Draait op jouw machine · grijpt alleen in als jij het zegt
De control plane
voor AI-agents
- Zie elke agent.
- Begrijp elke actie.
- Stop wat niet mag gebeuren.
Je machine heeft System Monitor voor processen. Dit is die voor AI-agents. Automatisch gedetecteerd zodra ze draaien, elke token gekoppeld aan de taak die hem uitgaf, elke ontspoorde loop gemarkeerd voordat het budget eraan gaat.
Gratis uitproberen, geen creditcard. macOS (.dmg) Windows (.exe) Linux (.AppImage)
Of installeer via de terminal
$ pip install clawmetry && clawmetry
7 dagen, elke runtime, geen creditcard. Daarna $9 of $19 per node per maand.
“claude_code: 84 tool calls, no file changes, not advancing.” Stop or Pause this agent from the ClawMetry dashboard or device.
Verbatim record, not a mockup. A real detection from the laptop ClawMetry was built on. The steps, the counts and the message are what the daemon wrote to disk.
Waarom ClawMetry bestaat
Elke AI-agent heeft een noodstop nodig.
Als een autonoom systeem zich misdraagt, wie houdt het dan tegen? Het verhaal achter ClawMetry, van twee jeugdfilms tot een onafhankelijk controleplatform.
Lees het verhaal van de oprichter →
❯ Supported agent runtimes
Don't see the agent harness you use?
Just share it and we'll add support in ~2 days. Leave your email and we'll ping you the moment it's live, plus 2 months of Pro, on us.
We only use your email to notify you and issue the Pro credit. No lists, no spam.
Gemeten, één installatie, vier maanden
Het markeert agents die vastlopen,
niet agents die geld kosten.
Een lange, dure sessie is vaak juist je beste werk, dus een tool die op grote getallen jaagt, snoeit het verkeerde weg. ClawMetry kijkt of een agent daadwerkelijk iets oplevert. Zelfde laptop, vier maanden, beide gevallen naast elkaar.
Werkt · nooit gemarkeerd
$171.58
The most expensive session of the four months. It ran long and cost real money, and it was writing code the whole time. ClawMetry left it alone, which is the correct answer.
Gemarkeerd · loopt vast
$175.10
Every one caught for the same reason: tool calls with no file changes, the same failure repeating, or a loop that stopped advancing. Most of them cost less than the session on the left.
Detectors waarschuwen. Ze grijpen niet in. Alle zeven van die sessies liepen gewoon af. De markering is een melding, geen trigger. Er wordt niets gestopt tenzij iemand het stopt, of tenzij je zelf een uitgavenlimiet instelt en een agent daaroverheen gaat.
165 sessions and $826.47 of agent spend on one developer’s laptop, April to August 2026. One machine, not a customer aggregate. Yours will look different, which is the reason to read your own.
Zie het in actie
Eén scherm. Alles wat er gebeurt bij je agents.
De gaten staan gewoon in de tabel
Wat we kunnen, per runtime.
Elke leverancier in deze categorie roept guardrails. Dit is de volledige matrix, inclusief de lege vakjes.
| Runtime | Observeren | Blokkeren vóór uitvoering | Afbreken tijdens uitvoering | Kosten in dollars |
|---|---|---|---|---|
| OpenClaw, NVIDIA NemoClaw, Goosefree forever | ✓ | via proxy | ✓ | ✓ |
| Claude Codethe only pre-execution tool gate | ✓ | ✓ | ✓ | ✓ |
| Codex, OpenCode, Aider | ✓ | via proxy | ✓ | ✓ |
| Qwen, Pi, Grok Build, DeepSeek Harnessper-terminal CLI processes, resolved by argv and cwd | ✓ | via proxy | ✓ | ✓ |
| GitHub Copilotbilled in vendor credits, not USD | ✓ | – | ✓ | – |
| Kimi CLIno model id on disk | ✓ | – | ✓ | – |
| Hermes, Deep Agents, n8n, Antigravity, QM, Exo |
✓ | via proxy | – | ✓ |
| NanoClaw, PicoClawno model id on disk | ✓ | – | – | – |
| Cursorone IDE process holds every session | ✓ | – | – | – |
Eight of the 30 have adapters but are not yet audited into this table: Gemini CLI, Lovable, Cline, OpenHands, OpenWorker, Devin, Grok Bot and Replit Agent. They are observed; the other three columns are unverified or unavailable, so they are absent rather than guessed.
Blokkeren vóór uitvoering
Claude Code gets a real pre-execution gate: a PreToolUse hook parks the call before the tool fires. Everything routed through the ClawMetry proxy gets spend refused with a 429 before tokens are spent.
