# magicrew/doc7

Turn documents into AI-ready Markdown with visual understanding

Repository: https://github.com/magicrew/doc7
Canonical: https://ross.abutalabs.com/products/doc7
Language: Go
License: MIT
License Family: permissive
Topics: document-ai, docx-to-markdown, local-ai, markdown, multimodal, open-source, pdf-to-markdown, vision-language-model
Last push: 2026-08-07T12:08:40+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 96, longevity 2
- inputs: {"age_days": 31, "days_push": 26, "days_rel": 26, "gap_med": 2.0, "n_releases_24m": 3}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1173, forks 47 (observed 2026-08-28T04:03:51.949416+00:00)

## What it is
doc7 is a Go CLI tool that converts PDFs, Office files, scans, screenshots, charts, formulas, and diagrams into AI-ready Markdown using any OpenAI-compatible multimodal vision-language model, including local deployments via Ollama or LM Studio. It requires no OCR stack and rebuilds multi-page documents into a single searchable Markdown output.

## Use cases
- convert pdf to markdown for llm ingestion
- extract text from scanned pdfs without ocr
- prepare documents for rag pipelines
- convert docx to markdown
- parse charts and formulas from pdfs into markdown
- run document conversion locally with a private vision model

## When to choose
- you need AI-ready Markdown from complex or raster-only documents
- you want local/private processing with your own multimodal model
- you want to avoid OCR stacks or per-page document-parser fees
- you need to preserve figures, equations, and layout structure in Markdown

## When to avoid
- you need a pure-text extraction pipeline with no LLM dependency
- you have no access to an OpenAI-compatible multimodal model endpoint
- you need pixel-perfect fidelity to original document formatting
- you need batch conversion at scale with minimal compute cost

## Facets
- artifact type: cli-tool
- maturity: active
- function: ocr, pdf, markdown, image-processing, llm-inference, nlp
- domain: pdf, files, developer-tools, artificial-intelligence, large-language-models
- platform: cli, windows, cross-platform, go
- tags: document-ai, pdf-to-markdown, docx-to-markdown, vision-language-model, multimodal, local-ai, openai-compatible, rag-preprocessing, macos, linux

## Member repositories
- magicrew/doc7 (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:51.949416+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 2026-08-30T06:28:23.826884+00:00, confidence not recorded.
  - readme: https://github.com/magicrew/doc7 (fetched 2026-08-28T04:03:51.949416+00:00, sha 33f4274d1d1e)
- Data as of 2026-08-30T08:39:29.467469+00:00.