# facebookresearch/nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

Repository: https://github.com/facebookresearch/nougat
Canonical: https://ross.abutalabs.com/products/nougat
Homepage: https://facebookresearch.github.io/nougat/
Language: Python
License: MIT
License Family: permissive
Last push: 2025-02-21T16:38:00+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 7, release rhythm 8, longevity 84
- inputs: {"age_days": 1183, "days_push": 558, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10063, forks 634 (observed 2026-08-28T04:10:39.401698+00:00)

## What it is
Nougat is Meta's neural OCR model that parses academic PDFs into structured Markdown, understanding LaTeX math and tables. It ships as a Python library with a CLI and optional API server.

## Use cases
- convert academic pdfs to markdown
- extract latex math from pdf papers
- ocr scientific documents with tables
- parse research papers into text
- digitize pdfs with equations
- batch convert pdf directory to markdown

## When to choose
- you need math and table extraction from academic PDFs
- you want Markdown output rather than plain OCR text
- you have a GPU for faster inference

## When to avoid
- you need general-purpose OCR for non-academic documents
- you need lightweight CPU-only processing
- you need layout-preserving PDF conversion rather than Markdown

## Facets
- artifact type: library
- maturity: maintenance
- function: ocr, pdf, parser, machine-learning, deep-learning, cli
- domain: pdf, machine-learning, developer-tools
- platform: python, cli, cross-platform
- tags: academic-documents, latex-math, pdf-to-markdown, vision-transformer, facebook-research, natural-language-processing, gpu

## Member repositories
- facebookresearch/nougat (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:39.401698+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:19:53.518089+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/nougat (fetched 2026-08-28T04:10:39.401698+00:00, sha f3d0659027eb)
  - homepage: https://facebookresearch.github.io/nougat/ (fetched 2026-08-29T08:19:35.650843+00:00, sha bd099a4b7c37)
- Data as of 2026-08-30T08:39:29.467469+00:00.