運作原理 Cloud OpenInfer NemoClaw 藍圖規劃 成長動能 案例展示 定價 部落格 Mac 安裝
即時可觀測性,專為 AI 代理 · 端對端加密 · 開源

掌握你的代理正在做什麼。 此時此刻。

你的 AI 代理 會衍生子代理、消耗 token、呼叫工具。你看不到它們在做什麼,也看不清自己付了什麼錢。ClawMetry 即時呈現一切,把每一個 token 對應到花費它的任務,並在失控迴圈拖垮預算之前就先發出警示。

支援 OpenClaw、NVIDIA NemoClaw 及另外 10 種執行環境。 更多安裝選項
📦 230k+ installs 🌍 123+ countries 337 on GitHub 🏆 #5 Product Hunt

Supported agent runtimes

使用者怎麼說

社群對 ClawMetry 的評價

查看全部
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.
在 Product Hunt 查看所有評論

快速開始

# 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?

實際運作一覽

一個畫面,掌握所有代理的即時動態。

clawmetry - flow
ClawMetry dashboard

你能獲得什麼

我們因為自己需要而打造,現在你不必再自己動手。

重磅功能

搶在代理花掉 $400 之前攔住它。

子代理會再生出子代理。一個失控的迴圈,你的月帳單一夜之間就翻三倍。ClawMetry 即時顯示生成樹,一鍵終止失控代理,並在代理超出預算線時通知你。你的財務團隊會注意到。

Sub-agent running

子代理執行中

Sub-agent on completion

子代理完成時

幾秒內診斷卡住的代理

頻道、閘道、模型、工具、節點。全部串接完成,隨事件即時更新。

削減 AI 帳單,無需更換模型。

輸入 token、輸出 token、快取命中、回應時間、每次呼叫成本。你真正需要的數字。

搶在客戶之前得知 cron 失敗

Cron 工作、服務正常運行時間、磁碟使用量、活躍子代理。一眼掌握。

稽核代理上週二做了什麼

每個工作階段皆有記錄。時間軸、工具呼叫、成本。回頭就能看清發生了什麼。

搭配你現有的代理技術堆疊

掛接 OpenClaw 的任務系統。掌握哪些代理正在處理哪些任務。

把成本分攤給正確的團隊

依工作階段、依模型、依工具。在帳單出現前就掌握你的支出。

捕捉幻覺與卡住的迴圈

標記動作幻覺、重複的工具呼叫失敗,以及陷入迴圈的代理。趁它們燒光你的預算之前。

OpenTelemetry 原生支援

將 ClawMetry 放入你現有的 OpenTelemetry 管線。我們在 /v1/traces 與 /v1/metrics 接收標準 OTLP 追蹤與指標。不需要專屬 SDK。

你在哪裡執行,它就在哪裡執行

OpenClaw 能跑的地方,ClawMetry 就能跑。筆電、伺服器、Raspberry Pi,全都行。

AWS GCP Azure macOS Ubuntu Windows WSL Docker Kubernetes
+ 也能在 Raspberry Pi、Hostinger、Hetzner、Digital Ocean 上執行
Raspberry Pi Hostinger Hetzner Digital Ocean Debian

團隊需要嗎?我們一天內就能幫你建置完成。

代管部署、量化定價,以及為 10+ 節點機群提供直通創辦人的聯絡管道。

🖥
代管部署
我們在你的整個機群上部署、設定並維運 ClawMetry。你從第一天起就擁有完整可視性。
🚀
99.9% 正常運行時間 SLA
合約保障的正常運行時間承諾,未達標即退費。狀態公布於 status.clawmetry.com。
📈
10+ 節點的量化定價
當機群超過十個節點時提供客製化定價。支援年度合約、採購單計費與採購文件流程。
與創辦人洽談

掌握最新消息

獲得新功能、版本發布,以及日益壯大的 -metry 生態系通知。

常見問題

關於 ClawMetry 你需要知道的一切。

什麼是 ClawMetry?

ClawMetry 是一款免費、開源的即時觀測儀表板,專為在 OpenClaw 上執行的 AI 代理打造。它讓你即時掌握 token 成本、cron 工作、子代理活動、記憶檔案變更與工作階段歷史,全部集中於單一本機儀表板。

ClawMetry 免費嗎?

是的,完全免費。ClawMetry 採用 MIT 授權,在你的機器上本機執行。沒有雲端依賴、沒有遙測、沒有訂閱。另外也提供選用的 ClawMetry Cloud 方案,適合想要代管多節點儀表板的團隊。

如何安裝 ClawMetry?

執行 pip install clawmetry,接著執行 clawmetry。它會自動偵測你的 OpenClaw 工作區,不需要設定檔。建置大約只要 30 秒。

ClawMetry 監控什麼?

ClawMetry 監控每個工作階段與模型的 token 用量與成本、cron 工作狀態與歷史、子代理的生成與結果、記憶檔案變更(SOUL.md、MEMORY.md、AGENTS.md)、工作階段逐字記錄、頻道活動,以及即時工具呼叫追蹤。

ClawMetry 能搭配 Claude、GPT-4 與其他模型嗎?

可以。ClawMetry 能搭配你的 OpenClaw 代理使用的任何模型,包括 Claude(Anthropic)、GPT-4(OpenAI)、Gemini(Google)等。它會自動追蹤每個模型的成本與 token 用量。

ClawMetry 與 LangSmith 或 Weights & Biases 有何不同?

LangSmith 與 W&B 是為 LLM 應用程式開發者打造的企業平台。ClawMetry 則是專為 OpenClaw 使用者量身打造,它理解頻道、cron 工作、子代理、記憶檔案與完整代理執行環境等特定概念。它能在 30 秒內以零設定本機執行。

ClawMetry 對於合規與維運團隊安全嗎?

是的。ClawMetry 完全在你自己的機器上執行,並為每一次工具呼叫、政策違規與子代理動作保留完整的稽核軌跡。個人識別資訊(PII)留在裝置上,因為沒有任何逐字記錄會離開你的網路。資料主管、合規與維運團隊可以檢視每個代理做了什麼、何時做、為何做,而無需將資料傳送給廠商。

ClawMetry 支援哪些作業系統?

ClawMetry 可在 Linux、macOS 與 Windows(透過 WSL)上執行。它也能在 Raspberry Pi 與其他 ARM 裝置上運作。需要 Python 3.8+ 以及一個運作中的 OpenClaw 安裝環境。