Sovereign-OS: A Charter-Governed Operating System for Autonomous AI Agents with Verifiable Fiscal Discipline

TL;DR

Sovereign-OS is a governance-centric operating system designed for autonomous AI agents, enforcing fiscal discipline, permissions, and auditability through a declarative Charter and cryptographic verification, ensuring reliable and compliant agent behavior.

Contribution

It introduces a novel OS framework that integrates constitutional governance, fiscal constraints, permission management, and tamper-evident audits for autonomous AI agents, enhancing trust and compliance.

Findings

Blocks 100% of fiscal violations in tested scenarios

Achieves 94% correct permission gating

Maintains zero integrity failures over 1,200+ audits

Abstract

As AI agents evolve from text generators into autonomous economic actors that accept jobs, manage budgets, and delegate to sub-agents, the absence of runtime governance becomes a critical gap. Existing frameworks orchestrate agent behavior but impose no fiscal constraints, require no earned permissions, and offer no tamper-evident audit trail. We introduce Sovereign-OS, a governance-first operating system that places every agent action under constitutional control. A declarative Charter (YAML) defines mission scope, fiscal boundaries, and success criteria. A CEO (Strategist) decomposes goals into dependency-aware task DAGs; a CFO (Treasury) gates each expenditure against budget caps, daily burn limits, and profitability floors via an auction-based bidding engine; Workers operate under earned-autonomy permissions governed by a dynamic TrustScore; and an Auditor (ReviewEngine) verifies outputs against Charter KPIs, sealing each report with a SHA-256 proof hash. Across our evaluation suite, Sovereign-OS blocks 100% of fiscal violations (30 scenarios), achieves 94% correct permission gating (200 trust-escalation missions), and maintains zero integrity failure over 1,200+ audit reports. The system further integrates Stripe for real-world payment processing, closing the loop from task planning to revenue collection. Our live demonstration walks through three scenarios: loading distinct Charters to observe divergent agent behavior, triggering CFO fiscal denials under budget and profitability constraints, and escalating a new worker's TrustScore from restricted to fully authorized with on-the-spot cryptographic audit verification.