← back to the directory
Library / SDK Retrieval & Memory

Surya

1Multilingual 2OCR 3toolkit 4for 5document 6layout

the six Ws · specification

W1 Who

Vik Paruchuri, creator of Marker, released Surya through his company Datalab.

W2 What

Surya is an OCR and document analysis toolkit that performs text detection, recognition across 90-plus languages, layout analysis, reading order, and table recognition.

W3 Where

Hosted on GitHub at VikParuchuri/surya and distributed as the surya-ocr Python package.

W4 When

Released in January 2024, with continued updates through 2025.

W5 Why

It gives developers a single open pipeline for accurate multilingual OCR and layout parsing, feeding tools like Marker.

W6 With

Runs on PyTorch and installs via pip as surya-ocr.

W7 Watch

Released under the GPL-3.0 license, with a separate commercial license available from Datalab for closed-source use; released by Datalab.

OCRdocument layouttable recognitionmultilingual

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.