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.
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
Markdown
[](/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
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** ๐
<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)
- ---
- name: command-center
- version: 1.5.0
- 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.
- metadata:
- openclaw:
- requires:
- node: ">=18"
- install:
- - id: start
- kind: shell
- command: "node lib/server.js"
- label: "Start Command Center (http://localhost:3333)"
- ---
- # OpenClaw Command Center
- Mission control for your AI workforce.
- ## Quick Start
- ```bash
- npx clawhub@latest install command-center
- cd skills/command-center
- node lib/server.js
- ```
- Dashboard runs at **http://localhost:3333**
- ## Features
- - **Session Monitoring** โ Real-time view of all AI sessions with live updates
- - **LLM Fuel Gauges** โ Track Claude, Codex, and other model usage
- - **System Vitals** โ CPU, Memory, Disk, Temperature
- - **Cron Jobs** โ View and manage scheduled tasks
- - **Cerebro Topics** โ Automatic conversation organization
- - **Cost Tracking** โ Per-session costs, projections, savings estimates
- - **Privacy Controls** โ Hide sensitive topics for demos
- ## Configuration
- The dashboard auto-detects your OpenClaw workspace. Set `OPENCLAW_WORKSPACE` to override.
- ### Authentication
- | Mode | Use Case |
- | ------------ | ----------------- |
- | `none` | Local development |
- | `token` | Remote access |
- | `tailscale` | Team VPN |
- | `cloudflare` | Public deployment |
- ```bash
- DASHBOARD_AUTH_MODE=tailscale node lib/server.js
- ```
- ## API
- | Endpoint | Description |
- | ----------------- | ---------------------------- |
- | `GET /api/state` | All dashboard data (unified) |
- | `GET /api/events` | SSE stream for live updates |
- | `GET /api/health` | Health check |
- ## Links
- - [GitHub](https://github.com/jontsai/openclaw-command-center)
- - [ClawHub](https://www.clawhub.ai/jontsai/command-center)
- - [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)
- # ๐ฆ OpenClaw Command Center
- English | [็ฎไฝไธญๆ](README.zh-CN.md)
- <div align="center">
- **Mission control for your AI agents**
- [](https://github.com/jontsai/openclaw-command-center/actions/workflows/ci.yml)
- [](https://opensource.org/licenses/MIT)
- [](https://nodejs.org)
- [](https://www.clawhub.ai/jontsai/command-center)
- [](https://github.com/jontsai/openclaw-command-center/pulls)
- [Features](#features) โข [Quick Start](#quick-start) โข [Security](#-security) โข [Configuration](#configuration)
- </div>
- ---
- ## Standalone monitoring, recommended companion
- ### Human-readable costs and channels
- Click **Est. API Cost** to enter a monthly spend baseline for the savings scenario.
- The baseline is stored only in this browser and dashboard path; no plan price is
- assumed. The selected calendar-day average is projected to 30 days and compared
- with your baseline. Include subscription and API spending for the same scope.
- Incomplete pricing stays marked partial, and negative differences are displayed.
- This is a what-if comparison, not realized savings or a billing forecast.
- Channel names come from OpenClaw's native directory, cached per provider/account
- for five minutes. Channel IDs remain in session-title and cost-breakdown tooltips.
- Unknown channels have an explicit generic label; stale cached names retain their
- status in the tooltip. No workspace-specific channel map or provider credentials
- are embedded in the dashboard. Directory reads are bounded and asynchronous.
- Cron Jobs lists OpenClaw automations through its read-only CLI API, cached for
- 30 seconds. Loading, partial and stale catalogs are labeled; missing legacy JSON
- files no longer imply zero automations. AI Jobs is a separate optional provider:
- without it the page shows "not connected", not an empty successful job catalog.
- **Command Center works out of the box without Spacesuit.** It owns OpenClaw
- sessions, health, jobs, usage and the common dashboard. For a minimal core-only
- view, run `COMMAND_CENTER_MODE=core npm start`.
- **Spacesuit is the highly recommended companion** for per-agent flavors, domain
- panels and workflows. Spacesuit can scaffold a workspace and collect data by itself,
- but it has **no graphical humanโagent interaction surface of its own**; Command
- Center provides the dashboard and supported controls. The extension system does
- not add a chat composer.
