Deterministic pre-execution gate for AI agents (fail-closed, YAML policy)
Deterministic execution boundary for AI agents. IFC enforcement at the sink. 5 frameworks. 50 attack vectors. Apache 2.0.
A deterministic three-state stop controller. Constraint-first design through executable clarity.
Core execution boundary engine (decision + proof + ledger)
Small, deterministic control primitives for software systems. Testable, auditable bricks.
Transport-layer application profile for Execution Boundary Core Spec.
Admissibility Rotation Corridor — closed constitutional runtime with visible interrupt geometry
Deterministic execution boundary for AI systems enforcing signed approvals, replay protection, and cryptographic receipts.
A deterministic admissibility layer for interpretation proposals before verdict and execution.
Execution boundary for GitHub pull requests that interprets repository mutations before CI enforcement.
Observability profile for Execution Boundary systems — OTel collector topology, semantic conventions, dashboards, alerts
Experiments showing where AI governance must physically stop execution.
AI Execution Boundary Standard (AEBS) - Pre-incident reference for execution governance
Entry point and architectural map for execution boundary research.
Minimal proof of execution-bound admissibility: no present-state proof at bind, no execution.
Minimal reference model for separating proposal, authorization, and execution in side-effecting systems.
Runtime commit gate for AI governance: no mutation without a valid DecisionRecord.
Add a description, image, and links to the execution-boundary topic page so that developers can more easily learn about it.
To associate your repository with the execution-boundary topic, visit your repo's landing page and select "manage topics."