chunky

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications. Maintained by GiovanniPasq on GitHub, where it has earned 161 stars from the community.

It's actively developed around chunking, rag, retrieval-augmented-generation, and is a solid reference for anyone building with these tools.