runworthy is a command-line tool that scans and grades code repositories for AI agent operations, evaluating them against the Agent Flight Rules (AFR). It orchestrates multiple open-source security scanners and provides plain-English verdicts to help developers and security engineers ensure compliance and operational safety. The tool is open source and designed for defensive agent development workflows.
runworthy is an Other AI product. It focuses on ensuring code repositories for AI agents comply with security and operational best practices through automated scanning and grading. runworthy is an open-source project aimed at AI agent developers and security engineers. The project is open source (MIT). It runs on the command line.
Behind runworthy is geofflava, and the product first shipped in 2026. The project is developed in the open on GitHub with 3 commits in the last 90 days. Across PulseGate's embedding index, runworthy has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are repo grading, security scanning, and plain-English verdicts.
Latest indexed changes and source events
Other apps tracked under the same category.
