Skip to content
AGENT GOVERNANCE

Secure Hybrid AI Hub

A local policy broker for scoped AI work, typed artifacts and verification evidence.

Secure Hybrid AI Hub actual command-line help
TECHNICAL REFERENCE
CURRENT SCOPE

Open-source policy broker · 257 tests passed in September

WHO IT'S FOR

Independent build

My experimental open-source policy broker. Real-client and end-to-end acceptance remain separate from its test evidence.

THE ENGINEERING

An experimental Python broker and CLI for governed Codex, Claude Code, VS Code and local Ollama workflows. Deterministic controls mediate scope, policy, artifacts and privileged transitions while models propose work. The September public snapshot recorded 257 passing tests with one expected private-dossier skip and Python 3.11–3.13 CI/security checks. The October review did not rerun those gates. Phase 1 closure, authority enforcement and end-to-end acceptance remain incomplete; real-client operation, browser/API delivery and distributed capacity retain separate gates.

PythonTyped artifactsPolicy broker

BEFORE → AFTER

Real problems from this build, what I changed and the verified result.

  1. CASE 01
    Before

    An unrestricted model could confuse a proposed action with permission to execute it.

    After

    Source verification with test data is recorded; complete authority enforcement and end-to-end acceptance remain open.

    How I fixed it

    Implemented a local broker with typed policy/task records and separately controlled privileged transitions.

  2. CASE 02
    Before

    Passing tests can be mistaken for real-client production readiness.

    After

    The September public snapshot recorded 257 passes and one expected private-dossier skip; the October review did not rerun those gates.

    How I fixed it

    Separated published baseline tests from Phase 1 closure and real-client acceptance gates.

Evidence reviewed: Source review October 14, 2026; verification dates and open gates stated above