Agent Builder کیوں گورننس کوریج آپ کی مشین سیلف ہوسٹڈ قیمتیں Cloud سائن اِن ڈیوائس دستاویزات بلاگ شوکیس روڈ میپ انٹرپرائز

آپ کی مشین پر چلتا ہے · صرف آپ کے کہنے پر کارروائی کرتا ہے

کنٹرول پلین
برائے AI ایجنٹس

  • ہر ایجنٹ دیکھیں۔
  • ہر کارروائی سمجھیں۔
  • جو نہیں ہونا چاہیے، اسے روکیں۔

آپ کی مشین میں پروسیسز کے لیے System Monitor موجود ہے۔ یہ AI ایجنٹس کے لیے ہے۔ جیسے ہی وہ چلتے ہیں خودکار طور پر پہچان لیے جاتے ہیں، ہر ٹوکن اُسی کام سے جُڑا ہوتا ہے جس نے اسے خرچ کیا، اور ہر بے قابو لُوپ بجٹ بگاڑنے سے پہلے نشان زد ہو جاتا ہے۔

ڈاؤن لوڈ کریں برائے Linux

مفت آزمائیں، کارڈ کی ضرورت نہیں۔ macOS (.dmg) Windows (.exe) Linux (.AppImage)

یا ٹرمینل سے انسٹال کریں

$ pip install clawmetry && clawmetry

7 دن، ہر رن ٹائم، کارڈ کے بغیر۔ اس کے بعد $9 یا $19 فی نوڈ، فی ماہ۔

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.

ClawMetry کیوں موجود ہے

ہر AI ایجنٹ کو ایک کِل سوئچ کی ضرورت ہے۔

جب کوئی خودمختار نظام بے قابو ہو جائے تو اسے کون روکے؟ ClawMetry کے پیچھے کی کہانی، بچپن کی دو فلموں سے لے کر ایک آزاد کنٹرول پلین تک۔

بانی کی کہانی پڑھیں →

Supported agent runtimes

ماپا گیا، ایک انسٹال، چار ماہ

یہ اُن ایجنٹس کی نشاندہی کرتا ہے جو رُک جائیں،
نہ کہ اُن کی جو پیسہ خرچ کریں۔

ایک طویل، مہنگا سیشن اکثر آپ کا بہترین کام ہوتا ہے، اس لیے بڑے اعداد کے پیچھے بھاگنے والا ٹول غلط چیز کو ختم کر دیتا۔ ClawMetry یہ دیکھتا ہے کہ ایجنٹ کچھ پیدا کر بھی رہا ہے یا نہیں۔ وہی لیپ ٹاپ، چار ماہ، دونوں صورتیں ساتھ ساتھ۔

کام کر رہا ہے · کبھی نشان زد نہیں ہوا

$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.

نشان زد · رُکا ہوا

$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.

ڈیٹیکٹر خبردار کرتے ہیں۔ کارروائی نہیں کرتے۔ اُن ساتوں سیشنز مکمل ہوئے۔ نشان ایک اطلاع ہے، کوئی ٹرگر نہیں۔ کچھ بھی نہیں روکا جاتا جب تک کوئی شخص خود نہ روکے، یا جب تک آپ خود اخراجات کی حد مقرر نہ کریں اور کوئی ایجنٹ اُس سے تجاوز نہ کرے۔

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.

اسے عمل میں دیکھیں

ایک اسکرین۔ آپ کے تمام ایجنٹس میں ہونے والی ہر چیز۔

clawmetry - agents
Every runtime on the machine with cost, owner, last seen and what it is doing right now.
مشین پر موجود ہر رن ٹائم، لاگت، مالک، آخری بار نظر آنے کا وقت اور ابھی کیا کر رہا ہے، سب ایک جگہ۔

خامیاں بھی اسی جدول میں ہیں

ہم فی رن ٹائم کیا کر سکتے ہیں۔

اس شعبے کا ہر وینڈر گارڈریلز کا دعویٰ کرتا ہے۔ یہ پورا میٹرکس ہے، خالی خانوں سمیت۔

رن ٹائم مشاہدہ چلنے سے پہلے روکیں دورانِ عمل ختم کریں ڈالر میں لاگت
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.

چلنے سے پہلے روکیں

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.

دورانِ عمل ختم کریں

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.

