What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks

Compiler-style pre-execution safety analysis for Harness shell actions.

Duc is a SQLite-based project-state format for physical-engineering work before execution.

Policy-Gated Governance for Operational AI Agents

Open AI Permit specification for pre-execution action authorization records

Deterministic pre-execution gate for AI agents (fail-closed, YAML policy)

A production-grade pre-execution authority layer that binds AI agent identity to deterministic state. Standard IdPs (Entra ID, Okta, OIDC) issue passport to your Agent, predicate-authority issues/revokes "work permit" to your Agent based on intent & state

Core execution boundary engine (decision + proof + ledger)

Pre-execution safety gate for AI agents. Evaluates proposed actions and returns allow, require_approval, revise_action, or block before execution.

Find blind spots before you build them. A multi-agent overnight research pattern for Claude Code that knows when not to run.

AI Admissibility Boundary reference surface for the external admit authority model and its proof meaning.

Deterministic pre-execution gate for one credentialed tool request: explicit policy, allow/deny decision, and inspectable decision artifact....verifiable receipts for multi-agent systems.

Transport-layer application profile for Execution Boundary Core Spec.

AI Code Safety Gate demo showing ALLOW, REQUIRE_APPROVAL, and BLOCK decisions for AI-generated code changes.

Implementation governed by the Aperture execution calculus

AI Execution Boundary Standard (AEBS) - Pre-incident reference for execution governance

Open-source pre-execution security for AI coding agents

The effect layer for AI-agent firewalls — simulate an action, get a canonical effect delta. Zero-dep, deterministic, fail-closed. 5 domains (fs, sql, shell, http, solana).

Local deterministic CLI for detecting policy/source conflicts before proposed agent actions.