#policy-as-code

Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-checked by an SMT solver (cvc5), every decision independently verifiable offline. Pure Rust.

The trust control plane for enterprise AI agents — real-time policy verdicts in under 800ms and litigation-grade evidence of every decision. Pharos decides. Pharos proves.

Policy-as-code admission controller for AI agent skills and MCP tools. SkillBOM, lockfiles, and supply-chain baselines.

A seatbelt for the AI acting on your systems — deterministic, open-source governance gate for AI-agent actions

Portable, deterministic controls for agent actions. Experimental open-source specification and reference implementation.

Policy layer for agent-authored pull requests. One .gatekeeper.yml decides what auto-merges, what escalates to a human, what gets grouped — and refuses forbidden writes before the code exists. Built for Sparkles.

GitHub Action + CLI for replayable CI/PR/release gate decisions - zero-config Self-Test turning checks, scanners, and AI-agent signals into deterministic, tamper-evident PASS/WARN/BLOCK records. Read-only, zero dependencies, Apache-2.0.

Legacy HouseNet component archive; canonical source: HouseNet-Projects/house-net