Low-Code is an approach to application development that enables rapid application creation with minimal coding effort. However, as Low-Code applications scale, challenges related to documentation, maintainability, and technical debt become increasingly prevalent. Inadequate documentation hampers collaboration, maintenance, troubleshooting, and knowledge retention, particularly in agile development environments where documentation is often neglected. Fragmented knowledge, poor traceability, and missing documentation sources are the main challenges for low-code documentation. To address these issues, we developed CLAIR (Connecting Low-Code and Artificial Intelligence for RAG), which is an AI-driven documentation assistant that leverages a knowledge graph and an LLM-based Multi Agent System to generate on-demand, context-aware documentation for Low-Code applications. CLAIR was validated through expert evaluations and a series of test cases, demonstrating its ability to generate accurate, usable, and context-aware documentation. Therefore, our main contribution is a novel approach that combines knowledge graphs and LLMs to improve documentation processes. By bridging the gap between Low-Code application development and AI-driven automation, CLAIR sets the foundation for future advancements in intelligent Low-Code maintainability solutions.