OpenClaw Dashboard

A beautiful, zero-dependency command center for OpenClaw AI agents.

Why This Exists

When you run OpenClaw seriously — multiple agents, dozens of cron jobs, sub-agents spawning sub-agents, several Telegram groups and Whatsapp, Slack, and Discord channels, 10+ models, multiple agents and sub-agents — information gets scattered fast.

The problem: there was no single place to answer the obvious questions:

• Is my gateway actually running right now?
• How much have I spent today, and which model is burning the most?
• Which cron jobs ran, which failed, and when does the next one fire?
• What sessions are active and how much context are they consuming?
• Are my sub-agents doing useful work or spinning in circles?
• What's the cost trend over the last 7 days — am I accelerating?

The only way to answer these was digging through log files, running CLI commands, and mentally stitching together a picture from 5 different sources. That friction adds up.

The solution: a single local page that collects everything in one place — gateway health, costs, cron status, active sessions, sub-agent runs, model usage, git log — refreshed automatically, no login, no cloud, no external dependencies. Open a browser tab, get the full picture in seconds.

It's not trying to replace the OpenClaw CLI or Telegram interface. It's the at-a-glance overview layer that tells you whether everything is healthy and where your money and compute are going — so you can make decisions without hunting for data.

Features

12 Dashboard Panels

1. 📊 Top Metrics Bar — Live CPU, RAM, swap, disk + OpenClaw version + gateway — always on, colour-coded by configurable thresholds (see Top Metrics Bar)
2. 🔔 Header Bar — Bot name, online/offline status, auto-refresh countdown, theme picker
3. ⚠️ Alerts Banner — Smart alerts for high costs, failed crons, high context usage, gateway offline
4. 💚 System Health — Gateway status, PID, uptime, memory, compaction mode, active session count
5. 💰 Cost Cards — Today's cost, all-time cost, projected monthly, cost breakdown donut chart
6. ⏰ Cron Jobs — All scheduled jobs with status, schedule, last/next run, duration, model
7. 📡 Active Sessions — Recent sessions with model, type badges (DM/group/cron/subagent), context %, tokens
8. 📊 Token Usage & Cost — Per-model breakdown with 7d/30d/all-time tabs, usage bars, totals
9. 🤖 Sub-Agent Activity — Sub-agent runs with cost, duration, status + token breakdown (7d/30d tabs)
10. 📈 Charts & Trends — Cost trend line, model cost breakdown bars, sub-agent activity — all pure SVG, 7d/30d toggle
11. 🧩 Bottom Row — Available models grid, skills list, git log
12. 💬 AI Chat — Ask questions about your dashboard in natural language, powered by your OpenClaw gateway

Key Features

• 🔄 On-Demand Refresh — Refreshes data when you open the dashboard (no stale data)
• ⏱️ Auto-Refresh — Page auto-refreshes every 60 seconds with countdown timer
• 🎨 6 Built-in Themes — 3 dark (Midnight, Nord, Catppuccin Mocha) + 3 light (GitHub, Solarized, Catppuccin Latte), switchable from the UI
• 🖌️ Glass Morphism UI — Subtle transparency and hover effects
• 📱 Responsive — Adapts to desktop, tablet, and mobile
• 🔒 Local Only — Runs on localhost, no external dependencies
• 🛡️ Rate Limiting — 10 req/min per-IP on /api/chat (429 + Retry-After)
• ⏱️ HTTP Timeouts — Read 30s / Write 90s / Idle 120s
• 🐧 Cross-Platform — macOS and Linux
• ⚡ Zero Dependencies — Pure HTML/CSS/JS frontend, single Go binary backend
• 📊 Top Metrics Bar — Always-on CPU/RAM/swap/disk + gateway status, per-metric thresholds, macOS + Linux
• 💬 AI Chat — Natural language queries about costs, sessions, crons, and config via OpenClaw gateway
• 🎯 Accurate Model Display — 5-level resolution chain ensures every session/sub-agent shows its real model, not the default
• 🔍 Runtime Observability — /api/system includes live gateway runtime state (liveness, readiness, failing deps, uptime, PID, memory) sourced from /healthz, /readyz, and openclaw status --json
• 🟡 Gateway Readiness Alerts — Alert banner shows 🟡 Gateway not ready: discord (or any failing dep) and auto-clears on recovery
• ⚡ Gateway Runtime + Config Cards — System Settings split into two panels: Gateway Runtime (live probes) and Gateway Config (static config snapshot)

