agenteval-debugger is an MIT-licensed Python package for debugging AI agent executions. It provides tracing and observability capabilities for learners and developers working with agent workflows such as LangGraph.
In the LLM eval & observability space, agenteval-debugger takes a focused approach. It focuses on debugging and understanding the execution traces of AI agent workflows. It is built as an open-source project for AI developers and learners. agenteval-debugger is open source under the MIT license. It ships for the command line, and it can be self-hosted.
Behind agenteval-debugger is Xhan-985, and it first shipped in 2026. The project is developed in the open on GitHub with 35 commits in the last 90 days. Among its 4 catalogued features are agent tracing, execution debugging, and observability.
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