DocLang is the AI-native markup format for unstructured content — including documents, images, and more. It maps cleanly to LLM tokens while preserving structure, semantics, layout, and geometry in a single, unambiguous representation.
This repository is the home of the normative specification and the reference toolkit for DocLang. If you build with LLMs and VLMs on real-world content, this is where the standard lives.
The source of the specification is available in spec.md and exports to different formats can be found in the exports/ directory.
The commands below illustrate basic scenarios. For advanced installation and usage options (minimal install, platform notes, custom Schematron backends, Python API), see the toolkit README.
pip install "doclang[schematron-saxon]"doclang validate -n my_document.dclgdoclang pack my_document.dclgIf you use DocLang in academic or technical work, please cite the specification:
@misc{doclang_2026,
title = {DocLang: Universal AI Document Format},
author = {{DocLang Project}},
year = {2026},
version = {main},
howpublished = {\url{https://github.com/doclang-project/doclang}},
}To work on this repository — setup, tests, reference generation, releases — see CONTRIBUTING.md.
DocLang is developed in the open and supported by the LF AI & Data Foundation. Learn more about the project at doclang-project.
DocLang is licensed under the Apache License 2.0. See LICENSE for details.