all2md

<p align="center">
  <img src="https://raw.githubusercontent.com/thomas-villani/all2md/main/docs/source/_static/logo.svg" alt="all2md logo" width="120" />
</p>

# all2md

**Read, convert, search, and chunk PDFs, Office files, e-books, emails, and 40+ other formats, as Markdown and back again. From Python, from your terminal, or from your AI assistant.**

[![PyPI version](https://img.shields.io/pypi/v/all2md.svg)](https://pypi.org/project/all2md/)
[![Python Versions](https://img.shields.io/pypi/pyversions/all2md.svg)](https://pypi.org/project/all2md/)
[![CI](https://github.com/thomas-villani/all2md/actions/workflows/ci.yml/badge.svg)](https://github.com/thomas-villani/all2md/actions/workflows/ci.yml)
[![codecov](https://codecov.io/gh/thomas-villani/all2md/graph/badge.svg)](https://codecov.io/gh/thomas-villani/all2md)
[![Documentation](https://readthedocs.org/projects/all2md/badge/?version=latest)](https://all2md.readthedocs.io/)
[![License](https://img.shields.io/pypi/l/all2md.svg)](https://opensource.org/licenses/MIT)
<br>
[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://docs.astral.sh/uv/)
[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
[![Checked with mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)
[![Downloads](https://static.pepy.tech/badge/all2md/month)](https://pepy.tech/project/all2md)
[![MCP server](https://img.shields.io/badge/MCP-server-6E56CF)](https://all2md.readthedocs.io/en/latest/mcp.html)
[![GitHub Action](https://img.shields.io/badge/GitHub_Action-quality_gate-2088FF?logo=githubactions&logoColor=white)](https://all2md.readthedocs.io/en/latest/github_action.html)

<p align="center">
  <img src="https://raw.githubusercontent.com/thomas-villani/all2md/main/docs/source/_static/read-demo.gif" alt="all2md read showing a Word document in the terminal, with an outline, a table, code and a list of links" width="900" />
</p>

<p align="center"><i>A Word document, read in the terminal with <code>all2md read</code>.</i></p>

## Try it in ten seconds

With [uv](https://docs.astral.sh/uv/) there is nothing to install first:

```bash
uvx --from "all2md[all]" rcat report.pdf          # read any document in the terminal
uvx --from "all2md[all]" all2md report.docx       # print it as Markdown
```

Keep it around as a tool, with `all2md`, `rcat` and the `all2md-mcp` server on your `PATH`:

```bash
uv tool install "all2md[all]"
```

Or use it as a library:

```bash
uv add "all2md[pdf,docx]"      # or: pip install "all2md[pdf,docx]"
```

```python
from all2md import to_markdown

markdown = to_markdown("report.pdf")
```

## Pick your path

| I want to… | Start with | Read |
| --- | --- | --- |
| Read documents without leaving the terminal | `rcat report.docx`, `all2md read docs/` | [Read in the terminal](#read-documents-in-your-terminal) |
| Convert files, one or a thousand, in either direction | `all2md ./inbox -r --output-dir ./md` | [Convert](#convert-documents-from-the-command-line) |
| Parse documents in my Python code | `to_markdown("report.pdf")` | [Python API](#python-api) |
| Find text inside PDFs, Word files and slide decks | `all2md grep "deadline" contracts/ -r` | [Search](#search-inside-any-document) |
| Feed documents to a RAG pipeline | `all2md chunk handbook.pdf` | [RAG and chunking](#rag-and-chunking) |
| Let Claude or another assistant work with my files | the one-click Claude Desktop extension | [AI assistants (MCP)](#give-your-ai-assistant-your-documents) |
| Know how far to trust the output | `all2md report scan.pdf` | [Measured fidelity](#measured-fidelity) |

## Read documents in your terminal

`rcat` is `cat` for documents. It renders PDFs, Word and PowerPoint files (the 97-2003 `.doc` and `.ppt` too), spreadsheets, e-books, emails, notebooks, man pages and every other format all2md reads, with headings, tables, syntax-highlighted code, links with their targets, footnotes, math and admonitions. No browser, no office suite, and it works over SSH. If you reach for [glow](https://github.com/charmbracelet/glow) to read Markdown or [doxx](https://github.com/bgreenwell/doxx) to read Word files, `rcat` is the same idea for every format.

```bash
rcat report.docx                              # read a Word document
rcat deck.pptx --outline                      # just the slide titles
rcat handbook.pdf --extract "Installation"    # one section, by heading
rcat contract.pdf --pager                     # page through it
curl -sL https://example.com/spec.pdf | rcat -
```

For anything longer, `all2md read` (or `rcat -i`) opens the interactive viewer shown above: an outline beside the text, jumps between headings, the links on screen, and, given a folder, a tree of the documents in it.

```bash
all2md read handbook.pdf
all2md read docs/            # choose from the documents in a folder
```

When you would rather have a browser, `all2md view report.docx` opens a styled HTML preview, `all2md serve ./docs -r` serves a whole folder with on-demand conversion, and `all2md edit notes.md` opens a browser editor that saves back to the file.

