Se ejecuta en tu máquina · actúa solo cuando tú lo indicas
El plano de control
para agentes de IA
- Ve cada agente.
- Entiende cada acción.
- Detén lo que no debería ocurrir.
ClawMetry lee los 26 runtimes de agentes que tu equipo ya utiliza, desde Claude Code y Cursor hasta Codex y OpenClaw, directamente desde los archivos que ya escriben. No hay que añadir nada al agente.
$ pip install clawmetry && clawmetry
7 días, todos los runtimes, sin tarjeta. Después, $9 o $19 por nodo al mes.
“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.
❯ 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.
Medido, una instalación, cuatro meses
Señala agentes que se estancan,
no agentes que cuestan dinero.
Una sesión larga y cara suele ser tu mejor trabajo, así que una herramienta que persiguiera cifras altas eliminaría justo lo que no debe. ClawMetry observa si un agente está produciendo algo. El mismo portátil, cuatro meses, ambos casos en paralelo.
Funcionando · nunca señalado
$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.
Señalado · estancado
$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.
Los detectores avisan. No actúan. Las siete sesiones llegaron hasta el final. La alerta es una notificación, no un disparador. Nada se detiene salvo que lo detenga una persona, o salvo que tú fijes un límite de gasto y un agente lo supere.
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.
Míralo en acción
Una sola pantalla. Todo lo que ocurre en tus agentes.
Los huecos están en la tabla
Lo que podemos hacer, por runtime.
Todos los proveedores de esta categoría hablan de barreras de protección. Esta es la matriz completa, incluidas las celdas vacías.
| Runtime | Observar | Bloquear antes de ejecutarse | Detener en plena ejecución | Coste en dólares |
|---|---|---|---|---|
| OpenClaw, NVIDIA NemoClaw, Goosefree forever | ✓ | via proxy | ✓ | ✓ |
| Claude Codethe only pre-execution tool gate | ✓ | ✓ | ✓ | ✓ |
| Codex, OpenCode, Aider | ✓ | via proxy | ✓ | ✓ |
| Cursorone IDE process holds every session | ✓ | – | – | – |
| GitHub Copilotbilled in vendor credits, not USD | ✓ | – | – | – |
| NanoClaw, PicoClaw, Kimi CLIno model id on disk | ✓ | – | – | – |
| Qwen, Hermes, Pi, Deep Agents, n8n, Antigravity, Grok, QM, DeepSeek Harness, Exo |
✓ | via proxy | – | ✓ |
Bloquear antes de ejecutarse
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.
Detener en plena ejecución
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.
Auditar después
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.
Antes de poner un daemon en tu portátil
Qué le hace a la máquina,
y qué sale de ella.
Medido en ese mismo portátil, no estimado.
Huella
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.
Qué sale, exactamente
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.
El archivo local está en texto plano
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.
La redacción falla en abierto
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.
Un nodo conectado se puede detener en remoto
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.
Tres lugares donde ejecutarlo
La nube es opcional.
Siempre lo fue.
El daemon calcula sobre un archivo DuckDB en tu propio disco. Dónde vive el panel después de eso lo decides tú, y la tarifa es la misma elijas lo que elijas.
01 · Local only
No sale nada
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
Sellado antes de salir
$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
Tu infraestructura, un solo inquilino
$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
La tarifa no cambia según el despliegue. Autoalojado cuesta $19 por nodo al mes o $190 por nodo al año, exactamente igual que el plan en la nube, porque pagas por el software y no por nuestros servidores. Lo que cambia es quién guarda los datos y quién ejecuta el contenedor. Compra una clave autoalojada sin hablar con nadie.
Una tarifa, un contador
Calcula tu cifra
antes de hablar con nadie.
7 days, every runtime, no card
$19per node, per month
Pro, billed monthly. Starter is $9 and covers fewer features, not fewer runtimes. Annual is $190 per node, two months free. 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.
- Waste flags, error triage, cost optimizer, OTLP export, tool policy.
- Cancel any time in Stripe. No contract, no seat count.
Already decided? Buy now and install after. Your key is on the next screen.
Lo que te cuesta
Cuenta las máquinas que ejecutarán el daemon, no las personas que lo mirarán.
$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.
Para quienes asumen el riesgo
Desplegarlo en toda una empresa.
El trimestre pasado tus ingenieros instalaron Claude Code, Cursor, Codex y Copilot. Nadie los adquirió formalmente, y todos tienen tu repositorio y tus claves.
No hay nada que instalar en el agente
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.El autoalojamiento es la respuesta al SSO
SSO does not exist yet. Single-tenant self-hosted does: 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.Se adapta a la red que ya tienes
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.Hoy el despliegue en flota es manual
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.Las preguntas que nos hacen siempre.
¿Pueden bloquear algo antes de que se ejecute o solo avisarme de que ya pasó?
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.
¿Detendrá mis agentes por su cuenta?
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.
¿Cambia la forma en que se ejecutan mis agentes?
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.
¿Qué pasa cuando termina mi prueba?
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.
¿Quién está detrás de esto y qué pasa si desaparecen?
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.
¿Pasará una revisión de seguridad?
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, RBAC beyond owner and member, SOC 2, CAIQ and a third-party pen test are all absent, and that is a two-to-four quarter conversation.