBOARD_AUTH_MODE=token DASHBOARD_TOKEN=secret` |
  141. | `tailscale` | Team access | `DASHBOARD_AUTH_MODE=tailscale` |
  142. | `cloudflare` | Public deploy | `DASHBOARD_AUTH_MODE=cloudflare` |
  143. | `allowlist` | IP whitelist | `DASHBOARD_AUTH_MODE=allowlist DASHBOARD_ALLOWED_IPS=...` |
  144. ### ๐Ÿ“‹ Recommended OpenClaw Settings
  145. For the best Command Center experience, configure your OpenClaw gateway:
  146. #### Slack Threading (Critical)
  147. Enable threading for all messages to get proper topic tracking:
  148. ```yaml
  149. # In your OpenClaw config (gateway.yaml or via openclaw gateway config)
  150. slack:
  151. capabilities:
  152. threading: all # Options: all, dm, group, none
  153. ```
  154. **Why this matters:** Without threading, the dashboard can't track conversation topics properly. Each thread becomes a trackable unit of work.
  155. #### Session Labels
  156. Use descriptive session labels for better dashboard visibility:
  157. ```yaml
  158. sessions:
  159. labelFormat: "{channel}:{topic}" # Customize as needed
  160. ```
  161. #### Cerebro (Topic Tracking)
  162. Enable Cerebro for automatic conversation tagging:
  163. ```bash
  164. # Initialize Cerebro directories
  165. mkdir -p ~/your-workspace/cerebro/topics
  166. mkdir -p ~/your-workspace/cerebro/orphans
  167. ```
  168. The dashboard will automatically detect and display topic data.
  169. ---
  170. ### Multi-Profile Support
  171. Running multiple OpenClaw instances?
  172. ```bash
  173. # Production dashboard
  174. node lib/server.js --profile production --port 3333
  175. # Development dashboard
  176. node lib/server.js --profile dev --port 3334
  177. ```
  178. ---
  179. ## API
  180. Command Center exposes a REST API:
  181. | Endpoint | Description |
  182. | ------------------- | -------------------------------------------------- |
  183. | `GET /api/state` | **Unified state** โ€” all dashboard data in one call |
  184. | `GET /api/health` | Health check |
  185. | `GET /api/vitals` | System metrics |
  186. | `GET /api/sessions` | Active sessions |
  187. | `GET /api/events` | SSE stream for real-time updates |
  188. ---
  189. ## Architecture
  190. ```
  191. command-center/
  192. โ”œโ”€โ”€ lib/
  193. โ”‚ โ”œโ”€โ”€ server.js # HTTP server + API
  194. โ”‚ โ”œโ”€โ”€ config.js # Configuration
  195. โ”‚ โ””โ”€โ”€ jobs.js # Cron integration
  196. โ”œโ”€โ”€ public/
  197. โ”‚ โ”œโ”€โ”€ index.html # Dashboard UI
  198. โ”‚ โ””โ”€โ”€ js/ # Components (ES modules)
  199. โ””โ”€โ”€ scripts/
  200. โ”œโ”€โ”€ setup.sh # First-time setup
  201. โ””โ”€โ”€ verify.sh # Health check
  202. ```
  203. ---
  204. ## ๐Ÿš€ Coming Soon
  205. ### Advanced Job Scheduling
  206. Building on OpenClaw's native cron system with intelligent scheduling primitives:
  207. | Primitive | Description |
  208. | -------------------- | ------------------------------------------- |
  209. | **run-if-not** | Skip if job already running (dedupe) |
  210. | **run-if-idle** | Only execute when system capacity available |
  211. | **run-after** | Dependency chains between jobs |
  212. | **run-with-backoff** | Exponential retry on failure |
  213. | **priority-queue** | Critical vs. background work prioritization |
  214. ### Multi-Agent Orchestration
  215. - Agent-to-agent handoffs
  216. - Swarm coordination patterns
  217. - Specialized agent routing (data analysis, documentation, testing)
  218. - Cross-session context sharing
  219. ### Integration Ecosystem
  220. - Webhook triggers for external systems
  221. - Slack slash commands for quick actions
  222. - API for custom integrations
  223. - Plugin architecture for specialized agents
  224. ---
  225. ## Screenshots
  226. ### Dashboard Overview
  227. The hero view shows key metrics at a glance: total tokens, costs, active sessions, estimated savings, and system capacity.
  228. <p align="center">
  229. <img src="docs/screenshots/hero.png" alt="Dashboard Hero" width="800">
  230. </p>
  231. ### Sessions Panel
  232. Monitor all active AI sessions in real-time. Each card shows model, channel, token usage, cost, and activity status. Filter by status (live/recent/idle), channel, or session type.
  233. <p align="center">
  234. <img src="docs/screenshots/sessions-panel.png" alt="Sessions Panel" width="800">
  235. </p>
  236. ### Cron Jobs
  237. View and manage scheduled tasks. See run history, next scheduled time, and enable/disable jobs. The dashboard shows job success/failure sparklines and filters by status and schedule type.
