Skip to main content

Bundle a repository into a single XML file for LLMs.

Project description

repo2xml

Bundle a complete repository into a single XML file that ChatGPT or other LLMs can read, inspired by repomix.

Features

  • Walks any directory tree and bundles readable files into XML
  • Respects .gitignore rules (via pathspec)
  • Uses layered file detection: Magika, then puremagic MIME, then identify
  • Converts supported non-text files to Markdown via markitdown
  • Skips zero-byte files, oversized files, and common build/cache directories automatically
  • Outputs a well-formed XML document with a directory tree and full file contents
  • CLI tool (repo2xml) and importable Python API

Installation

pip install repo2xml

Or with uv:

uv tool install repo2xml

Usage

CLI

# Bundle current directory to stdout
repo2xml --repo-path .

# Bundle a specific directory and save to a file
repo2xml --repo-path /path/to/repo -o repo.xml

# Skip .gitignore and add extra exclusions
repo2xml --repo-path /path/to/repo --no-gitignore --ignore "*.log" --ignore "tests/"

Python API

from repo2xml import bundle_repo, RepoBundler

# Simple one-liner
xml = bundle_repo("/path/to/repo")

# More control
bundler = RepoBundler(
    "/path/to/repo",
    respect_gitignore=True,
    max_file_size=500_000,
    extra_ignore_patterns=["*.csv", "data/"],
)
xml = bundler.bundle()

Output Format

<?xml version="1.0" encoding="UTF-8"?>
<repository>
  <file_summary>
    <purpose>...</purpose>
    <usage_guidelines>...</usage_guidelines>
  </file_summary>
  <repository_info>
    <name>my-repo</name>
    <path>/home/user/my-repo</path>
    <file_count>42</file_count>
  </repository_info>
  <directory_structure>
    my-repo/
    ├── README.md
    └── src/
        └── main.py
  </directory_structure>
  <files>
    <file path="README.md">
      <content>...</content>
    </file>
  </files>
</repository>

Development

Requires uv.

# Install dependencies
uv sync --extra dev

# Run tests
uv run pytest --doctest-modules
just test-cov

# Lint and format
uvx ruff check src
uvx ruff format src

# Build one-file executable via PyInstaller
just build

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

repo2xml-2026.4.12.0.tar.gz (9.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

repo2xml-2026.4.12.0-py3-none-any.whl (12.5 kB view details)

Uploaded Python 3

File details

Details for the file repo2xml-2026.4.12.0.tar.gz.

File metadata

  • Download URL: repo2xml-2026.4.12.0.tar.gz
  • Upload date:
  • Size: 9.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.6 {"installer":{"name":"uv","version":"0.11.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for repo2xml-2026.4.12.0.tar.gz
Algorithm Hash digest
SHA256 dec0a207351fcd7c3f8ccebd2ac65bec681addad00d7c68e3194f969ee854282
MD5 b01b17f78e975eefbc5c659feb3b83c9
BLAKE2b-256 28d0013907846dc71ecf8007162178ee50c724ee720c17187706550110bd98f8

See more details on using hashes here.

File details

Details for the file repo2xml-2026.4.12.0-py3-none-any.whl.

File metadata

  • Download URL: repo2xml-2026.4.12.0-py3-none-any.whl
  • Upload date:
  • Size: 12.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.6 {"installer":{"name":"uv","version":"0.11.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for repo2xml-2026.4.12.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7dabb050be1c99d430fad94cdf6eb18267b5b834f661d931a8b478174465e878
MD5 043616554c378c901e1192847c5d5a34
BLAKE2b-256 0fb3a91649c4b2c3f9eb75e5de011ceddf841e7f767b2cc61a5dfe80cbdbc0b6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page