agent-chronicle is a Python package for recording and replaying agent decision graphs. It allows developers to capture LLM agent behavior in production, reproduce failures as committed regression tests, and re-run fixes without making live LLM calls. Built with support for OpenInference and OpenTelemetry, it is intended for teams building and maintaining reliable autonomous AI agents.
agent-chronicle is a Developer Tools product. It focuses on reproducing and debugging production failures in LLM agent decision-making without repeated live model inference calls. agent-chronicle is an open-source project aimed at developers. The project is open source (MIT). It runs on the command line.
Behind agent-chronicle is theagentplane, and the product first shipped in 2026. The project is developed in the open on GitHub with 33 commits in the last 90 days. Among its 4 catalogued features are record-replay, regression testing, and decision graph capture.
Latest indexed changes and source events
agent-chronicle verified by the PulseGate indexer
Other apps tracked under the same category.