  238. <p align="center">
  239. <img src="docs/screenshots/cron-panel.png" alt="Cron Jobs Panel" width="800">
  240. </p>
  241. ### Cerebro Topics
  242. Automatic conversation organization. Topics are auto-detected from Slack threads, with status tracking (active/resolved/parked), thread counts, and quick navigation. Privacy controls let you hide sensitive topics.
  243. <p align="center">
  244. <img src="docs/screenshots/cerebro-panel.png" alt="Cerebro Topics Panel" width="800">
  245. </p>
  246. ### Operators
  247. See who's interacting with your AI agents. Track active sessions per operator, permission levels, and last activity timestamps.
  248. <p align="center">
  249. <img src="docs/screenshots/operators-panel.png" alt="Operators Panel" width="800">
  250. </p>
  251. ### Memory Browser
  252. Browse your agent's memory files โ€” daily logs, long-term memory, and workspace files. Quick navigation with file sizes and modification times.
  253. <p align="center">
  254. <img src="docs/screenshots/memory-panel.png" alt="Memory Panel" width="800">
  255. </p>
  256. ### Cost Breakdown Modal
  257. Click on any cost stat to see detailed breakdowns: token usage by type, pricing rates, and calculation methodology. Includes estimated savings vs. manual work.
  258. <p align="center">
  259. <img src="docs/screenshots/cost-modal.png" alt="Cost Breakdown Modal" width="800">
  260. </p>
  261. ### Operator Details
  262. Click on an operator card to see their session history, stats, and activity timeline.
  263. <p align="center">
  264. <img src="docs/screenshots/operator-modal.png" alt="Operator Details Modal" width="800">
  265. </p>
  266. ### Privacy Settings
  267. Control what's visible for demos and screenshots. Hide sensitive topics, sessions, or cron jobs. Settings sync to the server automatically.
  268. <p align="center">
  269. <img src="docs/screenshots/privacy-modal.png" alt="Privacy Settings Modal" width="800">
  270. </p>
  271. ### Session Details
  272. Click any session card to see detailed information: summary, key facts, tools used, and recent messages.
  273. <p align="center">
  274. <img src="docs/screenshots/session-detail.png" alt="Session Details Panel" width="800">
  275. </p>
  276. ### Full Dashboard
  277. The complete dashboard with all panels visible.
  278. <details>
  279. <summary>Click to expand full dashboard view</summary>
  280. <p align="center">
  281. <img src="docs/screenshots/dashboard-full.png" alt="Full Dashboard" width="800">
  282. </p>
  283. </details>
  284. ---
  285. ## Contributing
  286. Contributions welcome! Please read [CONTRIBUTING.md](CONTRIBUTING.md).
  287. ### Preserve localization
  288. UI changes must preserve existing `data-i18n` attributes and related translation hooks. Update every supported locale when adding or changing user-facing text, including loading and error states. Keep translated labels separate from dynamic values, and verify English โ†’ Chinese โ†’ English switching with the affected panel open and after live updates. See [AGENTS.md](AGENTS.md#-preserve-internationalization) for the full agent requirements.
  289. ### Development
  290. ```bash
  291. npm install # Install dev dependencies
  292. npm run dev # Watch mode
  293. npm run lint # Check code style
  294. npm run format # Auto-format
  295. ./scripts/verify.sh # Run health checks
  296. ```
  297. ---
  298. ## License
  299. MIT ยฉ [Jonathan Tsai](https://github.com/jontsai)
  300. ---
  301. <div align="center">
  302. **[Install from ClawHub](https://www.clawhub.ai/jontsai/command-center)** ยท **[OpenClaw](https://github.com/openclaw/openclaw)** ยท **[Discord](https://discord.gg/clawd)**
  303. </div>
  304. ## Project portfolio (read-only preview)
  305. The [Projects board](docs/architecture/project-portfolio.md) groups delivery outcomes
  306. by workflow stage across explicitly selected tracker sources. Spacesuit supplies
  307. Linear/Jira adapters; Command Center supplies the unified view without depending
  308. on a tracker. Native statuses, source freshness and missing metrics stay visible.
  309. This slice consumes snapshots, not a live tracker connection configured at install.
  310. No tasks are moved and no external tracker records are changed.
  311. ### Operations map (read-only snapshot)
  312. Explore outcomes, roles, agents, and topics with evidence-labeled relationships in `operations.html`. See [the work graph contract](docs/work-graph.md) for collectors, limitations, and privacy behavior.
  313. ### Browse sessions without tracker setup
  314. Operations opens on **All sessions** from the native catalog. Group by channel,
  315. agent or activity; layer in outcome/role/topic relationships when available.
  316. Clickable stacks, composable breadcrumbs, density zoom and an inspector replace
  317. search-first navigation. Privacy, snapshot coverage and unknown accounting stay
  318. explicit. See the [source-build pilot guide](docs/operations-source-pilot.md) to
  319. test a pinned revision under another profile without publishing a package.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If itโ€™s helped, pass it on.