工作原理 Cloud OpenInfer NemoClaw 路线图 增长 案例展示 定价 设备 博客 Mac 安装
New: the desk device, $49 →
实时可观测性，专为 AI 智能体 · 端到端加密 · 开源

掌握你的智能体正在做什么。 就在此刻。

你的 AI 智能体 会派生子智能体、消耗 token、调用工具。你看不到它们在做什么，也不知道自己在为什么买单。ClawMetry 为你实时呈现一切，将每个 token 关联到花费它的任务，并在失控循环拖垮预算之前发出预警。

支持 OpenClaw、NVIDIA NemoClaw 及其他 10 种运行时。 更多安装选项
预约演示 · 免费注册 · ▸ 工作原理？
📦 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.

❯ 用户评价

社区对 ClawMetry 的评价

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 上查看全部评论 ↗

❯ 快速开始

# 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?

搭建时需要帮助？
获取免费上手帮助 →
Worried about data leaving your machine?
How ClawMetry stays private →

看看实际效果

一块屏幕，尽览所有代理的动态。

clawmetry - flow
ClawMetry dashboard

你将获得

因为我们自己需要才打造。现在你不必自己动手了。

重头戏

抓住那个即将花掉 $400 的智能体，赶在它动手之前。

子 Agent 不断衍生子 Agent。一个失控循环就能让您的月度账单一夜之间翻 3 倍。ClawMetry 实时展示衍生树,在循环开始的那一刻立即标记("codex 正在循环,38 次工具调用,无进展"),并在 Agent 超出预算线时通知您。您的财务团队会感受到变化。

Sub-agent running

子智能体运行中

Sub-agent on completion

子智能体完成时

几秒内诊断卡住的智能体

渠道、网关、模型、工具、节点。全部互联互通，随事件实时更新。

削减你的 AI 账单，无需更换任何模型。

输入 token、输出 token、缓存命中、响应时间、每次调用成本。都是你真正需要的数据。

在客户发现之前掌握 cron 失败

cron 任务、服务正常运行时间、磁盘使用、活跃子智能体。一目了然。

审计智能体上周二做了什么

每个会话都有记录。时间线、工具调用、成本。回溯查看究竟发生了什么。

兼容你正在使用的智能体技术栈

接入 OpenClaw 的任务系统。一眼看清哪些智能体在处理哪些任务。

清楚每一笔花费来自哪个 Agent

按 Agent、按会话、按模型、按工具细分。在账单送达之前就掌握支出情况。

捕捉卡死循环和静默失败

标记陷入循环的 Agent、反复失败的工具调用,以及毫无进展的会话。在它们烧光您的预算之前。

OpenTelemetry 原生支持

将 ClawMetry 直接接入你现有的 OpenTelemetry 管道。我们在 /v1/traces 和 /v1/metrics 上接收标准 OTLP 追踪和指标。无需任何专有 SDK。

你在哪运行，它就在哪运行

只要 OpenClaw 能跑，ClawMetry 就能跑。笔记本、服务器、树莓派，统统不在话下。

AWS GCP Azure macOS Ubuntu Windows WSL Docker Kubernetes
+ 同样支持树莓派、Hostinger、Hetzner、Digital Ocean
Raspberry Pi Hostinger Hetzner Digital Ocean Debian

需要为你的团队部署吗？我们一天之内即可搞定。

托管部署、批量定价，以及为 10+ 节点集群提供的创始人直连通道。

🖥
托管部署
我们在你的整个集群中部署、配置并运维 ClawMetry。从第一天起，你就拥有全面的可见性。
🚀
99.9% 正常运行时间 SLA
具有合同约束的正常运行时间承诺，未达标即返还费用。状态发布于 status.clawmetry.com。
📈
10+ 节点批量定价
集群超过十个节点后即可享受定制定价。支持年度承诺、采购单计费和采购流程文档。
与创始人交流 →

保持关注

第一时间获取新功能、版本发布和不断壮大的 -metry 生态系统的最新动态。

常见问题

关于 ClawMetry 你需要了解的一切。

什么是 ClawMetry？

ClawMetry 是一款免费、开源的实时可观测性仪表盘，面向运行在 OpenClaw 上的 AI 智能体。它让你即时洞察 token 成本、cron 任务、子智能体活动、记忆文件变更和会话历史，全部集中在一个本地仪表盘中。

ClawMetry 是免费的吗？

是的,完全免费。ClawMetry 采用 MIT 许可证,在您的设备上本地运行。无云端依赖,无订阅。如果您之后连接可选的 ClawMetry Cloud,您的 Agent 对话会进行端到端加密,只有您能读取;成本、健康状态等简单汇总数据安全同步,为托管仪表板提供支持。

我该如何安装 ClawMetry？

运行 pip install clawmetry，然后执行 clawmetry。它会自动检测你的 OpenClaw 工作区，无需任何配置文件。整个安装大约只需 30 秒。

ClawMetry 监控哪些内容？

ClawMetry 监控每个会话和模型的 token 用量与成本、cron 任务状态与历史、子智能体的派生与结果、记忆文件变更（SOUL.md、MEMORY.md、AGENTS.md）、会话记录、渠道活动，以及实时的工具调用追踪。

ClawMetry 兼容 Claude、GPT-4 以及其他模型吗？

是的。ClawMetry 兼容你的 OpenClaw 智能体使用的任何模型，包括 Claude（Anthropic）、GPT-4（OpenAI）、Gemini（Google）等。它会自动按模型跟踪成本和 token 用量。

ClawMetry 与 LangSmith 或 Weights & Biases 有何不同？

LangSmith 和 W&B 是为 LLM 应用开发者打造的企业级平台。ClawMetry 则专为 OpenClaw 用户量身打造，它深入理解渠道、cron 任务、子智能体、记忆文件以及完整智能体运行时这些特有概念。它无需任何配置，30 秒即可在本地运行。

ClawMetry 对合规与运维团队来说安全吗？

是的。ClawMetry 完全在你自己的机器上运行，并为每一次工具调用、策略违规和子智能体操作保留完整的审计记录。由于没有任何会话记录离开你的网络，个人身份信息（PII）始终留在设备本地。数据负责人、合规和运维团队无需向任何供应商发送数据，即可查看每个智能体在何时、为何、做了什么。

ClawMetry 支持哪些操作系统？

ClawMetry 可运行于 Linux、macOS 和 Windows（通过 WSL）。它同样支持树莓派和其他 ARM 设备。需要 Python 3.8+ 以及一个正在运行的 OpenClaw 安装环境。