LLMling is a framework for declarative LLM application development that emphasizes resource management, prompt templates, and tool execution. It provides a YAML-based configuration system for defining LLM environments, custom MPC servers, and AI agents. The core concepts include static declarations in YAML, adherence to the Machine Chat Protocol (MCP) for standardized LLM interaction, and the use of component types like resources (content providers), prompts (message templates), and tools (Python functions callable by the LLM). It is built with modern Python features, fully typed, and pydantic-based.