بعد میں آڈٹ

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.

اپنے لیپ ٹاپ پر ڈیمن رکھنے سے پہلے

یہ مشین کے ساتھ کیا کرتا ہے،
اور اس سے باہر کیا جاتا ہے۔

ایک ریفرنس انسٹال پر ماپا گیا: 165 سیشنز، 19,977 ایونٹس۔ تخمینہ نہیں۔

فٹ پرنٹ

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.

بالکل واضح طور پر، باہر کیا جاتا ہے

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.

مقامی فائل سادہ متن میں ہے

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.

ریڈیکشن ناکام ہو تو رسائی کھلی رہتی ہے

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.

منسلک نوڈ کو دور سے روکا جا سکتا ہے

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.

لوگ کیا کہتے ہیں

کمیونٹی ClawMetry کے بارے میں کیا کہہ رہی ہے

سب دیکھیں
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 پر تمام تبصرے دیکھیں

چلانے کے تین مقامات

Cloud اختیاری ہے۔
ہمیشہ سے تھا۔

ڈیمن آپ کی اپنی ڈسک پر ایک DuckDB فائل میں حساب کرتا ہے۔ اس کے بعد ڈیش بورڈ کہاں رہے، یہ آپ کا فیصلہ ہے، اور آپ جو بھی چنیں، قیمت وہی رہتی ہے۔

01 · Local only

کچھ باہر نہیں جاتا

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

باہر جانے سے پہلے سیل بند

$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

آپ کا انفراسٹرکچر، سنگل ٹیننٹ

$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

ڈیپلائمنٹ کے ساتھ قیمت تبدیل نہیں ہوتی۔ سیلف ہوسٹڈ $19 فی نوڈ فی ماہ یا $190 فی نوڈ فی سال ہے، بالکل Cloud پلان کی طرح، کیونکہ آپ سافٹ ویئر کی قیمت ادا کر رہے ہیں، ہمارے سرورز کی نہیں۔ فرق صرف یہ ہے کہ ڈیٹا کس کے پاس ہے اور کنٹینر کون چلاتا ہے۔ کسی سے بات کیے بغیر سیلف ہوسٹڈ کی خریدیں۔

ایک قیمت، ایک میٹر

کسی سے بات کرنے سے پہلے
اپنا حساب خود لگا لیں۔

7 days of Pro, every runtime, no card

$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.

آپ کی لاگت کتنی ہوگی

اُن مشینوں کو گنیں جن پر ڈیمن چلے گا، اُن لوگوں کو نہیں جو اسے دیکھیں گے۔

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.

اُن کے لیے جن پر خطرے کی ذمہ داری ہے

اسے پوری کمپنی میں چلانا۔

آپ کے انجینئرز نے پچھلی سہ ماہی میں Claude Code، Cursor، Codex اور Copilot انسٹال کیے۔ کسی نے انہیں باقاعدہ خریدا نہیں، اور اُن سب کے پاس آپ کی ریپو اور آپ کی کیز ہیں۔

ایجنٹ میں کچھ بھی انسٹال کرنے کی ضرورت نہیں

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 کا جواب سیلف ہوسٹنگ ہے

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.

یہ آپ کے موجودہ نیٹ ورک کے ساتھ چل جاتا ہے

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.

فلیٹ رول آؤٹ فی الحال دستی ہے

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 roles beyond owner and member, SOC 2 and data residency.

وہ سوالات جو ہر بار پوچھے جاتے ہیں۔

کیا آپ کسی چیز کو چلنے سے پہلے روک سکتے ہیں، یا صرف بتاتے ہیں کہ وہ چل چکی؟

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.

کیا یہ خود سے میرے ایجنٹس بند کر دے گا؟

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.

کیا اس سے میرے ایجنٹس کے چلنے کا طریقہ بدلتا ہے؟

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.

میرا ٹرائل ختم ہونے پر کیا ہوگا؟

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.

اس کے پیچھے کون ہے، اور اگر آپ غائب ہو گئے تو کیا ہوگا؟

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.

کیا یہ سیکیورٹی ریویو میں پاس ہو جائے گا؟

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.

باخبر رہیں

نئے فیچرز، ریلیزز، اور بڑھتے ہوئے -metry ایکو سسٹم کے بارے میں اطلاع پائیں۔