pickfit

BrowseProductivity & docs tools

MarkItDown

Python utility and CLI that converts PDF, Office documents, images, audio, HTML and other files to Markdown for use with LLMs.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.10,<=3.14
  1. create venv, pip install 'markitdown[all]', link markitdown into ~/.local/bin

    python3 -m venv ~/.venv && ~/.venv/bin/pip install -q 'markitdown[all]' && ln -sf ~/.venv/bin/markitdown ~/.local/bin/markitdown
  2. install markitdown-sample-plugin for plugin check

    ~/.venv/bin/pip install -q markitdown-sample-plugin

Check that it works

markitdown --version

The output should contain “markitdown 0.1.9”.

First thing to try

cat > page.html <<'EOF'
<html><body><h1>Main Heading</h1><h2>Sub</h2><ul><li>apple</li><li>banana</li></ul>
<p>See <a href="https://example.com/docs">the docs</a>.</p>
<table><tr><th>Col A</th><th>Col B</th></tr><tr><td>1</td><td>2</td></tr></table></body></html>
EOF
cat > gen.py <<'EOF'
from docx import Document
d = Document()
d.add_heading("Quarterly Report", level=1)
d.add_paragraph("First bullet item", style="List Bullet")
d.add_paragraph("Second bullet item", style="List Bullet")
t = d.add_table(rows=2, cols=2)
t.cell(0,0).text="Name"; t.cell(0,1).text="Value"
t.cell(1,0).text="Alpha"; t.cell(1,1).text="42"
d.save("sample.docx")
from openpyxl import Workbook
wb = Workbook(); ws = wb.active; ws.title="Sales"
ws.append(["Region","Units"]); ws.append(["North",120]); ws.append(["South",95])
wb.save("sample.xlsx")
from pptx import Presentation
p = Presentation(); s = p.slides.add_slide(p.slide_layouts[1])
s.shapes.title.text = "Slide Title Hello"; s.placeholders[1].text = "Bullet on slide"
p.save("sample.pptx")
objs = [b"<< /Type /Catalog /Pages 2 0 R >>",
 b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>",
 b"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>",
 None,
 b"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>"]
stream = b"BT /F1 24 Tf 72 700 Td (Hello PDF from MarkItDown) Tj ET"
objs[3] = b"<< /Length %d >>\nstream\n" % len(stream) + stream + b"\nendstream"
out = b"%PDF-1.4\n"; offs = []
for i,o in enumerate(objs):
    offs.append(len(out)); out += b"%d 0 obj\n" % (i+1) + o + b"\nendobj\n"
x = len(out)
out += b"xref\n0 %d\n0000000000 65535 f \n" % (len(objs)+1)
for o in offs: out += b"%010d 00000 n \n" % o
out += b"trailer\n<< /Size %d /Root 1 0 R >>\nstartxref\n%d\n%%%%EOF\n" % (len(objs)+1, x)
open("path-to-file.pdf","wb").write(out)
EOF
~/.venv/bin/pip install -q python-docx && ~/.venv/bin/python gen.py
markitdown path-to-file.pdf -o document.md && cat document.md

Run markitdown <file> to print a file's contents as Markdown.

What it does

  • Convert PDF, Word, PowerPoint and Excel files to Markdown
    How to use it
    1. Run markitdown <file>.pdf -o <output>.md to save a PDF as a Markdown file.
    2. Run markitdown <file>.docx, markitdown <file>.xlsx or markitdown <file>.pptx to print the Markdown to the terminal.
    Tested
  • Keep headings, lists, tables and links in the output
    How to use it
    1. Run markitdown <file>.docx to get headings, lists and tables as Markdown.
    2. Run markitdown <file>.html to convert a web page, with links kept as Markdown links.
    Tested
  • Caption images and transcribe audio
    Not tested
  • Add more file formats with third-party plugins
    Not shown working

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 2 of 4 features work
  4. Works offline

Good for

  • convert a PDF file to Markdown
  • prepare documents as Markdown for LLM text analysis pipelines
  • extract structured fields from invoices via Azure Content Understanding

An alternative to textract.

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 15 Nov 2026
  • Version 0.1.9

Differences the test machine hit

  • README: pip install 'markitdown[all]'
    In the test: Installed into a venv (python3 -m venv ~/.venv) as the README's Prerequisites recommend, then symlinked ~/.venv/bin/markitdown into ~/.local/bin so it is on PATH
  • README: git clone git@github.com:microsoft/markitdown.git
    In the test: Not needed; the SSH clone URL would also need a GitHub SSH key (https URL works without one)
  • README: markitdown path-to-file.pdf -o document.md
    In the test: No sample files are shipped; inputs were generated (python-docx is not part of markitdown[all], installed only to create the test .docx)

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.