Afbreken tijdens uitvoering
A gateway kill for OpenClaw, and SIGSTOP then SIGKILL against the process tree for the CLI runtimes, with a guard so a recycled pid is never the one we hit. macOS and Linux. Windows has no SIGSTOP, so pause and resume do not exist there.
Achteraf auditen
Every event carries a SHA-256 chain over its immutable fields, per node, with a verifier command. Approval decisions land in an append-only log. Works on every runtime.
Voordat je een daemon op je laptop zet
Wat het met de machine doet,
en wat er vertrekt.
Gemeten op één referentie-installatie: 165 sessies, 19.977 events. Niet geschat.
Footprint
clawmetry uninstallThe query server binds to loopback only, with a one-time 32-hex token and a discovery file at mode 0600. It is why the dashboard can read the store without holding the writer lock.
Wat er precies vertrekt
Never. These stay in the local file.
The key is generated on the node and never leaves it. Decryption happens in your browser. Compelled by a subpoena, we hand over a blob we cannot open, plus the node id, the version and some counters.
Het lokale bestand is platte tekst
Everything is sealed in transit and at rest in our cloud, and it is not encrypted on your own disk. The DuckDB file carries default user permissions. Anything running as your user can read it.
Redactie faalt open
Secrets are fingerprinted at ingest by default, before disk. It is pattern-based, and on an internal error it keeps the original value rather than dropping data. It is tuned for credential shapes, not customer PII.
Een verbonden node kan op afstand worden gestopt
If you turn cloud on, Stop, Pause and Resume are reachable from the dashboard and the desk device for any node on the account. That is the feature. Run local-only and no such channel exists.
Starred by the people building AI
Engineers and founders from OpenAI, Google, PostHog and more have starred ClawMetry on GitHub. One of them helped build it.
Drie plekken om het te draaien
Cloud is optioneel.
Dat is het altijd geweest.
De daemon rekent alles door naar een DuckDB-bestand op je eigen schijf. Waar het dashboard daarna leeft, bepaal jij, en het tarief is hetzelfde welke je ook kiest.
01 · Local only
Er vertrekt niets
Included in the MIT core
The dashboard reads the local file through a loopback query server. There is no account, no sync and no destination to point at.
- Network destinations: none
- Inbound ports opened: 0
- Free forever for OpenClaw, NVIDIA NemoClaw and Goose
02 · Our cloud
Verzegeld voordat het vertrekt
$19 per node, per month
The snapshot is encrypted on the node with a key generated there and never sent. Your browser decrypts it. Subpoena us and we hand over a blob we cannot open.
- AES-256-GCM, key held on the node
- Decryption happens client side
- Stop, Pause and Resume reach any node on the account
03 · Self-hosted
Jouw infrastructuur, single tenant
$190 per node, per year
One container serves the UI and the ingest API on your own network, with node tokens and admin auth. Licences verify offline against an embedded Ed25519 key you can fingerprint and compare.
- No calls to clawmetry.com beyond an off-by-default version ping
- Same feature set, same runtimes, same rate
- Two months free against the monthly price
Het tarief verandert niet met de deployment. Self-hosted kost $19 per node per maand of $190 per node per jaar, precies zoals het cloudplan, want je betaalt voor de software en niet voor onze servers. Wat verandert, is wie de data beheert en wie de container draait. Koop een self-hosted sleutel zonder met iemand te praten.
Eén tarief, één meter
Reken je bedrag uit
voordat je iemand spreekt.
7 days of Pro, every runtime, no card
$9per node, per month
Starter, billed monthly. Annual is $90 per node, two months free. Starter is the observability tier: fewer features than Pro, not fewer runtimes. Free forever for OpenClaw, NVIDIA NemoClaw and Goose.
Start the trial- Every runtime, including Claude Code, Codex and Cursor.
- Cloud or fully self-hosted, at the same rate. Unlimited chat channels.
- Cost and token split, budget limits, anomaly detection, approval queue.
- Cancel any time in Stripe. No contract, no seat count.
Not in Starter: the pre-execution tool gate, waste flags, per-run compare, error triage, Self-Evolve findings, the eval suite and OTel export. Those are Pro.
$19per node, per month
Pro, billed monthly. Annual is $190 per node, two months free. Pro is the governance tier: it adds gates, evals and waste analysis on top of Starter. Free forever for OpenClaw, NVIDIA NemoClaw and Goose.
Start the trial- Everything in Starter, and the same 30 runtimes.
- Tool policy with a pre-execution gate, and an eval suite that scores runs.
- Waste flags, per-run compare, error triage, cost optimizer, OTel export.
- Cancel any time in Stripe. No contract, no seat count.
The 7-day trial is Pro, whichever plan you land on afterwards. No card, and nothing is charged if you stop.
Already decided? Buy now and install after. Your key is on the next screen. Compare Starter and Pro.
