How it works Cloud NemoClaw Roadmap Traction Showcase Pricing Blog Mac Install
Real-time observability for OpenClaw agents · E2E Encrypted · Open Source

Know what your agents
are doing. Right now.

Your OpenClaw and NVIDIA NemoClaw agents spawn sub-agents, burn tokens, call tools. You have no idea what they're actually doing. ClawMetry shows you in real-time and catches the weird ones before they make expensive mistakes.

Get Started Free Watch demo (3 min)
▸ How it works?
📦 186k+ installs 🌍 123+ countries ⭐ 337 on GitHub 🏆 #5 Product Hunt

❯ What People Say

What the community is saying about ClawMetry

View all →
@jonah_lipsitt
▶ Video
"I got tired of not knowing what my OpenClaw was doing. A Phillips Hue spotlight now shines on my Mac Mini based on what it is doing, further visualized by @clawmetry"
@Save_Delete
"If you are building with OpenClaw, ClawMetry is the missing piece. Real-time visibility into every sub-agent, tool call, token cost, and session log."
@ricardotosatt
"Love this for agent monitoring. Tracking tokens and memory in real time is a huge win for devs."
Product Hunt
#5 Launch Day
"ClawMetry launched alongside Claude Sonnet 4.6 and held #5 all day. Featured in the PH newsletter under 'Keep agents in line.' 198+ upvotes."
@nickvnturi
"This looks like a very helpful tool for tracking agents. Thanks for sharing it."
@Asif2BD
"ClawMetry and our JARVIS Mission Control complement each other. Observability and coordination are separate problems."
@KalariyaHiren1
Thread
"Ask OpenClaw to do something. It starts working. And you just... wait. Hoping. Is it searching? Which websites? Where is it stuck right now? Zero visibility. ClawMetry fixes that."
Mykola Kondratiuk
Mykola Kondratiuk
Product Hunt
"Oh this is exactly what I needed. The biggest pain point has been figuring out where my tokens are going. Especially with sub-agents spawning other sub-agents, costs spiral fast and you have zero visibility."
Damian Saez
Damian Saez
Product Hunt
"Observability for AI agents is something most builders overlook until things break in production. Love that you're tackling this early."
Mihail / HookWatch
Product Hunt
"This is exactly the kind of tooling the AI agent ecosystem needs right now. The per-session cost breakdown is a smart move. Most teams have no idea what their agents actually cost until the invoice hits."
Harsh Upadhyay
Product Hunt
"Really like the clarity of 'Know what your agents are doing. Right now.' The core pain you're solving feels bigger than a single ecosystem. Very clean execution."
@complete_ai_training
Instagram
"On the 19th of February, I discovered 5 exciting new AI tools you won't want to miss: ClawMetry for OpenClaw, Flixier, Your AI Clone, Baseline Core, and STUD."
Omar Diaz
@oadiaz
Medium
"It's like going from 'I think my agents are working' to having a mission control center. The cost tracking alone was worth it. I discovered one agent was using 3x more tokens than necessary."
LinkedIn
Post
"Then I installed ClawMetry. Before ClawMetry: Blind faith. After ClawMetry: Clear visibility."
@jonah_lipsitt
▶ Video
"I got tired of not knowing what my OpenClaw was doing. A Phillips Hue spotlight now shines on my Mac Mini based on what it is doing, further visualized by @clawmetry"
@Save_Delete
"If you are building with OpenClaw, ClawMetry is the missing piece. Real-time visibility into every sub-agent, tool call, token cost, and session log."
@ricardotosatt
"Love this for agent monitoring. Tracking tokens and memory in real time is a huge win for devs."
Product Hunt
#5 Launch Day
"ClawMetry launched alongside Claude Sonnet 4.6 and held #5 all day. Featured in the PH newsletter under 'Keep agents in line.' 198+ upvotes."
@nickvnturi
"This looks like a very helpful tool for tracking agents. Thanks for sharing it."
@Asif2BD
"ClawMetry and our JARVIS Mission Control complement each other. Observability and coordination are separate problems."
View all comments on Product Hunt ↗

❯ Quick Start

# One command. That's it. 🦞
$ curl -fsSL https://clawmetry.com/install.sh | bash

macOS, Linux, Windows. The installer figures it out.

Need help setting up?
Get free onboarding help →
Don't want to self-host?
Request managed instance →

See it in action

One screen. Everything happening across your agents.

clawmetry - flow
ClawMetry dashboard

What you get

Built because we needed it. Now you don't have to build it yourself.

