Clawmetry

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

LLM Mart
13 views 125 listing impressions

ClawMetry is a control plane for AI agents that discovers, observes, and governs AI agents across multiple runtimes. It supports 32 AI agent runtimes, including Claude Code, Cursor, OpenAI Codex, and GitHub Copilot. ClawMetry reads the session stores that supported agents already write, requiring no SDK and no change to how agents run.

It offers governance features like approvals, budgets, and a kill switch, which are off by default and opt-in. ClawMetry can be installed on a machine to find agent runtimes and display sessions, sub-agents, and tool calls. The tool includes a free tier for monitoring agents on a single machine, with team and enterprise plans available.

It integrates with MCP, OpenTelemetry, custom ingest, and alert destinations, with enterprise SIEM export. ClawMetry is open source and has been featured as a top product on Product Hunt.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Comments (0)

Sign in to join the conversation.

No comments yet.

Related tools