martin-loop: MartinLoop is a governance layer for AI coding loops that enforces budget caps, verifier gates, rollback evidence, and audit trails. It prevents unbounded retries by stopping unsafe or uneconomical work before execution, providing visibility and accountability for autonomous coding agents.; systemprompt-template: This repository is the evaluation template for systemprompt.io, a self-hosted AI governance platform. It provides a single Rust binary that handles inference, auditing, evals, and tool calls across your AI fleet. With native integration for Claude Cowork, it works with any agent, model, or provider, and every request lands on infrastructure you operate.
Bounding AI agent retry loops with budget and safety constraints
Enterprise AI governance and compliance