Berjalan di mesin Anda · bertindak hanya atas perintah Anda
Control Plane
untuk Agen AI
- Lihat setiap agen.
- Pahami setiap tindakan.
- Hentikan yang tidak semestinya terjadi.
Mesin Anda punya System Monitor untuk proses. Ini versinya untuk agen AI. Terdeteksi otomatis begitu berjalan, setiap token terhubung ke tugas yang menghabiskannya, setiap loop liar ditandai sebelum anggaran jebol.
Coba gratis, tanpa kartu. macOS (.dmg) Windows (.exe) Linux (.AppImage)
Atau pasang lewat terminal
$ pip install clawmetry && clawmetry
7 hari, semua runtime, tanpa kartu. Setelah itu $9 atau $19 per node, per bulan.
“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.
Mengapa ClawMetry ada
Setiap agen AI butuh tombol pemutus.
Ketika sistem otonom berulah, siapa yang memegang kendalinya? Inilah kisah di balik ClawMetry, dari dua film masa kecil hingga control plane yang independen.
Baca kisah sang pendiri →
❯ 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.
Terukur, satu pemasangan, empat bulan
Yang ditandai adalah agen yang mandek,
bukan agen yang mahal.
Sesi yang panjang dan mahal sering kali justru hasil kerja terbaik Anda, jadi alat yang memburu angka besar akan mematikan hal yang salah. ClawMetry melihat apakah sebuah agen benar-benar menghasilkan sesuatu. Laptop yang sama, empat bulan, kedua kasus berdampingan.
Bekerja · tidak pernah ditandai
$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.
Ditandai · mandek
$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.
Detektor memperingatkan. Detektor tidak bertindak. Ketujuh sesi itu berjalan sampai selesai. Penandaan adalah notifikasi, bukan pemicu. Tidak ada yang dihentikan kecuali seseorang menghentikannya, atau kecuali Anda sendiri menetapkan batas biaya dan sebuah agen melewatinya.
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.
Lihat aksinya
Satu layar. Semua yang terjadi di seluruh agen Anda.
Celahnya ada di dalam tabel
Apa yang bisa kami lakukan, per runtime.
Setiap vendor di kategori ini bicara soal guardrail. Ini matriks lengkapnya, termasuk sel-sel yang kosong.
| Runtime | Amati | Blokir sebelum berjalan | Hentikan saat berjalan | Biaya dalam dolar |
|---|---|---|---|---|
| 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.
Blokir sebelum berjalan
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.
Hentikan saat berjalan
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.
Audit setelahnya
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.
Sebelum Anda menaruh daemon di laptop Anda
Apa dampaknya bagi mesin,
dan apa yang keluar darinya.
Diukur pada satu instalasi referensi: 165 sesi, 19.977 peristiwa. Bukan perkiraan.
Jejak sumber daya
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.
Apa persisnya yang keluar
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.
File lokal berupa teks biasa
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.
Redaksi gagal secara terbuka
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.
Node yang terhubung bisa dihentikan dari jarak jauh
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.
Tiga tempat untuk menjalankannya
Cloud itu opsional.
Selalu begitu.
Daemon menghitung ke dalam file DuckDB di disk Anda sendiri. Setelah itu, di mana dashboard berada adalah keputusan Anda, dan tarifnya sama apa pun pilihan Anda.
01 · Local only
Tidak ada yang keluar
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
Disegel sebelum keluar
$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
Infrastruktur Anda, 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
Tarif tidak berubah mengikuti jenis penerapan. Self-hosted seharga $19 per node per bulan atau $190 per node per tahun, persis seperti paket cloud, karena yang Anda bayar adalah perangkat lunaknya, bukan server kami. Yang berubah adalah siapa yang memegang data dan siapa yang menjalankan kontainer. Beli kunci self-hosted tanpa perlu bicara dengan siapa pun.
Satu tarif, satu meteran
Hitung angka Anda
sebelum bicara dengan siapa pun.
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.
Berapa biayanya untuk Anda
Hitung mesin yang akan menjalankan daemon, bukan orang yang akan melihatnya.
$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.
Untuk mereka yang memikul risikonya
Menjalankan ini di seluruh perusahaan.
Kuartal lalu para engineer Anda memasang Claude Code, Cursor, Codex dan Copilot. Tidak ada yang melalui pengadaan, dan semuanya memegang repo dan kunci Anda.
Tidak ada yang perlu dipasang ke dalam agen
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 adalah jawaban untuk 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.Cocok dengan jaringan yang sudah Anda miliki
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.Peluncuran ke seluruh armada masih manual saat ini
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.Pertanyaan yang selalu kami terima.
Bisakah memblokir sesuatu sebelum berjalan, atau hanya memberi tahu bahwa itu sudah berjalan?
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.
Apakah ini akan menghentikan agen saya sendiri?
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.
Apakah ini mengubah cara agen saya berjalan?
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.
Apa yang terjadi saat masa uji coba saya berakhir?
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.
Siapa di balik ini, dan apa yang terjadi jika kalian menghilang?
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.
Apakah ini akan lolos tinjauan keamanan?
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.