The big one

Catch the agent that's about to spend $400. Before it does.

Sub-agents spawn sub-agents. One bad loop and your monthly bill 3x's overnight. ClawMetry shows the live spawn tree, kills runaways with one click, and pages you when an agent crosses a budget line. Your finance team will notice.

Sub-agent running

Sub-agent running

Sub-agent on completion

Sub-agent on completion

Diagnose a stuck agent in seconds

Channels, gateway, models, tools, nodes. All wired up, updating as things happen.

Cut your AI bill. Without changing a model.

Tokens in, tokens out, cache hits, response times, cost per call. Numbers you actually need.

Know about a cron failure before your customer does

Cron jobs, service uptime, disk usage, active sub-agents. Glanceable.

Audit what the agent did last Tuesday

Every session logged. Timeline, tool calls, cost. Go back and see what happened.

Works with the agent stack you already run

Hooks into OpenClaw's task system. See which agents are on which tasks.

Charge back to the right team

Per-session, per-model, per-tool. Know what you're spending before the invoice shows up.

Catch hallucinations and stuck loops

Flag action hallucinations, repeated tool call failures, and agents stuck in a loop. Before they burn through your budget.

OpenTelemetry-native

Drop ClawMetry into your existing OpenTelemetry pipeline. We accept standard OTLP traces and metrics on /v1/traces and /v1/metrics. No proprietary SDK required.

Runs where you run

If OpenClaw runs there, ClawMetry runs there. Laptop, server, Raspberry Pi, whatever.

AWS GCP Azure macOS Ubuntu Windows WSL Docker Kubernetes
+ also runs on Raspberry Pi, Hostinger, Hetzner, Digital Ocean
Raspberry Pi Hostinger Hetzner Digital Ocean Debian

Need this for your team? We’ll set it up in a day.

Managed deployment, volume pricing, and a direct line to the founder for 10+ node fleets.

🖥
Managed deployment
We deploy, configure, and operate ClawMetry across your fleet. You get full visibility from day one.
🚀
99.9% uptime SLA
Contractual uptime commitment with credit-back if we miss it. Status published at status.clawmetry.com.
📈
Volume pricing for 10+ nodes
Custom pricing once your fleet crosses ten nodes. Annual commits, PO billing, and procurement paperwork supported.
Request managed deployment → Talk to founder →

Stay in the loop

Get notified about new features, releases, and the growing -metry ecosystem.

Frequently Asked Questions

Everything you need to know about ClawMetry.

What is ClawMetry?

ClawMetry is a free, open-source real-time observability dashboard for AI agents running on OpenClaw. It gives you instant visibility into token costs, cron jobs, sub-agent activity, memory file changes, and session history — all in a single local dashboard.

Is ClawMetry free?

Yes, completely. ClawMetry is MIT licensed and runs locally on your machine. No cloud dependency, no telemetry, no subscription. There is also an optional ClawMetry Cloud plan for teams who want a hosted multi-node dashboard.

How do I install ClawMetry?

Run pip install clawmetry then clawmetry. It auto-detects your OpenClaw workspace — no config file needed. Setup takes about 30 seconds.

What does ClawMetry monitor?

ClawMetry monitors token usage and cost per session and model, cron job status and history, sub-agent spawns and outcomes, memory file changes (SOUL.md, MEMORY.md, AGENTS.md), session transcripts, channel activity, and real-time tool call traces.

Does ClawMetry work with Claude, GPT-4, and other models?

Yes. ClawMetry works with any model your OpenClaw agents use — Claude (Anthropic), GPT-4 (OpenAI), Gemini (Google), and others. It tracks cost and token usage per model automatically.

How is ClawMetry different from LangSmith or Weights & Biases?

LangSmith and W&B are enterprise platforms built for LLM application developers. ClawMetry is purpose-built for OpenClaw users — it understands the specific concepts of channels, cron jobs, sub-agents, memory files, and the full agent runtime. It runs locally in 30 seconds with zero config.

Is ClawMetry safe for compliance and ops teams?

Yes. ClawMetry runs entirely on your own machine and keeps a full audit trail of every tool call, policy violation, and sub-agent action. Personally Identifiable Information (PII) stays on-device because no transcripts leave your network. Data leaders, compliance, and ops teams can review what every agent did, when, and why, without sending data to a vendor.

What operating systems does ClawMetry support?

ClawMetry runs on Linux, macOS, and Windows (via WSL). It also works on Raspberry Pi and other ARM devices. Requires Python 3.8+ and an active OpenClaw installation.