Quick Start

Homebrew (macOS / Linux)

brew install mudrii/tap/openclaw-dashboard

The Homebrew formula installs the binary and seeds a writable runtime directory at
~/.openclaw/dashboard on first run.

Then run:

openclaw-dashboard --refresh   # generate data.json
openclaw-dashboard             # start server on http://localhost:8080

Pre-built Binary

Download a release tarball — includes the binary plus runtime assets.

# macOS (Apple Silicon)
curl -L https://github.com/mudrii/openclaw-dashboard/releases/latest/download/openclaw-dashboard-darwin-arm64.tar.gz | tar xz
./openclaw-dashboard --port 8080

# macOS (Intel)
curl -L https://github.com/mudrii/openclaw-dashboard/releases/latest/download/openclaw-dashboard-darwin-amd64.tar.gz | tar xz
./openclaw-dashboard --port 8080

# Linux (x86_64)
curl -L https://github.com/mudrii/openclaw-dashboard/releases/latest/download/openclaw-dashboard-linux-amd64.tar.gz | tar xz
./openclaw-dashboard --port 8080

# Linux (ARM64 / Raspberry Pi)
curl -L https://github.com/mudrii/openclaw-dashboard/releases/latest/download/openclaw-dashboard-linux-arm64.tar.gz | tar xz
./openclaw-dashboard --port 8080

Verify download integrity:

curl -L https://github.com/mudrii/openclaw-dashboard/releases/latest/download/checksums-sha256.txt -o checksums-sha256.txt
shasum -a 256 -c checksums-sha256.txt

One-Line Install

curl -fsSL https://raw.githubusercontent.com/mudrii/openclaw-dashboard/main/install.sh | bash

This will:

1. Install to ~/.openclaw/dashboard
2. Download the pre-built Go binary for your platform
3. Create a default config
4. Run initial data refresh
5. Start the server as a system service
6. Open http://127.0.0.1:8080

Upgrading via Homebrew

brew upgrade mudrii/tap/openclaw-dashboard

Running as a Background Service (macOS)

After installing via Homebrew, you can run the dashboard as a launchd service:

# Start on login
brew services start mudrii/tap/openclaw-dashboard

# Or manually create a launchd plist pointing to /opt/homebrew/bin/openclaw-dashboard

Build from Source

git clone https://github.com/mudrii/openclaw-dashboard.git
cd openclaw-dashboard
go build -ldflags="-s -w" -o openclaw-dashboard ./cmd/openclaw-dashboard
./openclaw-dashboard --port 8080

Docker

docker build -t openclaw-dashboard .
docker run -p 8080:8080 -v ~/.openclaw:/home/dashboard/.openclaw openclaw-dashboard

Nix Flake

# Run directly
nix run github:mudrii/openclaw-dashboard

# Dev shell (Go + tools)
nix develop github:mudrii/openclaw-dashboard

Themes

Click the 🎨 button in the header to switch themes instantly — no reload or server restart needed. Choice persists via localStorage.

