{"id":"rag-anything","name":"RAG-Anything","maker":"HKUDS","url":"https://github.com/HKUDS/RAG-Anything","repo":"HKUDS/RAG-Anything","package":"pypi:raganything","summary":"A framework built on LightRAG that handles text, images, tables and equations in documents for retrieval.","details":"RAG-Anything parses mixed-content documents, such as PDFs and Office files, and builds a graph and index over all content types. It is a Python library that depends on LightRAG and runs locally with a configured model provider.","open_source":true,"hosted":false,"also":["documents"],"verified":"2026-11-15","category":"retrieval","category_name":"Vector databases and retrieval","page":"https://modelmoot.com/tools/rag-anything","reviewed":"2026-11-15","checked":{"at":"2026-11-15T16:10:15.342Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}