OpenClaw Monitor
A free, self-hosted dashboard that watches your OpenClaw agents' token usage, sessions and 7-day trends.
- Source repo
- flik2002/openclaw-monitor
- Stars
- ★ 13
- Last updated
- 6mo ago
- License
- MIT
- Primary language
- JavaScript
- FA score
- 36/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specific
- Cost
- Free, no paid service needed
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- Developers already running an OpenClaw Gateway who want to see which model burned the most prompt/completion tokens over the last seven days.
- Not a fit if
- Teams without an OpenClaw Gateway running
- Users monitoring AI runtimes other than OpenClaw
- Anyone wanting a single-command, no-backend deployment
- Maintenance
- No commits for 6+ monthslast commit 2026-05-14latest release v1.0.0 (2026-05-14)
- Source review
- 36/100 · Major gaps 2 safety controls not found
What does this agent do, and when should you use it?
OpenClaw Monitor is an MIT-licensed, self-hosted monitoring dashboard for OpenClaw AI agents. It has three parts: a Vue 3 + Vite + Element Plus + ECharts frontend, a Node.js + Express backend monitor API with a WebSocket client, and helper scripts under openclaw-monitor/. All data comes from local session JSON files and history .reset files, with no cloud component, so the whole pipeline runs offline. At runtime the backend opens a WebSocket connection to an OpenClaw Gateway on port 18789, reads local session data, and exposes REST endpoints that the dashboard on localhost:5173/monitor-v2 consumes. The rendered output covers per-model prompt/completion token bar charts, a live session list, daily message trends for the past seven days, and system uptime and memory metrics.
The backend monitor API connects over WebSocket to the OpenClaw Gateway on port 18789, reads local session JSON files plus history .reset files, and serves the results as REST endpoints: GET /health, GET /api/gateway/status, GET /api/sessions/list, GET /api/metrics/system, GET /api/messages/stats and GET /api/models/current. The frontend polls those endpoints and renders a seven-day prompt/completion token bar chart split by model, a daily message count trend, and a live session list showing model, runtime and status. It also displays a cron task scheduling view alongside system uptime and memory usage. Model support is documented for Claude Code, OpenAI Codex, DeepSeek V4 and more; input is local session data, output is a browser dashboard.
- Developers already running an OpenClaw Gateway who want to see which model burned the most prompt/completion tokens over the last seven days.
- Teams juggling Claude Code, OpenAI Codex and DeepSeek V4 who want one panel comparing usage and message distribution across models.
- On-call or ops staff who need a live view of active sessions: which model each one uses, how long it has run, and whether it is healthy.
- Users who want to confirm that their scheduled agent tasks are laid out as expected via the cron task scheduling view.
- Privacy-sensitive users who want usage metrics to stay on the machine, since the dashboard reads local session JSON rather than a cloud service.
- Anyone debugging resource pressure who needs uptime and memory metrics side by side with session and message trends.
Key setup facts
Pulled from the install and usage notes below. The project README has the current values.
- Ports
18789·3000·5173- Runtime
- Node.js 18+
- Install notes cover
- Windows · macOS · Linux
How do you install or deploy this agent?
Prerequisites: Node.js 18+ and an OpenClaw Gateway already listening on port 18789. On Windows, start everything from the repo root with the one-click script:
start-all.batTo run the two services manually, install and start the backend monitor API on port 3000 first:
cd backend && npm install && npm startThen, in a second terminal, install and start the frontend on port 5173:
cd frontend && npm install && npm run devUse stop-all.bat from the root to shut both down. The README does not document one-click scripts for Linux/macOS, nor any environment-variable or config-file reference.
How do you use this agent?
With both services up, open the dashboard in a browser:
http://localhost:5173/monitor-v2The backend API listens on port 3000; call it directly to sanity-check the data:
curl http://localhost:3000/health
curl http://localhost:3000/api/gateway/status
curl http://localhost:3000/api/sessions/list
curl http://localhost:3000/api/metrics/system
curl http://localhost:3000/api/messages/stats
curl http://localhost:3000/api/models/currentIf either port is taken you must change it yourself and keep the WebSocket connection from the backend to the Gateway on 18789 reachable.
What are this agent's strengths and limitations?
- Fully local data path: session JSON files and history .reset files only, so usage metrics never leave the machine.
- The seven-day prompt/completion token bar chart is broken down per model, which directly answers which model is burning budget.
- Documented multi-model display for Claude Code, OpenAI Codex and DeepSeek V4 in a single dashboard.
- Windows one-click start-all.bat/stop-all.bat plus a two-step manual path (npm install, npm start) for each service.
- Clean REST surface (/api/sessions/list, /api/metrics/system, /api/messages/stats and more) that is easy to scrape for your own alerts or reports.
- Hard dependency on an OpenClaw Gateway listening on port 18789; without it the dashboard has no live data source.
- Scope is limited to the OpenClaw ecosystem — no collection adapter for other AI runtimes is documented.
- You must run two processes (backend on 3000, frontend on 5173), and any port conflict has to be resolved by hand.
- The one-click start script is Windows-only; Linux/macOS users have to assemble the manual steps themselves.
