Agent Builder Phạm vi hỗ trợ Máy của bạn Tự vận hành Bảng giá Cloud Đăng nhập Thiết bị Tài liệu Blog Giới thiệu Lộ trình Doanh nghiệp

Chạy trên máy của bạn · chỉ hành động khi bạn cho phép

Trung tâm điều khiển
dành cho AI Agent

  • Thấy mọi agent.
  • Hiểu mọi hành động.
  • Chặn những gì không nên xảy ra.

ClawMetry đọc 26 runtime agent mà đội của bạn đang chạy, từ Claude Code và Cursor đến Codex và OpenClaw, trực tiếp từ những tệp mà chúng vốn đã ghi ra. Không cần thêm gì vào agent.

$ pip install clawmetry && clawmetry

7 ngày, đủ mọi runtime, không cần thẻ. Sau đó $9 hoặc $19 mỗi node, mỗi tháng.

Hoặc tải ứng dụng máy tính 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.

15lượt phát hiện trong bốn tháng: 6 không tiến triển, 6 lỗi công cụ lặp lại, 3 kẹt vòng lặp
7 of 68phiên Claude Code có ít nhất một cảnh báo. Không ồn ào, cũng không hiếm gặp.
0cấu hình cần thiết. Việc phát hiện bắt đầu ngay khi cài và bao trùm mọi runtime tìm thấy.

Supported agent runtimes

Đo thực tế, một lần cài, bốn tháng

Nó cảnh báo agent bị đứng,
không phải agent tốn tiền.

Một phiên dài và tốn kém thường lại là phần việc tốt nhất của bạn, nên công cụ chỉ săn các con số lớn sẽ giết nhầm mục tiêu. ClawMetry xem agent có thật sự tạo ra kết quả hay không. Cùng một chiếc laptop, bốn tháng, hai trường hợp đặt cạnh nhau.

Đang chạy tốt · chưa từng bị cảnh báo

$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.

Bị cảnh báo · đang đứng im

$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.

Bộ phát hiện chỉ cảnh báo. Chúng không hành động. Cả bảy phiên đó đều chạy đến khi hoàn tất. Cảnh báo là một thông báo, không phải một cò súng. Không có gì bị dừng trừ khi có người dừng nó, hoặc trừ khi chính bạn đặt hạn mức chi tiêu và một agent vượt qua mức đó.

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.

Xem nó hoạt động

Một màn hình. Mọi thứ đang diễn ra trên tất cả các agent của bạn.

clawmetry - flow
ClawMetry dashboard

Những lỗ hổng đều nằm trong bảng

Chúng tôi làm được gì, trên từng runtime.

Nhà cung cấp nào trong lĩnh vực này cũng nói về rào chắn an toàn. Đây là toàn bộ ma trận, kể cả những ô còn trống.

Runtime Quan sát Chặn trước khi chạy Dừng giữa chừng Chi phí bằng đô la
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

Chặn trước khi chạy

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.

Dừng giữa chừng

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.

Kiểm tra sau

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.

Trước khi bạn đưa một daemon lên laptop

Nó tác động gì đến máy,
và những gì rời khỏi máy.

Đo trên chính chiếc laptop đó, không phải ước lượng.

Mức chiếm dụng

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.

Chính xác những gì rời đi

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.

Tệp cục bộ ở dạng văn bản thuần

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.

Việc che dữ liệu có thể bỏ sót

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.

Một node đã kết nối có thể bị dừng từ xa

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.

Mọi người nói gì

Cộng đồng đang nói gì về ClawMetry

Xem tất cả
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.
Xem tất cả bình luận trên Product Hunt

Ba nơi để chạy

Cloud là tùy chọn.
Vốn luôn như vậy.

Daemon tính toán và ghi vào một tệp DuckDB trên ổ đĩa của chính bạn. Sau đó bảng điều khiển đặt ở đâu là quyền của bạn, và giá vẫn như nhau dù bạn chọn cách nào.

01 · Local only

Không có gì rời đi

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

Được niêm phong trước khi rời đi

$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

Hạ tầng của bạn, một khách hàng duy nhất

$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

Giá không thay đổi theo cách triển khai. Tự vận hành là $19 mỗi node mỗi tháng hoặc $190 mỗi node mỗi năm, đúng như gói Cloud, vì bạn trả tiền cho phần mềm chứ không phải cho máy chủ của chúng tôi. Thứ thay đổi là ai giữ dữ liệu và ai vận hành container. Mua khóa tự vận hành mà không cần trao đổi với ai.

Một mức giá, một cách tính

Tự tính ra con số của bạn
trước khi phải trao đổi với ai.

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.

Chi phí của bạn

Đếm số máy sẽ chạy daemon, không phải số người sẽ xem bảng điều khiển.

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.

Dành cho những người gánh rủi ro

Triển khai trên toàn công ty.

Quý vừa rồi, kỹ sư của bạn đã cài Claude Code, Cursor, Codex và Copilot. Không ai mua sắm chính thức, và tất cả chúng đều có repo và khóa của bạn.

Không cần cài gì vào 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.

Tự lưu trữ chính là câu trả lời cho 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.

Phù hợp với hạ tầng mạng bạn đang có

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.

Triển khai theo fleet hiện vẫn phải làm thủ công

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.

Những câu hỏi lần nào cũng gặp.

ClawMetry chặn được trước khi chạy, hay chỉ báo là đã chạy?

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.

Nó có tự ý dừng agent của tôi không?

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.

Nó có làm thay đổi cách agent của tôi chạy không?

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.

Hết thời gian dùng thử thì sao?

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.

Ai đứng sau dự án này, và nếu các bạn biến mất thì sao?

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.

Sản phẩm này có qua được vòng thẩm định bảo mật không?

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.

Luôn cập nhật tin tức

Nhận thông báo về các tính năng mới, bản phát hành, và hệ sinh thái -metry đang phát triển.