Bounded human-to-agent delegation with checkpointed execution, dual-bond accountability, and a local append-only transparency log.
-
Updated
May 25, 2026 - TypeScript
Bounded human-to-agent delegation with checkpointed execution, dual-bond accountability, and a local append-only transparency log.
Unit27 public protocol package for Authority-Reach-Delegation classification before AI agents receive tools, credentials, autonomy, or delegation rights.
Add a description, image, and links to the delegated-authority topic page so that developers can more easily learn about it.
To associate your repository with the delegated-authority topic, visit your repo's landing page and select "manage topics."