I've been building ClawMetry for past 5 weeks. 90k+ installs across 100+ countries.
The observability features I built first were the ones I personally needed: a live execution graph (Flow tab), full decision transcripts (Brain tab), token cost tracking per session, and visibility into sub-agent spawns.
But I keep hearing variations of the same thing: "I don't really know what my agents are doing." And everyone means something slightly different by that.
For some it's costs. For some it's timing (why did this take 4 minutes?). For some it's trust (did the agent actually do what I think it did?). For some it's failures (where exactly did it break?).
So I want to ask you directly:
If you're running AI agents today -- what's the one thing missing from your observability setup? What would make you feel like you actually understand what's happening inside your agents?
Options I'm thinking about next:
- Alerting (get notified when an agent fails or goes over budget)
- Cost per task breakdown (not just per session)
- Agent run comparisons (before/after a prompt change)
- Memory snapshots (what did the agent "know" at each decision point)
Drop your answer below. The next feature I build will be heavily influenced by this thread.
(ClawMetry is free to try locally: pip install clawmetry. Cloud: app.clawmetry.com, $5/node/month, 7-day free trial.)
ClawMetry
Hey Product Hunt! 👋
I'm Vivek, and I built ClawMetry because I got tired of not knowing what my AI agents were doing.
I run several OpenClaw agents. They handle code, research, deployment, scheduling. But every time one took 10 minutes on a task, I had no idea: is it stuck? Did it hallucinate? Is it burning through tokens?
NemoClaw (NVIDIA's AI agent sandbox) made running agents safer. But the built-in TUI is ephemeral and terminal-only. You can't see what happened yesterday. You can't watch 10 sandboxes from your phone. You can't track costs across your fleet.
So I built ClawMetry for NemoClaw. One command on the host, and every sandbox gets full observability:
🧠 Brain tab: every thought, tool call, and decision in real time
📊 Token tracking: per call, per session, no surprises
🔐 E2E encrypted: keys never leave your machine
🌐 Cloud dashboard: monitor everything from any browser
It's open source (MIT), free for local use, and took about two months of obsessive building.
With your love and support, ClawMetry has been downloaded 95,000+ times across 100+ countries. This NemoClaw integration is the next step.
What's coming next:
• Policy drift detection (get alerted when sandbox policies change)
• Remote egress approvals from your phone
• Fleet-wide policy management
Cloud sync is $5/sandbox/month. Local dashboard is free forever.
Would love your feedback. Happy to answer any questions!
🔗 https://clawmetry.com/nemoclaw
Token tracking per session is exactly what I've been wanting. Running multiple sandboxes and having zero visibility into which ones are burning through credits is so frustrating.
The E2E encryption part is a nice touch too. Most monitoring tools want you to ship all your data to their cloud which is a nonstarter for anything sensitive. Open source MIT makes it easy to just try it without committing.