Styling needs the `cli_extras` extra and the viewer needs `tui` (Python 3.11+); `all2md[all]` includes both. More in the [viewer documentation](https://all2md.readthedocs.io/en/latest/viewer.html).

## Convert documents from the command line

Any supported format to Markdown, and Markdown back to DOCX, PDF, PPTX, HTML, EPUB and more:

```bash
all2md report.pdf > report.md                     # to Markdown on stdout
all2md answer.md --out answer.docx                # Markdown (an LLM's output, say) to Word
all2md ./inbox -r --output-dir ./markdown -p 4    # a whole tree, four at a time
all2md ./inbox -r --output-dir ./markdown --watch # keep converting as files arrive
all2md scan.pdf --pdf-ocr-enabled                 # scanned pages, through OCR
```

Every option of every converter is a CLI flag (`all2md --help`) or a key in a config file (`all2md config generate`). Every file command reads stdin and writes stdout with `-`, so all2md slots into pipelines. Word documents come out as Word shows them: tracked changes resolved by policy, comments with their anchors, footnotes, field results, merged cells, and the list numbers Word actually prints.

See the [CLI reference](https://all2md.readthedocs.io/en/latest/cli.html) and the [cheat sheet](https://all2md.readthedocs.io/en/latest/cheatsheet.html).

## Python API

`to_markdown()` handles the common case; `convert()` goes between any two formats; `to_ast()` gives you the parsed document to work with.

```python
from all2md import to_markdown, convert, to_ast, from_ast

markdown = to_markdown("report.pdf", pages="1-3", flavor="gfm")
convert("notes.md", "notes.docx", target_format="docx")

doc = to_ast("report.docx")          # a typed document tree
html = from_ast(doc, target_format="html")
```

The core has no dependencies; each format's extra pulls in only what that format needs. Options are typed dataclasses (`PdfOptions`, `DocxOptions`, …) or plain keyword arguments, and AST transforms (`remove-images`, `heading-offset`, your own) slot in between parsing and rendering. New formats and transforms plug in through entry points.

If you are an LLM with a coding environment, `all2md llm-help` prints usage guidance written for you, and `all2md install-skills` installs it as a skill for Claude Code, Cursor and others.

See the [Python API guide](https://all2md.readthedocs.io/en/latest/python_api.html), the [AST guide](https://all2md.readthedocs.io/en/latest/ast_guide.html), and [examples/python](https://github.com/thomas-villani/all2md/tree/main/examples/python).

## Search inside any document

`grep` doesn't look inside a PDF or a `.docx`. `all2md grep` does, across any mix of formats, with the usual flags:

```bash
all2md grep -i "termination" contracts/ -r            # every format in the tree
all2md grep -C 2 "deadline" contracts/ -r --rich      # with context, highlighted
all2md search "renewal terms" ./contracts --keyword   # ranked BM25 search
all2md search "who approved the budget" ./minutes --hybrid
all2md diff draft-v1.docx draft-v2.pdf                # a colored diff, across formats
```

Vector and hybrid search need the `search` extra. Add `--cache` (or `ALL2MD_CACHE=1`) to reuse parsed documents across repeated runs.

## RAG and chunking

`all2md chunk` converts and splits in one step. Each chunk carries its section heading and source page span, so answers can cite where they came from.

```bash
all2md chunk handbook.pdf --strategy semantic --max-tokens 512 --overlap 64 > chunks.jsonl
```

```python
import all2md

for c in all2md.chunk("handbook.pdf", strategy="semantic", max_tokens=512, overlap=64):
    print(c.chunk_id, c.section_heading, c.page, c.token_count)
```

There are 11 strategies (semantic, heading, section, token, sentence, paragraph, code, …). Tables and code blocks are kept whole, and the output is JSONL ready for any vector store. Real token counts use `tiktoken` from the `chunk` extra. See the [chunk command](https://all2md.readthedocs.io/en/latest/cli.html#chunk-command).

## Give your AI assistant your documents

all2md ships a [Model Context Protocol](https://modelcontextprotocol.io/) server, so an assistant like Claude can read your PDFs and Office files, write Word documents, edit them in place, search a folder, and compare two versions. You don't need to write any code.

**In Claude Desktop** (no Python or terminal needed):

1. Download `all2md.mcpb` from the [latest release](https://github.com/thomas-villani/all2md/releases/latest).
2. Open **Claude Desktop → Settings → Extensions** and drag the file onto the page.
3. Choose the folder all2md may work in, and whether it may write files.
4. Ask Claude about the documents in that folder.

<details>
<summary><b>Other MCP clients, and th