- No Docker image, config file format or environment variables are documented, so containerised or centralised deployment needs extra work.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| OpenClaw Monitor This agent | 36 · Major gaps | Self-hosted serviceFree | ★ 13 | 6mo ago | JavaScript | — |
| AgentAcct | 75 · Good | CLIFree | ★ 757 | 1mo ago | Python | Codex · Claude Code |
| OpenClaw Command Center | 62 · Some gaps | Agent plugin / skillFree | ★ 250 | 1mo ago | JavaScript | — |
| ClawMetry | 71 · Some gaps | CLIFreemium | ★ 439 | 1d ago | Python | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The README says data comes from local session JSON files and can run offline, and it identifies a Gateway connection. The packet does not explain collected fields, network flows, or sensitive-data protections, so evidence for data transparency and privacy handling is thin. The server enables broad CORS by default, and the shown code has no mechanism for writing, modifying, or rolling back monitored data; privilege, external-effects, and recovery scores are therefore limited. CI uses npm ci --ignore-scripts, but no lockfile or dependency audit evidence is shown. The MIT license and repository name provide limited attribution clues, not verified maintainer identity.
The README says the manual backend starts on port 3000, while backend/src/index.js defaults to 3001. The README's session, metrics, and message endpoints also do not appear in the provided server entry point, which mounts auth, gateway, announcement, and ad routes. These are direct consistency gaps. CI includes install and build steps, but ignores install scripts and the packet provides no lockfile evidence, so dependency availability is only partly supported. The entry point logs startup failures and returns a generic 500 response, but error handling is basic.
The described features target OpenClaw operators and cover sessions, models, tokens, trends, and system metrics, giving ordinary scenarios a clear outline. Boundaries are only partly stated through claims about local JSON, offline operation, and a single Gateway port; supported scale, data limits, and malformed-data behavior are not described. Startup prerequisites name Node.js 18+ and a running Gateway, but configuration, network exposure, and environment adaptation remain unclear.
The README is organized into features, stack, structure, installation, API, and architecture. Windows one-click and manual startup steps help onboarding, but the port conflicts with the shown entry point and configuration details are absent. Naming is mostly stable, though the README's feature and API claims differ from the provided server entry point. A screenshot is referenced, but no FAQ, changelog, or clear limitations are shown. The MIT license text is complete and identifies a copyright year and holder. The release workflow generates timestamped versions, but no maintainer or ongoing maintenance commitment is identified.
The dashboard's stated outputs—sessions, token trends, message statistics, and system metrics—fit monitoring use and appear potentially useful; the README lists endpoints and visualizations. The packet's server entry point does not show those monitoring endpoints, so the claimed marginal value has only partial support. Node/npm, local services, and a running Gateway are identified as operating costs, but resource and maintenance costs are not discussed.
Some README claims about stack, data source, features, and endpoints have architectural diagrams and code-entry clues, but the provided implementation does not substantiate the monitoring features, and port and route descriptions conflict. Traceability and cross-source corroboration are therefore limited. The README presents features and architecture as statements without distinguishing implemented behavior from plans or overview claims, leaving fact and inference boundaries weak.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- The README's backend port and monitoring API claims do not match the provided backend entry point; verify the actual startup path and route implementations before adoption.
- The packet does not describe sensitive session fields, access controls, or network-transfer scope; do not assume the default deployment is secure or that all data exposure is limited to the local machine.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v1.0.0 OpenClaw Monitor v1.0.0
Release notes excerpt
OpenClaw Monitor v1.0.0 — First Stable Release Free open-source monitoring dashboard for OpenClaw AI agents. [](https://github.com/flik2002/openclaw-monitor) [](https://opensource.org/licenses/MIT) Download Binaries > Build assets are published to the [v20260514-140808 release](https://github.com/flik2002/openclaw-monitor/releases/tag/v20260514-140808) (same codebase). | File | Description | |------|-------------| …View on GitHub ↗ -
v20260514-140808 OpenClaw Monitor 2026-05-14T14:08:08Z
Release notes excerpt
OpenClaw Monitor Release Build: v20260514-140808 Date: 2026-05-14T14:08:08Z Included - frontend/dist/ - Built frontend static files - backend/ - Backend (run cd backend && npm start) - openclaw-monitor/ - Helper scripts Quick Start ``` tar -xzf openclaw-monitor-*.tar.gz cd openclaw-monitor cd backend && npm start cd frontend && npm run dev ```View on GitHub ↗ -
v20260514-134729 OpenClaw Monitor 2026-05-14T13:47:29Z
Release notes excerpt
OpenClaw Monitor Release Build: v20260514-134729 Date: 2026-05-14T13:47:29Z Included - frontend/dist/ - Built frontend static files - backend/ - Backend (run cd backend && npm start) - openclaw-monitor/ - Helper scripts Quick Start ``` tar -xzf openclaw-monitor-*.tar.gz cd openclaw-monitor cd backend && npm start cd frontend && npm run dev ```View on GitHub ↗
FAQ
Does it cost anything?
Do I need an OpenClaw Gateway?
Does any data leave my machine?
What if port 3000 or 5173 is already in use?
Can I run it on Linux or macOS?
Is OpenClaw Monitor open source?
Is OpenClaw Monitor safe to use?
Is OpenClaw Monitor still maintained?
Who makes OpenClaw Monitor?
Thanks — we use this to improve the page.