How do I monitor Hermes agents?

Install ClawMetry (pip install clawmetry). The daemon auto-detects Hermes and renders every session, tool call, model, and token in one dashboard at http://localhost:8900. The Hermes gateway itself is untouched — ClawMetry only observes.

Is ClawMetry safe to point at a running Hermes install?

Yes. ClawMetry only observes. It never writes to Hermes, and it never blocks Hermes while Hermes is working.

Does ClawMetry track per-channel Hermes activity?

Yes. Hermes records which channel adapter (Slack, Discord, Telegram, WhatsApp, web, or one of the 20+ others) each session came from; ClawMetry surfaces that provenance on the Sessions tab so you can filter by channel, see per-channel spend, and catch a runaway loop that's spamming one channel.

Does ClawMetry work with Hermes crons and skills?

Yes. ClawMetry reads both and surfaces cron health (last run, next run, failure count) and skill provenance (which skills the agent uses, how often, whether they are stale).

How much does ClawMetry cost for Hermes?

Free forever on your own machine. ClawMetry Cloud starts at $9 per node per month (Starter) or $19 per node per month (Pro, which adds policy gates, evals, and Self-Evolve findings). Hermes is one of 18 paid runtimes on the Cloud tier.

Hermes × ClawMetry

Observability and governance for Hermes agents

See every Hermes Agent session, tool call, and token as it happens. ClawMetry detects Hermes automatically and renders sessions, tokens, cost, cron health, and channel provenance in one dashboard. No wrapper.

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

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

What ClawMetry sees on Hermes

Once ClawMetry is running, your Hermes 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-session token totals pre-computed by Hermes: input, output, cache-read, cache-write, reasoning.
Cost per session, per model, per hour: cache-aware where the model supports caching. Compare Hermes spend against the other 19 runtimes ClawMetry observes.
Cross-channel session ownership (one Hermes session can span Slack, Discord, Telegram, and web at the same time): the Hermes-specific signal ClawMetry surfaces that generic dashboards do not.
Approval + kill switch: watch for token-maxing signals (message repeat, no-progress heuristic, cost-per-hour threshold), pause or kill the session 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 Hermes 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 Hermes.

Start the free trial →

The one thing this catches that Hermes alone does not

Left alone, Hermes's failure mode is a session that pauses on one channel and quietly resumes on another under a different rate limit. ClawMetry watches for it: cost per hour on the Hermes 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.