Paano ito gumagana Cloud OpenInfer NemoClaw Roadmap Traksyon Showcase Presyo Device Blog Mac I-install
New: the desk device, $49 →
Real-time na obserbasyon para sa AI agents · E2E Encrypted · Open Source

Alamin kung ano ang ginagawa ng iyong mga agent. Sa mismong sandaling ito.

Ang iyong AI agents ay gumagawa ng mga sub-agent, kumokonsumo ng token, at tumatawag ng mga tool. Hindi mo nakikita ang kanilang ginagawa o ang binabayaran mo. Ipinapakita sa iyo ng ClawMetry ang lahat sa real-time, iniuugnay ang bawat token sa gawaing gumastos nito, at nagbabala sa mga runaway loop bago maubos ang badyet.

Gumagana sa OpenClaw, NVIDIA NemoClaw + 10 pang mga runtime. Higit pang mga opsyon sa pag-install
Mag-book ng Demo · Mag-sign up nang libre · ▸ Paano ito gumagana?
📦 230k+ installs 🌍 123+ countries ⭐ 337 on GitHub 🏆 #5 Product Hunt

❯ Supported agent runtimes

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.

Peter Steinberger
Peter Steinberger OpenAI
Creator of OpenClaw and founder of PSPDFKit, now at OpenAI.
 Matt Van Horn
Matt Van Horn June · Weber
Co-founder of June, the smart oven acquired by Weber. ClawMetry contributor.
 Alex Krentsel
Alex Krentsel Google
Systems research engineer at Google and PhD student at UC Berkeley.
 Manoel Aranda Neto
Manoel Aranda Neto PostHog
Software engineer at PostHog, previously mobile SDKs at Sentry.
 Kody Kendall
Kody Kendall LlamaPress AI
Co-founder of LlamaPress AI, an open-source AI web-app builder.

❯ Sinasabi ng mga Tao

Ang sinasabi ng komunidad tungkol sa ClawMetry

Tingnan lahat →
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.
Tingnan lahat ng komento sa Product Hunt ↗

❯ Mabilis na Simula

# One command. That's it. 🦞
$ curl -fsSL https://clawmetry.com/install.sh | bash

macOS, Linux, Windows. The installer figures it out. · How does this stay private?

Kailangan ng tulong sa pag-setup?
Kumuha ng libreng tulong sa onboarding →
Worried about data leaving your machine?
How ClawMetry stays private →

Tingnan ito sa aksyon

Isang screen. Lahat ng nangyayari sa iyong mga agent.

clawmetry - flow
ClawMetry dashboard

Ang makukuha mo

Ginawa dahil kailangan namin ito. Ngayon, hindi mo na ito kailangang gawin mismo.

Ang pinakamalaki

Hulihin ang agent na malapit nang gumastos ng $400. Bago pa ito mangyari.

Nagsi-spawn ng sub-agents ang mga sub-agent. Isang masamang loop lang at 3x na ang buwanang bill mo paggising mo. Ipinapakita ng ClawMetry ang live spawn tree, fina-flag ang loop sa sandaling magsimula ito ("codex looping, 38 tool calls, no progress"), at pina-page ka kapag lumampas ang isang agent sa budget line. Mapapansin ito ng finance team mo.

Sub-agent running

Tumatakbo ang sub-agent

Sub-agent on completion

Natapos na ang sub-agent

Suriin ang naipit na agent sa ilang segundo

Mga channel, gateway, model, tool, node. Lahat ay konektado, nag-a-update habang nangyayari ang mga bagay.

Bawasan ang iyong AI bill. Nang hindi nagpapalit ng model.

Tokens papasok, tokens palabas, cache hits, oras ng pagtugon, gastos kada tawag. Mga numerong talagang kailangan mo.

Malaman ang isang cron failure bago pa ito malaman ng iyong customer

Mga cron job, service uptime, paggamit ng disk, aktibong sub-agent. Madaling tingnan.

I-audit ang ginawa ng agent noong Martes

Bawat session ay naka-log. Timeline, tool calls, gastos. Bumalik at tingnan kung ano ang nangyari.

Gumagana sa agent stack na ginagamit mo na

Kumokonekta sa task system ng OpenClaw. Tingnan kung aling agent ang nasa aling task.

Alamin kung aling agent ang gumastos

Bawat agent, bawat session, bawat model, bawat tool. Alamin ang ginagastos mo bago pa dumating ang invoice.

Hulihin ang mga stuck na loop at tahimik na pagkabigo

I-flag ang mga agent na stuck sa loop, paulit-ulit na pagkabigo ng tool call, at mga session na walang progreso. Bago nila maubos ang budget mo.

Likas sa OpenTelemetry

Idagdag ang ClawMetry sa iyong umiiral nang OpenTelemetry pipeline. Tumatanggap kami ng standard na OTLP traces at metrics sa /v1/traces at /v1/metrics. Walang kinakailangang proprietary SDK.