Custom Themes

Add your own themes by editing themes.json in your runtime directory. Default themes
ship from assets/runtime/themes.json. Each theme defines 19 CSS color variables:

{
  "my-theme": {
    "name": "My Theme",
    "type": "dark",
    "icon": "🎯",
    "colors": {
      "bg": "#1a1a2e",
      "surface": "rgba(255,255,255,0.03)",
      "surfaceHover": "rgba(255,255,255,0.045)",
      "border": "rgba(255,255,255,0.06)",
      "accent": "#e94560",
      "accent2": "#0f3460",
      "green": "#4ade80",
      "yellow": "#facc15",
      "red": "#f87171",
      "orange": "#fb923c",
      "purple": "#a78bfa",
      "text": "#e5e5e5",
      "textStrong": "#ffffff",
      "muted": "#737373",
      "dim": "#525252",
      "darker": "#404040",
      "tableBg": "rgba(255,255,255,0.025)",
      "tableHover": "rgba(255,255,255,0.05)",
      "scrollThumb": "rgba(255,255,255,0.1)"
    }
  }
}

Architecture

cmd/openclaw-dashboard/      CLI entrypoint
internal/appconfig/          config loading
internal/appruntime/         runtime-dir resolution
internal/appchat/            chat prompt + gateway client
internal/apprefresh/         data collector
internal/appserver/          HTTP server
internal/appsystem/          metrics and runtime probes
web/index.html              embedded frontend
assets/runtime/             runtime defaults
data.json                   generated dashboard data

Endpoints:

When you open the dashboard, the embedded frontend calls /api/refresh. The server runs --refresh (with 30s debounce) to collect fresh data from your OpenClaw installation, then returns the JSON. No cron jobs needed.

The /api/chat endpoint accepts {"question": "...", "history": [...]} and forwards a stateless request to the OpenClaw gateway's OpenAI-compatible /v1/chat/completions endpoint, with a system prompt built from live data.json.

Frontend Module Structure

The entire frontend lives in a single <script> tag inside web/index.html — zero dependencies, no build step. The JS is organized into 7 plain objects:

┌─────────────────────────────────────────────┐
│                 App.init()                   │
│       (wires everything, starts timer)       │
└───────┬──────────────┬──────────────┬───────┘
        │              │              │
   ┌────▼────┐   ┌─────▼─────┐  ┌────▼─────┐
   │  State  │◄──│ DataLayer │  │  Theme   │
   │ (truth) │   │  (fetch)  │  │ (colors) │
   └────┬────┘   └───────────┘  └──────────┘
        │
   ┌────▼────────────┐
   │  DirtyChecker   │
   │ (what changed?) │
   └────┬────────────┘
        │
   ┌────▼────┐   ┌────────┐
   │Renderer │   │  Chat  │
   │  (DOM)  │   │  (AI)  │
   └─────────┘   └────────┘

All inline onclick handlers route through window.OCUI — a thin namespace that calls State.setTab() / App.renderNow(). No bare globals remain outside the module objects and top-level utilities ($, esc, safeColor, relTime).

See ARCHITECTURE.md for the full specification.

Configuration

Edit config.json in your dashboard runtime directory. In a source checkout or
install.sh install this is the project/install folder; with Homebrew it is
~/.openclaw/dashboard/config.json.

{
  "bot": {
    "name": "My Bot",
    "emoji": "🤖"
  },
  "theme": {
    "preset": "nord"
  },
  "refresh": {
    "intervalSeconds": 30
  },
  "server": {
    "port": 8080,
    "host": "127.0.0.1"
  },
  "ai": {
    "enabled": true,
    "gatewayPort": 18789,
    "model": "your-model-id",
    "maxHistory": 6,
    "dotenvPath": "~/.openclaw/.env"
  },
  "system": {
    "enabled": true,
    "pollSeconds": 10,
    "diskPath": "/",
    "cpu":  { "warn": 80, "critical": 95 },
    "ram":  { "warn": 75, "critical": 90 },
    "swap": { "warn": 80, "critical": 95 },
    "disk": { "warn": 85, "critical": 95 }
  }
}

Configuration Options

Top Metrics Bar

The top bar shows live host metrics — always visible above the alerts banner.

