AltHub

microsoft/markitdown alternatives

document-to-Markdown conversion

Python tool to convert various files (PDF, Office, images, audio, HTML, etc.) to Markdown for LLM ingestion.

175.4kPythonMITactive · last push 4d agoGitHub

Drop-in peers

Same problem, same approach. Swapping one for another is a config change, not a rewrite.

docling-project/docling

drop-in Python library with broader format support and active development; choose for a robust alternative with similar integration.

Get your documents ready for gen AI

65.4k
Python
MIT
active2d ago
opendatalab/MinerU

Python library that converts PDFs and Office docs to LLM-ready markdown/JSON; choose for advanced PDF/OCR-heavy workflows.

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

78.2k
Python
NOASSERTION
active4d ago
firecrawl/anydoc

Rust library with Python bindings that converts office docs, PDFs, EPUB, etc. to markdown; choose for a fast, lightweight alternative.

Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.

17.8k
Rust
MIT
active2d ago

Same job, different approach

Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.

RoffyS/MarkEverythingDown

uses LLM-based conversion instead of deterministic parsing; choose if you want higher semantic fidelity at the cost of speed/cost.

Convert files (PDF, image, Word, PPT, Excel, notebooks, code snippets) to markdown using powerful multimodal LLM

343
Python
MIT
slowing1.3y ago
chrisryugj/kordoc

CLI/MCP server focused on Korean document formats (HWP/HWPX) plus PDF/Office; choose for HWP support or non-Python environments.

모두 파싱해버리겠다 — HWP·HWPX·PDF·Office 문서를 Markdown으로. 양식 자동 채우기와 신구대조를 갖춘 CLI·MCP 서버 | Convert Korean documents (HWP, HWPX, PDF, Office) to Markdown — CLI and MCP server with form filling and diff

1.8k
TypeScript
MIT
active1d ago

Older generation, or narrower

An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.

opendataloader-project/opendataloader-pdf

Java PDF parser for AI-ready data; choose if you need a PDF-only solution in a Java stack.

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

28.6k
Java
Apache-2.0
active2d ago
marph91/jimmy

converts specific note formats to markdown; choose for that narrow use case.

Convert your notes to Markdown

528
Python
GPL-3.0
active24d ago
datalab-to/marker

PDF-only converter to markdown/JSON with high accuracy; choose for PDF processing where marker's accuracy is required.

Convert PDF to markdown + JSON quickly with high accuracy

39.0k
Python
Apache-2.0
active16d ago

Listed as an alternative to

These projects were analysed and named markitdown among their alternatives. The relationship is not symmetric — how markitdown rates them is a separate judgement, made when markitdown is analysed in its own right.

firecrawl/anydoc

calls markitdownPython library for office-to-Markdown; choose for Python-native workflows.

Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.

17.8kRustactive
CatchTheTornado/text-extract-api

calls markitdownchoose for a Python library converting office/PDF docs to Markdown, but with no PII removal and a simpler pipeline.

Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

3.2kPythonslowing