agent-debug is an open-source CLI tool for diagnosing failures in AI agent workflows. It provides root cause analysis and actionable fix suggestions, helping AI developers and researchers debug and improve their agent systems.
agent-debug is a LLM eval & observability project. It focuses on diagnosing and resolving failures in AI agent workflows by providing actionable debugging insights. It is built as an open-source project for AI developers and researchers. agent-debug is open source under the MIT license. It runs on the command line.
Viktorsdb builds and maintains agent-debug, and it first shipped in 2026. The project is developed in the open on GitHub with 14 commits in the last 90 days. Key capabilities include root cause analysis, fix suggestions, and LLM debugging.
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