Deterministic execution authorization for AI agents
-
Updated
Mar 24, 2026 - TypeScript
Deterministic execution authorization for AI agents
Self-describing message protocol with immutable, replayable history for human-agent collaboration. Types and authority rules live in the append-only log—state reconstructed from cryptographically sealed messages.
Add a description, image, and links to the authorization-protocol topic page so that developers can more easily learn about it.
To associate your repository with the authorization-protocol topic, visit your repo's landing page and select "manage topics."