Install ClawMetry locally for free, or connect a fleet of machines to ClawMetry Cloud. E2E encrypted, one dashboard for everything.
Press play for the quick tour, or skip it and read the full walkthrough below. Same story, either way.
Paid self-hosted licenses unlock all runtimes and paid features locally. See pricing.
Get started freeClawMetry reads the session files and logs your agent runtimes already write - OpenClaw, Claude Code, Codex, Cursor + 29 more runtimes. Nothing sits between your agents and the models.
ClawMetry auto-detects every supported runtime on your machine and shows them side by side - same tabs, same live feed, same cost attribution. No SDK, no code changes.
OpenClaw, NVIDIA NemoClaw, Goose and Qwen Code are free on every plan.
See exactly what happens at every layer - from incoming messages to LLM calls to tool execution. Gateway runtimes like OpenClaw map to all three layers; CLI runtimes like Claude Code and Codex are observed at the runtime layer, straight from their session files.
Mac Minis under a desk, EC2 and GCP instances, a container on an Ubuntu box. If your agent runs there, a node runs there. Each node end-to-end encrypts your agents' conversations and activity before sending; our servers keep no copy of the key, so the cloud stores that content as ciphertext it cannot read. Operational metadata like cost, model names and health syncs in readable form, and you see every machine in one dashboard, wherever you are.
Two commands. That's it.
Works wherever Python 3.8+ is installed. Same machine as your agents.
clawmetryAuto-discovers the AI agent runtimes on your machine. Opens the dashboard at localhost:8900.
No account. No API key. No config file. Open your browser and start watching.
Six tabs. Each one answers a different question about what your agents are doing.
Live feed of every tool call your agents make - across OpenClaw, Claude Code, Codex and every other runtime. Name, what it did, how long it took, updated in real time.
Live7-day history of every sub-agent run. See what task it was given, when it started, when it finished, and what it did along the way.
7-day historyReal-time token usage broken down by model and session. Know exactly which sessions are burning through your budget.
LiveEvery scheduled task in your agent setup - last run time, status, and run history. Catch a missed cron before it matters.
LiveService status for your agent gateway and connected components at a glance.
LiveBrowse past sessions with a full timeline of what happened - tool calls, costs, duration. Useful for debugging anything that went wrong.
SearchableClawMetry doesn't intercept traffic or modify your setup. Every runtime already writes its activity to disk - OpenClaw its workspace, Claude Code and Codex their session transcripts, Cursor its local state. ClawMetry reads those native files and presents them as one live dashboard.
This means zero overhead on your agents and zero risk of ClawMetry breaking anything.
ClawMetry reads these. Your agents keep writing them. Nothing changes.
Free, open source, and running in under a minute. No account required.
Get notified about new features, alerting integrations, the Mac app, and everything else coming to ClawMetry.