agent-run-ledger is an open-source, local-first infrastructure tool for AI developers and researchers. It provides a verdict layer for AI coding-agent runs, including graded repair receipts and loop-gating exit codes. The tool operates without outbound network code and offers an optional local dashboard for monitoring agent activity.
agent-run-ledger sits in PulseGate's Other AI category. It focuses on tracking and verifying the outcomes of AI coding-agent runs locally without network dependencies. agent-run-ledger is an open-source project aimed at AI developers and researchers working with coding agents. agent-run-ledger is open source under the FSL-1.1-ALv2 license. It runs on the command line, and it can be self-hosted.
huyn7539 builds and maintains agent-run-ledger, and it first shipped in 2026. Among its 6 catalogued features are verdict layer, repair receipts, and loop-gating exit codes.
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