Metrics displayed:

Colour coding:

• 🟢 Green — below warn threshold
• 🟡 Yellow — above warn, below critical
• 🔴 Red — above critical threshold
• ⚫ Grey — collection error / N/A

Per-metric config example (config.json):

"system": {
  "enabled": true,
  "pollSeconds": 10,
  "diskPath": "/",
  "cpu":  { "warn": 80, "critical": 95 },
  "ram":  { "warn": 75, "critical": 90 },
  "swap": { "warn": 60, "critical": 80 },
  "disk": { "warn": 85, "critical": 95 }
}

Platform support:

• macOS — CPU via top -l 2 (current delta), RAM via vm_stat, Swap via sysctl vm.swapusage, Disk via statfs
• Linux — CPU via /proc/stat (200ms dual-sample including steal field), RAM+Swap via /proc/meminfo (single read, shared), Disk via statfs

API endpoint: GET /api/system — returns JSON with all metrics, thresholds, version info, and the openclaw runtime block. Includes stale-serving semantics (returns cached data immediately while refreshing in background).

openclaw block in /api/system — provides live gateway runtime state beyond what the refresh collector gathers:

AI Chat Setup

The chat panel requires:

1. Your OpenClaw gateway running with the chatCompletions endpoint enabled:

   "gateway": {
     "http": { "endpoints": { "chatCompletions": { "enabled": true } } }
   }

2. OPENCLAW_GATEWAY_TOKEN set in your .env file (defaults to ~/.openclaw/.env)

The chat is stateless — each question is sent directly to the gateway with a system prompt built from live data.json. No agent memory or tools bleed in.

See docs/CONFIGURATION.md for full details.

Screenshots

Full dashboard view — all sections at a glance:

🔔 Overview & System Health

Real-time bot status, gateway uptime, memory usage, active session count, today's cost, all-time spend, projected monthly cost, and a per-model cost breakdown donut chart. Smart alert banners surface high costs, failed crons, and context overflows automatically.

📈 Charts & Trends

Three always-visible SVG charts with 7d/30d toggle: cost trend over time, per-model cost breakdown bars, and sub-agent activity volume. No external chart libraries — pure inline SVG.

⏰ Cron Jobs

All scheduled jobs with status badges (active/idle/error), schedule expression, last run time, next run, duration, and the model used. At-a-glance view of your automation health.

📡 Active Sessions + Agent Hierarchy Tree

Live sessions with model, type badges (DM / group / subagent), context usage %, and token count. Above the session list: a visual agent hierarchy tree showing parent → sub-agent → sub-sub-agent relationships with live/idle status and trigger labels — updated every refresh.

📊 Token Usage & Cost

Per-model token and cost breakdown with 7d / 30d / all-time tabs. Includes input tokens, output tokens, cache reads, and total cost per model — sortable at a glance.

🤖 Sub-Agent Activity

All sub-agent runs with cost, duration, status, and token breakdown. Separate 7d/30d tabs. Useful for tracking which tasks spawn the most agents and where spend is concentrated.

🧩 Available Models, Skills & Git Log

Quick reference panel showing all configured models, active skills, and the last 5 git commits from your OpenClaw workspace — so you always know what's deployed.

⚙️ Agent & Model Configuration

Full agent setup at a glance: model routing chain (primary → fallbacks), sub-agent routing by purpose (General / Dev+Coding / Work), agent details table with per-agent fallbacks, agent bindings with resolved group names, runtime config (compaction, memory flush), and subagent limits (max depth, max children/agent).

Uninstall

./uninstall.sh

Or manually:

# macOS
launchctl unload ~/Library/LaunchAgents/com.openclaw.dashboard.plist
rm -rf ~/.openclaw/dashboard

# Linux
systemctl --user stop openclaw-dashboard
rm -rf ~/.openclaw/dashboard

Requirements

• Pre-built Go binary — no runtime dependencies
• bash (only needed if using the optional refresh.sh wrapper script, not required for the binary itself)
• OpenClaw — Installed at ~/.openclaw (docs)
• macOS 10.15+ or Linux (Ubuntu 18.04+, Debian 10+, ARM64)
• Modern web browser

Contributing

See CONTRIBUTING.md for guidelines.

License

MIT License — see LICENSE

Made with 🦞 for the OpenClaw community