Runopsy is an open-source Python package for debugging and observability of AI agents. It traces agent runs to pinpoint the exact moment and cause of failures rather than just the final error state. Designed for developers building with LLMs, it supports root-cause analysis and integrates with existing agent frameworks.
runopsy sits in PulseGate's LLM eval & observability category. It focuses on debugging AI agent failures by identifying the exact point where a run started going wrong instead of just the final error. It is built as an open-source project for developers. runopsy is open source under the Apache-2.0 license. runopsy is available on the command line, and it can be self-hosted.
Behind runopsy is vahit19, and it first shipped in 2026. Development happens publicly on GitHub with 59 commits in the last 90 days. Among its 3 catalogued features are Root Cause Analysis, Agent Tracing, and Error Debugging. 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