Docling alternatives.
Docling: Turns documents into clean text for AI. Here are other rag & document parsing tools, most-starred first.
| Tool | What it does | Licence | GitHub stars |
|---|---|---|---|
| MarkItDown | Convert files and Office docs to markdown. | MIT | 190,405 |
| RAGFlow | Deep-document RAG engine with a UI. | Apache-2.0 | 92,283 |
| PaddleOCR | OCR and document parsing toolkit. | Apache-2.0 | 91,178 |
| MinerU | Converts complex PDFs to markdown or JSON. | Other | 81,815 |
| AnythingLLM | All-in-one desktop app for chat with your docs. | MIT | 67,160 |
| Meilisearch | Fast search engine with hybrid vector search. | Other | 59,577 |
| Marker | Fast, accurate PDF-to-markdown converter. | Apache-2.0 | 40,473 |
| LightRAG | Simple, fast graph-based RAG. | MIT | 40,153 |
| Qdrant | High-performance vector database. | Apache-2.0 | 35,085 |
| Chroma | Open-source embedding database. | Apache-2.0 | 29,510 |
| pgvector | Vector search inside Postgres. | Other | 23,371 |
| LanceDB | Embedded multimodal vector database. | Apache-2.0 | 11,680 |
Stars are a popularity signal, not a quality score. Gap Scores come after our Mac Studio tests.
# Docling alternatives URL: https://insidethemachine.ai/alternatives/docling Docling: Turns documents into clean text for AI. Better input means better answers from your docs. Category: RAG & document parsing. Sorted by GitHub stars (checked 2026-10-15). | name | what | licence | stars | md | |---|---|---|---|---| | MarkItDown | Convert files and Office docs to markdown. | MIT | 190405 | https://insidethemachine.ai/setups/markitdown.md | | RAGFlow | Deep-document RAG engine with a UI. | Apache-2.0 | 92283 | https://insidethemachine.ai/setups/ragflow.md | | PaddleOCR | OCR and document parsing toolkit. | Apache-2.0 | 91178 | https://insidethemachine.ai/setups/paddleocr.md | | MinerU | Converts complex PDFs to markdown or JSON. | Other | 81815 | https://insidethemachine.ai/setups/mineru.md | | AnythingLLM | All-in-one desktop app for chat with your docs. | MIT | 67160 | https://insidethemachine.ai/setups/anythingllm.md | | Meilisearch | Fast search engine with hybrid vector search. | Other | 59577 | https://insidethemachine.ai/setups/meilisearch.md | | Marker | Fast, accurate PDF-to-markdown converter. | Apache-2.0 | 40473 | https://insidethemachine.ai/setups/marker.md | | LightRAG | Simple, fast graph-based RAG. | MIT | 40153 | https://insidethemachine.ai/setups/lightrag.md | | Qdrant | High-performance vector database. | Apache-2.0 | 35085 | https://insidethemachine.ai/setups/qdrant.md | | Chroma | Open-source embedding database. | Apache-2.0 | 29510 | https://insidethemachine.ai/setups/chroma.md | | pgvector | Vector search inside Postgres. | Other | 23371 | https://insidethemachine.ai/setups/pgvector.md | | LanceDB | Embedded multimodal vector database. | Apache-2.0 | 11680 | https://insidethemachine.ai/setups/lancedb.md |