- The [read-only extension API](docs/architecture/extension-api-v1.md) loads explicit,
- profile-bound Spacesuit snapshots through the existing state feed. Legacy built-in
- domain panels remain the default compatibility mode until you select a flavor or
- core-only mode; existing panels and data are not silently removed. See the
- [ownership and migration plan](docs/architecture/core-and-flavors.md).
- ## Why Command Center?
- Your AI agents are running 24/7. You need to know what they're doing.
- Command Center gives you **real-time visibility** into your OpenClaw deployment โ sessions, costs, system health, scheduled tasks โ all in one secure dashboard.
- ### โก Fast
- - **Single API call** โ unified state endpoint, not 16+ separate requests
- - **2-second updates** โ real-time SSE push, not polling
- - **5-second cache** โ backend stays responsive under load
- - **Instant startup** โ no build step, no compilation
- ### ๐ชถ Lightweight
- - **Zero dependencies** for users โ just Node.js
- - **~200KB total** โ dashboard + server
- - **No webpack/vite/bundler** โ runs directly
- - **No React/Vue/Angular** โ vanilla JS, works everywhere
- ### ๐ฑ Responsive
- - **Desktop & mobile** โ works on any screen size
- - **Dark mode** โ easy on the eyes, Starcraft-inspired
- - **Live updates** โ no manual refresh needed
- - **Offline-friendly** โ graceful degradation
- ### ๐ง Modern
- - **ES Modules** โ clean component architecture
- - **SSE streaming** โ efficient real-time updates
- - **REST API** โ integrate with your tools
- - **TypeScript-ready** โ JSDoc types included
- ### ๐ Security (Most Important)
- Command Center takes security seriously:
- | Feature | Description |
- | ------------------------ | --------------------------------------------------- |
- | **Auth Modes** | Token, Tailscale, Cloudflare Access, IP allowlist |
- | **No external calls** | Dashboard runs 100% locally โ no telemetry, no CDNs |
- | **Localhost default** | Binds to `127.0.0.1` by default |
- | **Read-only by default** | View your agents without exposing control |
- | **No secrets in UI** | API keys, tokens never displayed |
- | **Audit logging** | Know who accessed what, when |
- ```bash
- # Secure deployment example (Tailscale)
- DASHBOARD_AUTH_MODE=tailscale node lib/server.js
- # Only users on your Tailscale network can access
- ```
- ---
- ## Features
- | Feature | Description |
- | -------------------------- | ------------------------------------------- |
- | ๐ **Session Monitoring** | Real-time view of active AI sessions |
- | โฝ **LLM Fuel Gauges** | Token usage, costs, quota remaining |
- | ๐ป **System Vitals** | CPU, memory, disk, temperature |
- | โฐ **Cron Jobs** | View and manage scheduled tasks |
- | ๐ง **Cerebro Topics** | Automatic conversation tagging |
- | ๐ฅ **Operators** | Who's talking to your agents |
- | ๐ **Memory Browser** | View agent memory files |
- | ๐ **Privacy Controls** | Hide sensitive topics for demos/screenshots |
- | ๐ฐ **Cost Breakdown** | Detailed per-model cost analysis |
- | ๐ **Savings Projections** | Monthly cost vs. manual estimates |
- ---
- ## Quick Start
- ```bash
- npx clawhub@latest install command-center
- cd skills/command-center
- node lib/server.js
- ```
- **Dashboard runs at http://localhost:3333** ๐
- <details>
- <summary>Alternative: Git clone</summary>
- ```bash
- git clone https://github.com/jontsai/openclaw-command-center
- cd openclaw-command-center
- node lib/server.js
- ```
- </details>
- ---
- ## Zero-Config Experience
- Command Center **auto-detects** your OpenClaw workspace:
- 1. `$OPENCLAW_WORKSPACE` environment variable
- 2. `~/.openclaw-workspace` or `~/openclaw-workspace`
- 3. Common names: `~/molty`, `~/clawd`, `~/moltbot`
- If you have `memory/` or `state/` directories, you're good to go.
- ---
- ## Optional System Dependencies
- 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.
- | OS | Package | Purpose | Install | Without It |
- | --------------------- | ------------------- | ---------------------------------- | ------------------------------------------------------------- | --------------------------------- |
- | Linux | `sysstat` | Disk I/O vitals (IOPS, throughput) | `sudo apt install sysstat` | Disk stats show zeros |
- | Linux | `lm-sensors` | Additional temperature sensors | `sudo apt install lm-sensors` | Uses thermal_zone (usually works) |
- | macOS (Intel) | `osx-cpu-temp` | CPU temperature | [Build from source](https://github.com/lavoiesl/osx-cpu-temp) | Battery temp fallback |
- | macOS (Apple Silicon) | passwordless `sudo` | CPU temperature via `powermetrics` | Configure in sudoers | Shows note in UI |
- Command Center logs hints for missing optional dependencies once at startup.
