Alternatives to Surya
A local OCR toolkit with layout analysis, reading order and table recognition in 90+ languages. The listings below can replace it for an important use case. Each note says what changes if you switch.
The original
Surya
A local OCR toolkit with layout analysis, reading order and table recognition in 90+ languages.
Replacements
Listings that take over the same core job as Surya.
olmOCR
Open-source toolkit that uses a vision language model to turn PDFs and scans into Markdown.
olmOCR uses a vision language model to turn PDFs and scans into Markdown, handling tables, equations and handwriting, with open Apache-licensed model and training code.
MinerU
A document parser that converts PDFs, Office files and scans into Markdown and JSON.
MinerU parses PDFs, Office files, EPUB and scans into Markdown and JSON with OCR, but uses a non-standard license and suits technical users.
Docling
Open source library that converts documents into AI-ready structured formats.
Docling is an MIT licensed library converting many document formats into structured output, focused on document conversion more than multilingual OCR.
Similar software
Related functionality, not a direct replacement.
AnythingLLM
A desktop AI app that answers questions about your own documents, with no account and no API key needed.
LocalGPT
A self-hosted tool for asking questions about your own documents using local language models.
Kotaemon
An open-source, self-hosted RAG app for chatting with your documents using local or hosted models.
PrivateGPT
A self-hosted API layer for building private AI applications on top of local language models.
