atlas-doc-parser

What it is and what it does

atlas_doc_parser bridges Confluence and Jira's Atlassian Document Format (ADF)—a complex JSON structure—into clean Markdown that AI models can consume. The library provides a straightforward API: parse ADF JSON via NodeDoc.from_dict(), then call to_markdown() to get usable text. This solves a real friction point: teams store knowledge in Confluence pages and Jira issues, but those systems' rich-text format is opaque to LLMs. By converting to Markdown, you unlock that knowledge for AI workflows—summarization, context injection, training data generation, or semantic search.

The package is minimal and focused: it depends only on func_args and installs as a pure Python wheel with no compiled dependencies. It targets modern Python versions and carries an MIT license. The repository is active but shows aging maintenance signals—the latest release was 222 days ago, though the last commit is recent. With no known security vulnerabilities and moderate adoption, it's a straightforward tool for a specific task.

Use it for:

• Extract Confluence page content and feed it to an LLM for summarization or Q&A without manual copy-paste.
• Bulk convert Jira issue descriptions and comments to Markdown for use as training data or context in AI pipelines.
• Build a knowledge base ingestion system that pulls from Confluence/Jira and prepares it for semantic search or RAG.
• Automate documentation export from Confluence into a format suitable for static site generators or LLM processing.
• Parse Jira issue details to generate AI-assisted ticket summaries or automated status reports.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Converts Atlassian Document Format (ADF) JSON from Confluence and Jira into clean Markdown suitable for AI processing and analysis.

Yes, if you need to extract and convert Confluence or Jira content for AI workflows. The package solves a specific, real problem with low install friction and no security issues. The aging maintenance status is a minor concern but not a blocker—the code is stable, the last commit is recent, and the task is narrow. Install it if ADF-to-Markdown conversion is on your critical path.

Install

atlas-doc-parser on PyPI

pip install atlas-doc-parser

uv add atlas-doc-parser

poetry add atlas-doc-parser

Installing atlas-doc-parser

Before you install

Low friction: pure Python wheel with a single runtime dependency. Repository is active with a recent commit on 2026-01-04, though marked as aging at 222 days since release.

License in practice

MIT license permits commercial and private use with minimal restrictions—you may use, modify, and distribute the package freely provided you retain the license notice.

Quickstart

pip install atlas-doc-parser

from atlas_doc_parser.api import NodeDoc

# Parse ADF JSON from Confluence/Jira API
doc = NodeDoc.from_dict(adf_json)
markdown = doc.to_markdown()

Requires Python 3.10 or later (supports 3.10, 3.11, 3.12, 3.13).

Verify before relying

• Completeness of ADF feature coverage—which Confluence/Jira ADF node types are fully supported vs. partially handled or skipped.
• Performance characteristics with large or deeply nested ADF documents.
• Whether the Markdown output is optimized for specific LLM models or is generic.

Package facts

Evidence: atlas_doc_parser-1.0.1-py3-none-any.whl

Tags

More Markup packages