Launching today
ClawMetry for OpenClaw
Real-time observability dashboard for OpenClaw AI agents
299 followers
Real-time observability dashboard for OpenClaw AI agents
299 followers
ClawMetry is a free, open-source observability dashboard for OpenClaw AI agents. Think Grafana, but purpose-built for AI. One command install (pip install clawmetry), zero config. Monitor token costs, sub-agent activity, cron jobs, memory changes, and session history. All in real-time with a beautiful live flow visualization. Works on macOS, Linux, Windows, even Raspberry Pi
Observability for AI agents is something most builders overlook until things break in production. Love that you're tackling this early. How do you handle tracing when agents make multiple chained calls? In my experience building database agents, the hardest part to debug is when the agent interprets a query correctly but chains the wrong follow-up action. Clean dashboards for that would be a game changer.
@saezbaldo Great question, Damian. Tracing chained agent calls is exactly where most logging tools fall short.
ClawMetry tracks every tool call, sub-agent spawn, and session handoff with full context. So when agent A calls agent B which queries a database and picks the wrong follow-up, you can trace the entire chain: what each agent saw, what it decided, and where it went wrong.
The cron management dashboard also helps here. You can see scheduled tasks, their run history, and drill into individual executions. No more guessing which step broke.
We're actively building deeper tracing for multi-agent workflows. Would love your feedback if you try it out: pip install clawmetry and you're up in 30 seconds.
Thanks @vivek_chand ! The full chain tracing sounds exactly right — especially the part about tracking what each agent saw vs what it decided. That's where most debugging falls apart.
Curious: when you trace a chain where agent B picks the wrong follow-up action, does ClawMetry also capture whether B had the authority to take that action in the first place? That's been our obsession — the gap between "the agent did X" and "the agent was authorized to do X."
Will definitely give it a try. Tracing + authority control feels like a natural combo.
ResumeUp.AI
Congrats on the launch 🚀
Finally, real visibility into what agents are actually doing. Super useful for anyone building with OpenClaw.
@rohithreddy Thank you Rohith! That means a lot. Visibility into what the agent is doing was the #1 thing I was missing when I started building with OpenClaw, so I built it. Glad it resonates. Would love to hear how you use it with your setup!