- ---
- ## Configuration
- ### Environment Variables
- | Variable | Description | Default |
- | -------------------- | -------------- | ----------- |
- | `PORT` | Server port | `3333` |
- | `OPENCLAW_WORKSPACE` | Workspace root | Auto-detect |
- | `OPENCLAW_PROFILE` | Profile name | (none) |
- ### ๐ Authentication
- | Mode | Use Case | Config |
- | ------------ | ------------- | --------------------------------------------------------- |
- | `none` | Local dev | `DASHBOARD_AUTH_MODE=none` |
- | `token` | API access | `DASHBOARD_AUTH_MODE=token DASHBOARD_TOKEN=secret` |
- | `tailscale` | Team access | `DASHBOARD_AUTH_MODE=tailscale` |
- | `cloudflare` | Public deploy | `DASHBOARD_AUTH_MODE=cloudflare` |
- | `allowlist` | IP whitelist | `DASHBOARD_AUTH_MODE=allowlist DASHBOARD_ALLOWED_IPS=...` |
- ### ๐ Recommended OpenClaw Settings
- For the best Command Center experience, configure your OpenClaw gateway:
- #### Slack Threading (Critical)
- Enable threading for all messages to get proper topic tracking:
- ```yaml
- # In your OpenClaw config (gateway.yaml or via openclaw gateway config)
- slack:
- capabilities:
- threading: all # Options: all, dm, group, none
- ```
- **Why this matters:** Without threading, the dashboard can't track conversation topics properly. Each thread becomes a trackable unit of work.
- #### Session Labels
- Use descriptive session labels for better dashboard visibility:
- ```yaml
- sessions:
- labelFormat: "{channel}:{topic}" # Customize as needed
- ```
- #### Cerebro (Topic Tracking)
- Enable Cerebro for automatic conversation tagging:
- ```bash
- # Initialize Cerebro directories
- mkdir -p ~/your-workspace/cerebro/topics
- mkdir -p ~/your-workspace/cerebro/orphans
- ```
- The dashboard will automatically detect and display topic data.
- ---
- ### Multi-Profile Support
- Running multiple OpenClaw instances?
- ```bash
- # Production dashboard
- node lib/server.js --profile production --port 3333
- # Development dashboard
- node lib/server.js --profile dev --port 3334
- ```
- ---
- ## API
- Command Center exposes a REST API:
- | Endpoint | Description |
- | ------------------- | -------------------------------------------------- |
- | `GET /api/state` | **Unified state** โ all dashboard data in one call |
- | `GET /api/health` | Health check |
- | `GET /api/vitals` | System metrics |
- | `GET /api/sessions` | Active sessions |
- | `GET /api/events` | SSE stream for real-time updates |
- ---
- ## Architecture
- ```
- command-center/
- โโโ lib/
- โ โโโ server.js # HTTP server + API
- โ โโโ config.js # Configuration
- โ โโโ jobs.js # Cron integration
- โโโ public/
- โ โโโ index.html # Dashboard UI
- โ โโโ js/ # Components (ES modules)
- โโโ scripts/
- โโโ setup.sh # First-time setup
- โโโ verify.sh # Health check
- ```
- ---
- ## ๐ Coming Soon
- ### Advanced Job Scheduling
- Building on OpenClaw's native cron system with intelligent scheduling primitives:
- | Primitive | Description |
- | -------------------- | ------------------------------------------- |
- | **run-if-not** | Skip if job already running (dedupe) |
- | **run-if-idle** | Only execute when system capacity available |
- | **run-after** | Dependency chains between jobs |
- | **run-with-backoff** | Exponential retry on failure |
- | **priority-queue** | Critical vs. background work prioritization |
- ### Multi-Agent Orchestration
- - Agent-to-agent handoffs
- - Swarm coordination patterns
- - Specialized agent routing (data analysis, documentation, testing)
- - Cross-session context sharing
- ### Integration Ecosystem
- - Webhook triggers for external systems
- - Slack slash commands for quick actions
- - API for custom integrations
- - Plugin architecture for specialized agents
- ---
- ## Screenshots
- ### Dashboard Overview
- The hero view shows key metrics at a glance: total tokens, costs, active sessions, estimated savings, and system capacity.
