RAGLight and RAG-Boilerplate
These are competitors—both provide end-to-end RAG frameworks with configurable components (LLMs, embeddings, vector stores), but RAGLight emphasizes modularity and MCP integration while RAG-Boilerplate emphasizes advanced retrieval techniques (hybrid search, reranking) and orchestration (CrewAI), so teams would typically choose one based on their architectural priorities rather than use both together.
About RAGLight
Bessouat40/RAGLight
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.
RAGLight helps you quickly build a chatbot that can answer questions using your own documents, like PDFs, Word files, or code. You feed it your collection of files, and it produces a chat interface where you can ask questions and get answers grounded in your specific information. This is ideal for anyone who needs to quickly create a custom AI assistant that understands their unique knowledge base.
About RAG-Boilerplate
mburaksayici/RAG-Boilerplate
RAG boilerplate with semantic/propositional chunking, hybrid search (BM25 + dense), LLM reranking, query enhancement agents, CrewAI orchestration, Qdrant vector search, Redis/Mongo sessioning, Celery ingestion pipeline, Gradio UI, and an evaluation suite (Hit-Rate, MRR, hybrid configs).
This system helps developers build sophisticated AI applications that can 'chat' with custom data. It takes raw text documents, processes them using advanced chunking and search techniques, and allows users to ask questions and receive answers based on the content. The target user is a software developer or AI engineer looking to create conversational AI experiences over domain-specific information.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work