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.; agentic-ai: Agentic AI is a curated knowledge hub that aggregates the best projects, research, and resources on Agentic AI across 24 specialized domains. It provides easy navigation to domain-specific pages with focused posts and references. The repository is community-driven and welcomes contributions.
Bounding AI agent retry loops with budget and safety constraints
Researchers exploring Agentic AI methodologies and papers