Wat het je kost
Tel de machines die de daemon gaan draaien, niet de mensen die ernaar gaan kijken.
$551 $6,612 per year · 29 nodes
A node is a machine running the daemon and reporting a heartbeat. The unit of attribution is a machine, so spend maps to a laptop, not to a team. The same number applies self-hosted, so you can price a deployment on your own infrastructure off this figure without asking us. Ephemeral CI runners are not yet specified; the fleet brief carries the rule in writing before you sign.
Voor wie het risico draagt
Dit uitrollen over een heel bedrijf.
Je engineers installeerden vorig kwartaal Claude Code, Cursor, Codex en Copilot. Niemand heeft ze ingekocht, en ze hebben allemaal je repo en je sleutels.
Niets te installeren in de agent
Each runtime is read from the session store it already writes. No SDK, no wrapper, no second agent on the laptop, nothing a developer has to opt into or can forget.
A control layer that governs only its own SDK is blind to everything a developer runs outside it.Self-hosted is het antwoord op SSO
SSO ships: SAML and OIDC through WorkOS, with the pinned domain gating provisioning. Roles are owner and member, and nothing finer. If your rollout needs more than that, it is not built yet. Single-tenant self-hosted runs air-gapped: one container serves the UI and the ingest API, with node tokens and admin auth, and licences verify offline against an embedded Ed25519 key you can fingerprint and compare.
A self-hosted deployment makes no calls to clawmetry.com beyond an off-by-default version ping.Het past binnen het netwerk dat je hebt
SIEM and syslog export in CEF or JSON over TCP, UDP or TLS, emitted daemon-side because the cloud never holds plaintext. Corporate TLS interception is supported, with a doctor command that walks DNS, TCP, proxy and TLS in order.
In: your collector feeds us over OTLP. Out: full-event SIEM export. Not yet: correlated spans carrying your trace ids.Uitrol over een fleet gaat vandaag handmatig
There is no Helm chart, no Terraform provider and no Intune or Jamf package. If a daemon on developer laptops is a non-starter, run the enforcement proxy centrally and govern spend without touching an endpoint.
Auto-update ships on by default. CLAWMETRY_AUTO_UPDATE=0 turns it off. No staged rollout, no version pinning.Vragen die we elke keer krijgen.
Kun je iets blokkeren voordat het draait, of hoor ik alleen achteraf dat het gedraaid is?
Both, and the split is in the table above. Claude Code gets a genuine pre-execution tool gate, and anything routed through the proxy gets spend refused with a 429 before tokens are spent. For the other runtimes it is detection plus process control: we can see it and end it, we cannot veto the call it already made.
Is ClawMetry only for OpenClaw?
No. It launched in February 2026 as an OpenClaw-only dashboard and many directory listings still describe it that way, but it now reads 30 runtimes: OpenClaw, Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Lovable, Cline, OpenHands, OpenWorker, OpenCode, NVIDIA NemoClaw, Aider, Goose, n8n, Qwen, Devin, Antigravity, Grok Build, Grok Bot, Hermes, Pi, Deep Agents, Kimi CLI, DeepSeek Harness, Exo, NanoClaw, PicoClaw, QM and Replit Agent. It auto-detects whichever of those are on the machine, so a mixed fleet lands in one dashboard. OpenClaw, NVIDIA NemoClaw and Goose are free forever in the open source package; the rest are on the paid tier.
Legt het mijn agents uit zichzelf stil?
No. Detectors write a warning and stop there. On the reference install every flagged session ran to completion. A run ends only when a person ends it, or when you have set a spend cap yourself and an agent crosses it.
Verandert het hoe mijn agents draaien?
Read-only by default. Two things you opt into change that: the proxy, a separate process you point one env var at, and approval gates, where ClawMetry adds a gate to the runtime’s own permission system and removes only what it added.
Wat gebeurt er als mijn proefperiode afloopt?
The paid runtimes stop being read and the free three keep working. Entitlements are a commercial boundary, not a technical one. We do not hard-block a running fleet on a licence check.
Wie zit hierachter, en wat gebeurt er als jullie verdwijnen?
One person, plus contributors. The core is MIT and runs on your machine, so if we vanish your install keeps working and your data stays in a DuckDB file you own. The paid layer is a separate closed package. Ask for the fleet brief and it names the legal entity, the largest deployment we run today, and the reference count, with no rounding.
Komt dit door een security review?
For a pilot on non-production machines, usually: MIT source you can audit, local-first storage, single-tenant self-hosted and offline licence verification are the arguments that work. For a regulated production rollout, read the gap list first. SSO is there; RBAC beyond owner and member, SOC 2, CAIQ and a third-party pen test are not, and that is a two-to-four quarter conversation.