o11y-reflect is an open-source CLI tool that provides local-first telemetry and observability for AI coding agents such as Claude, Copilot, Gemini, and Cursor. It helps developers understand why agents fail, stall, or consume excessive resources by collecting actionable metrics and integrating with OpenTelemetry. Ideal for AI developers and researchers seeking deeper insights into agent behavior.
In the LLM eval & observability space, o11y-reflect takes a focused approach. It focuses on understanding and diagnosing failures or inefficiencies in AI coding agents by providing actionable telemetry. o11y-reflect is an open-source project aimed at AI developers and researchers. The project is open source (Apache-2.0). The product ships for the command line, and it can be self-hosted.
o11y-dev builds and maintains o11y-reflect, and the product first shipped in 2026. The project is developed in the open on GitHub with 106 commits in the last 90 days. Among its 5 catalogued features are telemetry collection, agent monitoring, and local-first storage.
Latest indexed changes and source events
Other apps tracked under the same category.
