# Nutlope/llama-ocr

Document to Markdown OCR library with Llama 3.2 vision

Repository: https://github.com/Nutlope/llama-ocr
Canonical: https://ross.abutalabs.com/products/llama-ocr
Homepage: https://llamaOCR.com/
Language: TypeScript
License Family: other
Last push: 2026-07-12T19:12:01+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 35, longevity 47
- inputs: {"age_days": 660, "days_push": 52, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2431, forks 231 (observed 2026-08-28T04:06:51.097706+00:00)

## What it is
An npm library that performs OCR by sending images to Llama 3.2 Vision models via Together AI and returns structured Markdown. It supports local and remote image files, with PDF support planned.

## Use cases
- convert receipt images to markdown
- extract text from images with a vision model
- turn scanned documents into markdown
- ocr images for free with llama 3.2
- parse image content into structured text

## When to choose
- you want image-to-markdown OCR via a hosted vision model
- you already use Together AI and want a simple Node.js API
- you need structured markdown output rather than raw text

## When to avoid
- you need fully offline or self-hosted OCR
- you need PDF support today
- you cannot send documents to a third-party API
- you need a production-hardened library with a license file and active maintenance

## Facets
- artifact type: library
- maturity: experimental
- function: ocr, nlp, machine-learning, llm-inference
- domain: computer-vision, developer-tools, files
- platform: cross-platform
- tags: vision-models, together-ai, markdown-conversion, document-parsing, llama, natural-language-processing, nodejs

## Member repositories
- Nutlope/llama-ocr (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:51.097706+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 2026-08-30T02:31:24.944890+00:00, confidence not recorded.
  - readme: https://github.com/Nutlope/llama-ocr (fetched 2026-08-28T04:06:51.097706+00:00, sha 6446d0664a8e)
  - homepage: https://llamaOCR.com/ (fetched 2026-08-29T10:12:55.786544+00:00, sha 8304a2393cc1)
  - registry_npm: https://registry.npmjs.org/llama-ocr (fetched 2026-08-29T10:12:55.807756+00:00, sha a05f4325133f)
- Data as of 2026-08-30T08:39:29.467469+00:00.