Agent Builder Cobertura Sua máquina Auto-hospedado Preços Cloud Entrar Dispositivo Docs Blog Vitrine Roadmap Empresas

Roda na sua máquina · age só quando você mandar

O Painel de Controle
para Agentes de IA

  • Veja cada agente.
  • Entenda cada ação.
  • Impeça o que não deveria acontecer.

O ClawMetry lê os 26 runtimes de agentes que seu time já usa, do Claude Code e Cursor ao Codex e OpenClaw, direto dos arquivos que eles já escrevem. Nada para adicionar ao agente.

$ pip install clawmetry && clawmetry

7 dias, todos os runtimes, sem cartão. Depois, $9 ou $19 por nó, por mês.

Ou baixe o aplicativo para desktop macOS Windows Linux

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.

15detecções em quatro meses: 6 sem progresso, 6 de falha repetida de ferramenta, 3 de loop travado
7 of 68das sessões do Claude Code geraram ao menos um alerta. Nem ruidoso, nem raro.
0de configuração necessária. A detecção começa na instalação e cobre todo runtime que encontrar.

Supported agent runtimes

Medido, uma instalação, quatro meses

Ele sinaliza agentes que travam,
não agentes que custam dinheiro.

Uma sessão longa e cara costuma ser seu melhor trabalho, então uma ferramenta que caça números altos mataria a coisa errada. O ClawMetry olha se o agente está produzindo algo. Mesmo notebook, quatro meses, os dois casos lado a lado.

Funcionando · nunca sinalizado

$171.58

1,700 turns · 527,741 tokens · 0 detections

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.

Sinalizado · travando

$175.10

7 sessions · 4% of all sessions · 21% of all spend

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.

Os detectores avisam. Eles não agem. Todas as sete sessões rodaram até o fim. O alerta é uma notificação, não um gatilho. Nada é interrompido a menos que uma pessoa interrompa, ou que você mesmo defina um limite de gasto e um agente o ultrapasse.

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.

Veja em ação

Uma tela. Tudo o que acontece em seus agentes.

clawmetry - flow
ClawMetry dashboard

As lacunas estão na tabela

O que conseguimos fazer, por runtime.

Todo fornecedor dessa categoria fala em guardrails. Esta é a matriz inteira, incluindo as células vazias.

Runtime Observar Bloquear antes de rodar Encerrar durante a execução Custo em 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 rodar

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.

Encerrar durante a execução

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 depois

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 colocar um daemon no seu notebook

O que ele faz com a máquina,
e o que sai dela.

Medido naquele mesmo notebook, não estimado.

Consumo

Local store, 165 sessions and 19,977 events145 MB
Per session, average~880 KB
Network destinations, cloud offnone
Inbound ports opened0
Localhost query server127.0.0.1 + token
Removalclawmetry uninstall

The 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.

O que sai, exatamente

transcriptspromptstool callsfile paths logsmemoryyour code

Never. These stay in the local file.

WITH CLOUD ON ↓
AES-256-GCM ciphertextnode idversioncounters

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.

O arquivo local é texto puro

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.

A remoção de dados sensíveis falha de forma permissiva

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.

Um nó conectado pode ser parado remotamente

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.

