एजेंट बिल्डर कवरेज आपकी मशीन सेल्फ-होस्टेड मूल्य निर्धारण Cloud साइन इन डिवाइस दस्तावेज़ ब्लॉग शोकेस रोडमैप एंटरप्राइज़

आपकी मशीन पर चलता है · तभी काम करता है जब आप कहें

AI एजेंट्स के लिए
कंट्रोल प्लेन

  • हर एजेंट देखें।
  • हर कार्रवाई समझें।
  • जो नहीं होना चाहिए, उसे रोकें।

ClawMetry आपकी टीम में पहले से चल रहे 26 एजेंट रनटाइम पढ़ता है, Claude Code और Cursor से लेकर Codex और OpenClaw तक, सीधे उन्हीं फ़ाइलों से जो वे पहले से लिखते हैं। एजेंट में कुछ जोड़ने की ज़रूरत नहीं।

$ pip install clawmetry && clawmetry

7 दिन, हर रनटाइम, बिना कार्ड। उसके बाद $9 या $19 प्रति नोड, प्रति माह।

या डेस्कटॉप ऐप प्राप्त करें 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.

15चार महीनों में पकड़े गए मामले: 6 बिना प्रगति, 6 बार-बार टूल विफलता, 3 अटके हुए लूप
7 of 68Claude Code सेशन में कम से कम एक चेतावनी आई। न शोर, न दुर्लभ।
0कॉन्फ़िगरेशन की ज़रूरत। पहचान इंस्टॉल होते ही शुरू होती है और हर मिले रनटाइम को कवर करती है।

Supported agent runtimes

मापा गया, एक इंस्टॉल, चार महीने

यह उन एजेंट्स को फ़्लैग करता है जो अटक जाते हैं,
उन्हें नहीं जो पैसा खर्च करते हैं।

लंबा और महंगा सेशन अक्सर आपका सबसे बेहतरीन काम होता है, इसलिए बड़े आंकड़ों के पीछे भागने वाला टूल गलत चीज़ को खत्म कर देगा। ClawMetry यह देखता है कि एजेंट कुछ बना भी रहा है या नहीं। वही लैपटॉप, चार महीने, दोनों मामले आमने-सामने।

काम कर रहा है · कभी फ़्लैग नहीं हुआ

$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.

फ़्लैग किया गया · अटक रहा है

$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.

डिटेक्टर चेतावनी देते हैं। कार्रवाई नहीं करते। उन सातों सेशन पूरे चले। फ़्लैग एक सूचना है, ट्रिगर नहीं। कुछ भी तब तक नहीं रुकता जब तक कोई व्यक्ति उसे न रोके, या जब तक आप खुद खर्च की सीमा तय न करें और कोई एजेंट उसे पार न कर जाए।

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.

इसे काम करते देखें

एक स्क्रीन। आपके एजेंट्स में हो रहा सब कुछ।

clawmetry - overview
ClawMetry dashboard

कमियाँ तालिका में ही हैं

हर रनटाइम पर हम क्या कर सकते हैं।

इस श्रेणी का हर वेंडर गार्डरेल्स की बात करता है। यह पूरी मैट्रिक्स है, खाली खानों समेत।

रनटाइम निगरानी चलने से पहले रोकें बीच में बंद करें डॉलर में लागत
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

चलने से पहले रोकें

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.

बीच में बंद करें

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.

बाद में ऑडिट

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.

अपने लैपटॉप पर डेमन डालने से पहले

यह मशीन पर क्या असर डालता है,
और उससे बाहर क्या जाता है।

उसी लैपटॉप पर मापा गया, अनुमान नहीं।

फ़ुटप्रिंट

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.

बाहर क्या जाता है, ठीक-ठीक

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.

स्थानीय फ़ाइल प्लेनटेक्स्ट है

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.

रिडैक्शन विफल होने पर डेटा खुला रह जाता है

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.

जुड़े हुए नोड को दूर से बंद किया जा सकता है

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.

लोग क्या कहते हैं

ClawMetry के बारे में समुदाय क्या कह रहा है

सभी देखें
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.
Product Hunt पर सभी टिप्पणियाँ देखें

इसे चलाने की तीन जगहें

Cloud वैकल्पिक है।
हमेशा से था।

डेमन आपकी अपनी डिस्क पर एक DuckDB फ़ाइल में गणना करता है। उसके बाद डैशबोर्ड कहाँ रहे, यह आपका फ़ैसला है, और जो भी चुनें, दर वही रहती है।

01 · Local only

कुछ भी बाहर नहीं जाता

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

बाहर जाने से पहले सील

$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

आपका इंफ़्रास्ट्रक्चर, सिंगल टेनेंट

$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

डिप्लॉयमेंट बदलने से दर नहीं बदलती। सेल्फ-होस्टेड $19 प्रति नोड प्रति माह या $190 प्रति नोड प्रति वर्ष है, बिल्कुल Cloud प्लान की तरह, क्योंकि आप सॉफ़्टवेयर के लिए भुगतान कर रहे हैं, हमारे सर्वर के लिए नहीं। बदलता सिर्फ़ यह है कि डेटा किसके पास है और कंटेनर कौन चलाता है। किसी से बात किए बिना सेल्फ-होस्टेड की खरीदें

एक दर, एक मीटर

किसी से बात करने से पहले
अपना आंकड़ा खुद निकालें।

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.

आपकी लागत कितनी होगी

उन मशीनों को गिनें जिन पर डेमन चलेगा, उन लोगों को नहीं जो उसे देखेंगे।

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.

जोखिम जिनके ज़िम्मे है, उनके लिए

इसे पूरी कंपनी में चलाना।

आपके इंजीनियरों ने पिछली तिमाही में Claude Code, Cursor, Codex और Copilot इंस्टॉल कर लिए। इन्हें किसी ने खरीदा नहीं, और इन सबके पास आपका रेपो और आपकी कीज़ हैं।

एजेंट में कुछ भी इंस्टॉल नहीं करना पड़ता

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.

SSO का जवाब है सेल्फ-होस्टेड

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.

आपके मौजूदा नेटवर्क में फिट हो जाता है

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.

फ्लीट रोलआउट अभी मैनुअल है

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.

हर बार पूछे जाने वाले सवाल।

क्या यह किसी चीज़ को चलने से पहले रोक सकता है, या सिर्फ़ बता सकता है कि वह चल गई?

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 26 runtimes: OpenClaw, Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Cline, OpenHands, OpenCode, NVIDIA NemoClaw, Aider, Goose, n8n, Qwen, Devin, Antigravity, Grok, Hermes, Pi, Deep Agents, Kimi CLI, DeepSeek Harness, Exo, NanoClaw, PicoClaw and QM. 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.

क्या यह अपने आप मेरे एजेंट रोक देगा?

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.

क्या इससे मेरे एजेंट के चलने का तरीका बदलता है?

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.

मेरा ट्रायल खत्म होने पर क्या होगा?

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.

इसके पीछे कौन है, और अगर आप गायब हो गए तो क्या होगा?

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.

क्या यह सिक्योरिटी रिव्यू में पास होगा?

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.

जुड़े रहें

नई सुविधाओं, रिलीज़, और बढ़ते -metry इकोसिस्टम के बारे में सूचना पाएं।