---
title: What is ClawMetry?
description: ClawMetry is a local-first observability and governance layer for AI coding agents. It reads what {{RUNTIME_COUNT}} runtimes already write to disk and makes it answerable.
keywords: AI agent observability, what is agent observability, LLM agent monitoring, coding agent telemetry
eyebrow: Get started
---

# What is ClawMetry?

You are running coding agents. Possibly several, possibly across several
machines, almost certainly across more than one vendor: Claude Code in one
terminal, Cursor in the editor, a Codex run on a server, an OpenClaw agent
answering Telegram messages at 3am.

Each of those writes a detailed record of what it did — transcripts, tool
calls, token counts — into its own private directory, in its own format. None
of them shows you the others. None of them tells you what the whole fleet cost
last week. And none of them tells you when one of them has been looping on the
same failing command for forty minutes.

ClawMetry reads all of them.

## The three jobs

**Observation.** Find every agent runtime on the machine, read what it wrote,
normalise it into one event schema, and store it locally. This is read-only:
ClawMetry opens those files read-only and never writes into an agent's
directory. See [How detection works](/docs/runtimes/detection/).

**Understanding.** Turn that stream into things you can act on — cost per
session, per model, per runtime, per skill; which tools are slow; which
sessions never made progress; what the agent was actually thinking when it
decided to `rm -rf` something. See the [dashboard tour](/docs/dashboard/overview/).

**Governance.** Detect an agent that has gone off the rails and — if and only
if you have opted in — stop it. See [Guard](/docs/guard/overview/).

## What makes it different

**It is local first.** The database is a DuckDB file on your machine. There is
no account required, no API key, and no network call in the default install.
Cloud sync is optional, and when you turn it on, session content is encrypted
with AES-256-GCM *before* it leaves the machine — the server stores ciphertext
it cannot read. See [End-to-end encryption](/docs/cloud/encryption/).

**It reads what already exists.** There is no SDK to import and no
instrumentation to add for the supported runtimes. You install it and it finds
your agents. For agents that write nothing to disk — a production service built
on an SDK — there are two explicit paths:
[the interceptor](/docs/runtimes/sdk-agents/) and
[the ingest API](/docs/runtimes/custom-ingest/).

**It refuses to invent numbers.** Runtimes differ wildly in what they persist.
PicoClaw's message struct has no token field at all; Cursor's backend is
proprietary; Kimi records a full token breakdown but never the model id. Where
the data is not there, ClawMetry reports it as unknown and says why, rather than
showing a plausible dollar figure. A `$0.00` and an *unknown* are different
facts and the UI keeps them different.

**Severity is measured in money.** A Guard incident carries
`spend_at_risk_usd` — the estimated cost of the flagged stretch, not the whole
session — plus the basis that produced it. Sessions are ranked by what they are
burning, because ranking a list by an invented severity score is how real
incidents end up on page three.

## What it is not

- It is not a hosted APM. Nothing is sent anywhere by default.
- It is not a prompt-evaluation product. There is an
  [eval suite runner](/docs/cli/eval/), but the core is telemetry, not scoring.
- It is not a proxy you must route traffic through. The
  [enforcement proxy](/docs/guard/proxy/) exists and is optional; observation
  does not need it.
- It is not, by default, able to touch your agents. Intervention is off until
  you turn it on, and there are exactly four surfaces that can do it — all
  documented in [Guard](/docs/guard/overview/).

## Who it is for

- **A developer with several agents** who wants one place to see what they cost
  and what they are doing.
- **A team lead** who needs to know which runtime, model or person is driving
  spend, and wants alerts before a bill arrives rather than after.
- **A platform or security engineer** who has to answer "what did the agent do,
  on which machine, with what permissions, and can we prove it?" — see
  [Tamper-evident integrity](/docs/data/integrity/) and
  [Hardening](/docs/config/security/).

## Next

[Install it](/docs/start/install/), then walk the
[quickstart](/docs/start/quickstart/).