# Sovereign-OS

A governance layer for autonomous AI work where a single YAML file declares an agent's mission, spending limits and allowed capabilities, and every task is planned, budget-checked, audited and recorded.

A submitted goal flows from a Charter file through a planning stage, a budget-approval stage, execution by built-in workers, verification by an Auditor, and a record in an append-only Ledger that cannot be overridden at runtime. Every task is checked against the Charter's stated KPIs, with a cryptographic proof hash attached to every report and a TrustScore that drops whenever an audit fails.

Agents start sandboxed and earn additional capabilities, such as spending money, calling external APIs, or writing files, as their TrustScore rises, rather than being granted an all-or-nothing API key from the start. A built-in job queue with Stripe integration and webhook delivery on completion lets agent work be offered as a paid service. It runs self-hosted with the operator's own API keys, through Docker Compose or a command-line interface, and is written in Python.

Website: https://github.com/Justin0504/Sovereign-OS