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.; mcp-for-beginners: This curriculum introduces the Model Context Protocol (MCP), an elegant solution for AI applications to communicate with various tools and services in a standardized way. It offers hands-on practice in multiple programming languages, guiding beginners from fundamental concepts to building and deploying their own MCP servers and clients.
Bounding AI agent retry loops with budget and safety constraints
Building capable and flexible AI applications.