Tumatakbo kung saan ka tumatakbo

Kung tumatakbo ang OpenClaw doon, tumatakbo ang ClawMetry doon. Laptop, server, Raspberry Pi, kahit ano.

AWS GCP Azure macOS Ubuntu Windows WSL Docker Kubernetes
+ tumatakbo rin sa Raspberry Pi, Hostinger, Hetzner, Digital Ocean
Raspberry Pi Hostinger Hetzner Digital Ocean Debian

Kailangan mo ito para sa iyong team? I-se-set up namin ito sa loob ng isang araw.

Pinamamahalaang deployment, volume pricing, at direktang linya sa founder para sa mga fleet na may 10+ na node.

🖥
Pinamamahalaang deployment
Ide-deploy, ico-configure, at papatakbuhin namin ang ClawMetry sa buong fleet mo. Makukuha mo ang buong visibility mula sa unang araw.
🚀
99.9% uptime SLA
Kontraktwal na uptime commitment na may credit-back kung mabigo kami. Nakalathala ang status sa status.clawmetry.com.
📈
Volume pricing para sa 10+ na node
Custom na pricing kapag lumampas ang iyong fleet sa sampung node. Suportado ang annual commits, PO billing, at procurement paperwork.
Makipag-usap sa founder →

Manatiling updated

Maabisuhan tungkol sa mga bagong feature, release, at ang lumalagong -metry ecosystem.

Mga Madalas Itanong

Lahat ng kailangan mong malaman tungkol sa ClawMetry.

Ano ang ClawMetry?

Ang ClawMetry ay isang libre at open-source na real-time observability dashboard para sa mga AI agent na tumatakbo sa OpenClaw. Nagbibigay ito ng instant na visibility sa mga gastos sa token, cron job, aktibidad ng sub-agent, mga pagbabago sa memory file, at kasaysayan ng session, lahat sa iisang lokal na dashboard.

Libre ba ang ClawMetry?

Oo, lubusan. MIT licensed ang ClawMetry at tumatakbo nang lokal sa iyong machine. Walang cloud dependency, walang subscription. Kung ikokonekta mo sa bandang huli ang opsyonal na ClawMetry Cloud, ang mga pag-uusap ng iyong mga agent ay end-to-end encrypted kaya ikaw lang ang makakabasa sa mga ito, at ang mga simpleng kabuuan tulad ng gastos at health ay ligtas na nagsi-sync para paganahin ang hosted dashboard.

Paano ko ii-install ang ClawMetry?

Patakbuhin ang pip install clawmetry pagkatapos ay clawmetry. Awtomatiko nitong nade-detect ang iyong OpenClaw workspace, walang kinakailangang config file. Mga 30 segundo lang ang setup.

Ano ang minomonitor ng ClawMetry?

Minomonitor ng ClawMetry ang paggamit ng token at gastos kada session at model, status at kasaysayan ng cron job, mga spawn at resulta ng sub-agent, mga pagbabago sa memory file (SOUL.md, MEMORY.md, AGENTS.md), mga transcript ng session, aktibidad ng channel, at real-time na tool call traces.

Gumagana ba ang ClawMetry sa Claude, GPT-4, at iba pang model?

Oo. Gumagana ang ClawMetry sa anumang model na ginagamit ng iyong mga OpenClaw agent, tulad ng Claude (Anthropic), GPT-4 (OpenAI), Gemini (Google), at iba pa. Awtomatiko nitong tina-track ang gastos at paggamit ng token kada model.

Paano naiiba ang ClawMetry sa LangSmith o Weights & Biases?

Ang LangSmith at W&B ay mga enterprise platform na ginawa para sa mga developer ng LLM application. Ang ClawMetry ay partikular na ginawa para sa mga gumagamit ng OpenClaw, naiintindihan nito ang mga espesipikong konsepto ng channel, cron job, sub-agent, memory file, at ang buong agent runtime. Tumatakbo ito nang lokal sa loob ng 30 segundo nang walang config.

Ligtas ba ang ClawMetry para sa compliance at ops teams?

Oo. Tumatakbo ang ClawMetry nang buo sa sarili mong makina at nagpapanatili ng kumpletong audit trail ng bawat tool call, paglabag sa patakaran, at aksyon ng sub-agent. Ang Personally Identifiable Information (PII) ay nananatili sa device dahil walang transcript na lumalabas sa iyong network. Masusuri ng mga data leader, compliance, at ops team kung ano ang ginawa ng bawat agent, kailan, at bakit, nang hindi nagpapadala ng data sa isang vendor.

Anong mga operating system ang sinusuportahan ng ClawMetry?

Tumatakbo ang ClawMetry sa Linux, macOS, at Windows (sa pamamagitan ng WSL). Gumagana rin ito sa Raspberry Pi at iba pang ARM device. Nangangailangan ng Python 3.8+ at isang aktibong OpenClaw installation.