ClawMetry is a live monitoring service for AI agents. It is presented as a way to see what agents are doing in real time, including spawned sub-agents, tool calls, and token usage, and it includes runaway-loop alerts intended to catch loops before they increase costs. It describes itself as an end-to-end encrypted product and offers a free start.
The product centers on live activity and cost tracking. Its dashboard shows every agent, session, and tool call as it happens, and it ties each token to the task that spent it. It also lists runaway-loop alerts and describes them as being caught and flagged before they blow the budget. The service says it works across 14 runtimes in one window: OpenClaw, NVIDIA NemoClaw, NanoClaw, PicoClaw, Claude Code, Codex, Cursor, Aider, Goose, OpenCode, Qwen, Hermes, Pi, and Deep Agents.
ClawMetry is available through a web-based sign-in flow. Users can continue with GitHub, continue with Google, or enter an email address to receive a verification code. The page also provides an API key after signup, followed by installation and connection steps using a shell script and a clawmetry connect command, and it says the same key works on all machines. A dashboard is available after connection.
The page mentions pricing only in the form of a prompt to view pricing and the statement that it is free to start. It also shows install and usage steps for connecting a machine to ClawMetry Cloud. On the page, the product is named ClawMetry and the content frames it as a tool for monitoring AI agent activity in real time.
ClawMetry sits in PulseGate's LLM eval & observability category. It focuses on providing visibility and control over AI agent operations, costs, and performance for developers and teams. It is built as a B2B product for AI developers, ML engineers, agent framework users. There is a free tier. It runs on the web and the command line.
ClawMetry first shipped in 2026. The project is developed in the open on GitHub with 381 stars and 2.1k commits in the last 90 days. Among its 8 catalogued features are real-time monitoring, token usage analytics, and runaway loop alerts. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do