Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Aojie Yuan, Haiyue Zhang, Ziyi Wang, Yue Zhao

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.

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

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.
Paper Structure (27 sections, 1 equation, 12 figures, 2 tables)

This paper contains 27 sections, 1 equation, 12 figures, 2 tables.

Table of Contents

  1. Introduction
  2. System Overview and Threat Model
  3. Charter: Constitutional Governance
  4. CEO: Goal Decomposition via Strategist
  5. CFO: Fiscal Gatekeeping via Treasury
  6. Auction and Worker Selection.
  7. TrustScore and SovereignAuth
  8. Auditor: ReviewEngine and Audit Trail
  9. Proof Hash.
  10. Feedback Loop.
  11. Evaluation
  12. Axis 1: Fiscal Governance
  13. Axis 2: TrustScore Permission Gating
  14. Axis 3: Audit Trail Integrity
  15. Limitations.
  16. ...and 12 more sections

Figures (12)

  • Figure 1: Sovereign-OS five-layer architecture. The Charter defines mission scope, fiscal boundaries, and success KPIs. The CEO (Strategist) decomposes goals into task DAGs mapped to Charter competencies. The CFO (Treasury) enforces budget approval, daily burn caps, and job profitability floors. Workers execute tasks subject to TrustScore-gated permissions (SovereignAuth). The Auditor (ReviewEngine) evaluates outputs against KPI verification prompts and produces SHA-256-hashed AuditReports. An append-only UnifiedLedger records all financial and token flows.
  • Figure 2: Sovereign-OS web dashboard showing mission status, worker activity, job queue, and audit trail after the end-to-end case study.
  • Figure 3: Command Center (main dashboard). Shows the Mission input, Task DAG with status badges (pending $\rightarrow$ running $\rightarrow$ passed/failed), Decision Stream with CEO/CFO/Audit events, Token Usage table, Job Queue, and top-bar summary (Charter, Balance, Tokens, TrustScore, Health).
  • Figure 4: Worker registry (Configure Skills). Lists all 16+ registered worker types with name, description, priority weight, and code status. New skills can be added and auto-generated via LLM when an API key is configured.
  • Figure 5: Charter editor. Operators configure the constitutional governance document: mission statement, daily burn limit (USD), maximum budget cap, and currency. Changes are persisted to the Charter YAML file.
  • ...and 7 more figures