O que as pessoas dizem

O que a comunidade está dizendo sobre o ClawMetry

Ver tudo
Simen.ai
Blog review
Blog
ClawMetry has become the go-to open source observability dashboard for OpenClaw agents. No configuration required, and the live flow visualization shows you the actual decision path your agent took, step by step.
Mykola Kondratiuk
Product Hunt
Product Hunt
Oh this is exactly what I needed. The biggest pain point has been figuring out where my tokens are going. Especially with sub-agents spawning other sub-agents, costs spiral fast and you have zero visibility.
@oadiaz
Medium
Medium
It's like going from 'I think my agents are working' to having a mission control center. The cost tracking alone was worth it. I discovered one agent was using 3x more tokens than necessary.
Product Hunt
#5 Launch Day
ClawMetry launched alongside Claude Sonnet 4.6 and held #5 all day. Featured in the PH newsletter under 'Keep agents in line.' 198+ upvotes.
Mayank Jain
LinkedIn
LinkedIn
What are your AI agents actually doing behind the scenes? Most builders don't know. They just hope everything works. But hope is not observability. Meet ClawMetry.
awesome-openclaw
Community list
Awesome List
Open source observability for OpenClaw: token costs, session drift, memory alerts. Nothing leaves your machine.
FunBlocks AI Reviews
Review
Review
A must-have for any serious developer or startup working with AI sandboxes.
@jonah_lipsitt
▶ Video
I got tired of not knowing what my OpenClaw was doing. A Phillips Hue spotlight now shines on my Mac Mini based on what it is doing, further visualized by @clawmetry
@KalariyaHiren1
Thread
Ask OpenClaw to do something. It starts working. And you just... wait. Hoping. Is it searching? Which websites? Where is it stuck right now? Zero visibility. ClawMetry fixes that.
@Save_Delete
If you are building with OpenClaw, ClawMetry is the missing piece. Real-time visibility into every sub-agent, tool call, token cost, and session log.
Mihail / HookWatch
Product Hunt
Product Hunt
This is exactly the kind of tooling the AI agent ecosystem needs right now. The per-session cost breakdown is a smart move. Most teams have no idea what their agents actually cost until the invoice hits.
@nickvnturi
This looks like a very helpful tool for tracking agents. Thanks for sharing it.
@Asif2BD
ClawMetry and our JARVIS Mission Control complement each other. Observability and coordination are separate problems.
@complete_ai_training
Instagram
Instagram
On the 19th of February, I discovered 5 exciting new AI tools you won't want to miss: ClawMetry for OpenClaw, Flixier, Your AI Clone, Baseline Core, and STUD.
@ProductHunToday
Top 5 · Product Hunt
Top 5 on Product Hunt (Feb 18, 2026): #5 ClawMetry for OpenClaw, launched alongside Claude Sonnet 4.6.
Harsh Upadhyay
Product Hunt
Product Hunt
Really like the clarity of 'Know what your agents are doing. Right now.' The core pain you're solving feels bigger than a single ecosystem. Very clean execution.
Damian Saez
Product Hunt
Product Hunt
Observability for AI agents is something most builders overlook until things break in production. Love that you're tackling this early.
Simen.ai
Blog review
Blog
ClawMetry has become the go-to open source observability dashboard for OpenClaw agents. No configuration required, and the live flow visualization shows you the actual decision path your agent took, step by step.
Mykola Kondratiuk
Product Hunt
Product Hunt
Oh this is exactly what I needed. The biggest pain point has been figuring out where my tokens are going. Especially with sub-agents spawning other sub-agents, costs spiral fast and you have zero visibility.
@oadiaz
Medium
Medium
It's like going from 'I think my agents are working' to having a mission control center. The cost tracking alone was worth it. I discovered one agent was using 3x more tokens than necessary.
Product Hunt
#5 Launch Day
ClawMetry launched alongside Claude Sonnet 4.6 and held #5 all day. Featured in the PH newsletter under 'Keep agents in line.' 198+ upvotes.
Mayank Jain
LinkedIn
LinkedIn
What are your AI agents actually doing behind the scenes? Most builders don't know. They just hope everything works. But hope is not observability. Meet ClawMetry.
awesome-openclaw
Community list
Awesome List
Open source observability for OpenClaw: token costs, session drift, memory alerts. Nothing leaves your machine.
FunBlocks AI Reviews
Review
Review
A must-have for any serious developer or startup working with AI sandboxes.
@jonah_lipsitt
▶ Video
I got tired of not knowing what my OpenClaw was doing. A Phillips Hue spotlight now shines on my Mac Mini based on what it is doing, further visualized by @clawmetry
@KalariyaHiren1
Thread
Ask OpenClaw to do something. It starts working. And you just... wait. Hoping. Is it searching? Which websites? Where is it stuck right now? Zero visibility. ClawMetry fixes that.
@Save_Delete
If you are building with OpenClaw, ClawMetry is the missing piece. Real-time visibility into every sub-agent, tool call, token cost, and session log.
Mihail / HookWatch
Product Hunt
Product Hunt
This is exactly the kind of tooling the AI agent ecosystem needs right now. The per-session cost breakdown is a smart move. Most teams have no idea what their agents actually cost until the invoice hits.
@nickvnturi
This looks like a very helpful tool for tracking agents. Thanks for sharing it.
@Asif2BD
ClawMetry and our JARVIS Mission Control complement each other. Observability and coordination are separate problems.
@complete_ai_training
Instagram
Instagram
On the 19th of February, I discovered 5 exciting new AI tools you won't want to miss: ClawMetry for OpenClaw, Flixier, Your AI Clone, Baseline Core, and STUD.
@ProductHunToday
Top 5 · Product Hunt
Top 5 on Product Hunt (Feb 18, 2026): #5 ClawMetry for OpenClaw, launched alongside Claude Sonnet 4.6.
Harsh Upadhyay
Product Hunt
Product Hunt
Really like the clarity of 'Know what your agents are doing. Right now.' The core pain you're solving feels bigger than a single ecosystem. Very clean execution.
Damian Saez
Product Hunt
Product Hunt
Observability for AI agents is something most builders overlook until things break in production. Love that you're tackling this early.
Ver todos os comentários no Product Hunt

Três lugares para rodar

A Cloud é opcional.
Sempre foi.

O daemon calcula tudo em um arquivo DuckDB no seu próprio disco. Onde o painel fica depois disso é decisão sua, e o valor é o mesmo em qualquer opção.

01 · Local only

Nada sai

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

Selado antes de sair

$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

Sua infraestrutura, 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

O valor não muda com o tipo de implantação. Auto-hospedado custa $19 por nó por mês ou $190 por nó por ano, exatamente como o plano na nuvem, porque você paga pelo software e não pelos nossos servidores. O que muda é quem guarda os dados e quem roda o contêiner. Compre uma chave auto-hospedada sem falar com ninguém.

Um valor, um medidor

Calcule seu número
antes de falar com alguém.

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.

Quanto custa para você

Conte as máquinas que vão rodar o daemon, não as pessoas que vão olhar o painel.

25
4

$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 quem responde pelo risco

Rodando isso em toda a empresa.

Seus engenheiros instalaram Claude Code, Cursor, Codex e Copilot no trimestre passado. Ninguém passou por compras, e todos eles têm seu repositório e suas chaves.

Nada para instalar no 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.

Self-hosted é a resposta para 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.

Funciona na rede que você já tem

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.

A implantação em frota ainda é 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.
Get the fleet brief The gap list Both dated and versioned. The gap list names everything we have not built, including SSO, RBAC, SOC 2 and data residency.

Perguntas que sempre recebemos.

Dá para bloquear algo antes de rodar ou só avisar que rodou?

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.

Ele vai parar meus agentes por conta própria?

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.

Muda a forma como meus agentes rodam?

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.

O que acontece quando meu teste gratuito termina?

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.

Quem está por trás disso e o que acontece se vocês sumirem?

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.

Isso passa em uma revisão de segurança?

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.

Fique por dentro

Receba avisos sobre novos recursos, lançamentos e o crescente ecossistema -metry.