How do I monitor NanoClaw agents?

Install ClawMetry (pip install clawmetry). The daemon auto-detects NanoClaw and renders every session, tool call, and token in one dashboard at http://localhost:8900. Works whether you run one NanoClaw agent or a fleet.

Does ClawMetry work with a NanoClaw fleet across Telegram / Slack / Discord?

Yes. NanoClaw's session records include the channel adapter that sourced each session; ClawMetry surfaces that on the Sessions tab so you can filter by channel, see per-channel spend, and catch a NanoClaw agent looping on one channel.

Can I see NanoClaw cost per hour?

Yes. The Cost tab computes per-session, per-model, per-hour spend from NanoClaw's turn-level token counts. Set a per-hour budget alert and the approval queue pauses the session before the next call if it crosses the threshold.

Does ClawMetry track NanoClaw crons and skills?

Yes. Cron jobs and skill usage are surfaced separately with last-run, next-run, and per-skill invocation counts.

How much does ClawMetry cost for NanoClaw?

Free forever on your own machine. Cloud starts at $9/node/mo (Starter, observability) or $19/node/mo (Pro, adds policy gates and evals).

NanoClaw × ClawMetry

Observability and governance for NanoClaw agents

See every NanoClaw session, tool call, and token as it happens. ClawMetry detects NanoClaw automatically and renders sessions, tokens, cost, and channel routing in one dashboard. No SDK.

Supported runtime Zero config, auto-detected Read-only Free trial Official NanoClaw site ↗

📦 631k+ installs 🌍 128+ countries ⭐ 392 on GitHub 🏆 #5 Product Hunt

What ClawMetry sees on NanoClaw

Once ClawMetry is running, your NanoClaw activity shows up as:

Sessions: started at, last activity, model, message count, per-session token totals.
Live activity: every tool call as it lands, with args and result. Turn-level tokens split.
Per-turn tokens: Per-turn token counts written by NanoClaw's runtime.
Cost per session, per model, per hour: cache-aware where the model supports caching.
Fleet-of-nano-agents attribution (one operator, many NanoClaw agents on different channels): the NanoClaw-specific signal ClawMetry surfaces that generic dashboards do not.
Approval and kill switch: watch for token-maxing signals (message repeat, no-progress heuristic, cost-per-hour threshold), pause or kill before the next call.

Enable it in about two minutes

1. Install ClawMetry

Pick the line that matches your OS. Windows users: paste the install.cmd line, not the shell one.

# macOS or Linux
curl -fsSL https://clawmetry.com/install.sh | bash

# Windows (cmd.exe or PowerShell)
curl -fsSL https://clawmetry.com/install.cmd -o install.cmd && install.cmd

Already have Python? pip works too; onboard is the interactive first-run wizard.

# Any OS with Python 3.9+
pip install clawmetry && clawmetry onboard

Or skip the terminal entirely and grab the desktop app: macOS (.dmg) · Windows (.exe) · Linux (.AppImage). It installs and updates ClawMetry for you.

2. Run the daemon

clawmetry

The daemon auto-detects NanoClaw and starts reading immediately. No env var, no config, no runtime restart.

3. Open the dashboard

Open http://localhost:8900. Switch the runtime chip to NanoClaw.

Start the free trial →

The one thing this catches that NanoClaw alone does not

Left alone, NanoClaw's failure mode is one of the fleet quietly loops on a channel nobody watches. ClawMetry watches for it: cost per hour on the NanoClaw runtime, message-repeat detection, and per-session token-growth curves. Set a threshold, and the approval queue pauses before the next call. Kill switch (Pro) stops it.