- <p align="center">
- <img src="docs/screenshots/hero.png" alt="Dashboard Hero" width="800">
- </p>
- ### Sessions Panel
- 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.
- <p align="center">
- <img src="docs/screenshots/sessions-panel.png" alt="Sessions Panel" width="800">
- </p>
- ### Cron Jobs
- 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.
- <p align="center">
- <img src="docs/screenshots/cron-panel.png" alt="Cron Jobs Panel" width="800">
- </p>
- ### Cerebro Topics
- 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.
- <p align="center">
- <img src="docs/screenshots/cerebro-panel.png" alt="Cerebro Topics Panel" width="800">
- </p>
- ### Operators
- See who's interacting with your AI agents. Track active sessions per operator, permission levels, and last activity timestamps.
- <p align="center">
- <img src="docs/screenshots/operators-panel.png" alt="Operators Panel" width="800">
- </p>
- ### Memory Browser
- Browse your agent's memory files โ daily logs, long-term memory, and workspace files. Quick navigation with file sizes and modification times.
- <p align="center">
- <img src="docs/screenshots/memory-panel.png" alt="Memory Panel" width="800">
- </p>
- ### Cost Breakdown Modal
- Click on any cost stat to see detailed breakdowns: token usage by type, pricing rates, and calculation methodology. Includes estimated savings vs. manual work.
- <p align="center">
- <img src="docs/screenshots/cost-modal.png" alt="Cost Breakdown Modal" width="800">
- </p>
- ### Operator Details
- Click on an operator card to see their session history, stats, and activity timeline.
- <p align="center">
- <img src="docs/screenshots/operator-modal.png" alt="Operator Details Modal" width="800">
- </p>
- ### Privacy Settings
- Control what's visible for demos and screenshots. Hide sensitive topics, sessions, or cron jobs. Settings sync to the server automatically.
- <p align="center">
- <img src="docs/screenshots/privacy-modal.png" alt="Privacy Settings Modal" width="800">
- </p>
- ### Session Details
- Click any session card to see detailed information: summary, key facts, tools used, and recent messages.
- <p align="center">
- <img src="docs/screenshots/session-detail.png" alt="Session Details Panel" width="800">
- </p>
- ### Full Dashboard
- The complete dashboard with all panels visible.
- <details>
- <summary>Click to expand full dashboard view</summary>
- <p align="center">
- <img src="docs/screenshots/dashboard-full.png" alt="Full Dashboard" width="800">
- </p>
- </details>
- ---
- ## Contributing
- Contributions welcome! Please read [CONTRIBUTING.md](CONTRIBUTING.md).
- ### Preserve localization
- 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.
- ### Development
- ```bash
- npm install # Install dev dependencies
- npm run dev # Watch mode
- npm run lint # Check code style
- npm run format # Auto-format
- ./scripts/verify.sh # Run health checks
- ```
- ---
- ## License
- MIT ยฉ [Jonathan Tsai](https://github.com/jontsai)
- ---
- <div align="center">
- **[Install from ClawHub](https://www.clawhub.ai/jontsai/command-center)** ยท **[OpenClaw](https://github.com/openclaw/openclaw)** ยท **[Discord](https://discord.gg/clawd)**
- </div>
- ## Project portfolio (read-only preview)
- The [Projects board](docs/architecture/project-portfolio.md) groups delivery outcomes
- by workflow stage across explicitly selected tracker sources. Spacesuit supplies
- Linear/Jira adapters; Command Center supplies the unified view without depending
- on a tracker. Native statuses, source freshness and missing metrics stay visible.
- This slice consumes snapshots, not a live tracker connection configured at install.
- No tasks are moved and no external tracker records are changed.
- ### Operations map (read-only snapshot)
- 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.
- ### Browse sessions without tracker setup
- Operations opens on **All sessions** from the native catalog. Group by channel,
- agent or activity; layer in outcome/role/topic relationships when available.
- Clickable stacks, composable breadcrumbs, density zoom and an inspector replace
- search-first navigation. Privacy, snapshot coverage and unknown accounting stay
- explicit. See the [source-build pilot guide](docs/operations-source-pilot.md) to
- test a pinned revision under another profile without publishing a package.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If itโs helped, pass it on.