IBM Research & LF AI & Data Foundation

Driven by Research. Powered by Open Source.

Learn how IBM Docling (docling ibm) evolved from groundbreaking document layout research at IBM Zurich into the open-source standard for AI document processing.

Our Mission

Document parsing for Generative AI should be fast, transparent, local-first, and accurate across complex scientific papers, financial spreadsheets, and multi-column reports. IBM Docling was built to eliminate proprietary cloud API lock-in by providing a 100% free, MIT-licensed parsing engine that runs natively on standard CPU and GPU hardware.

The Docling Journey

IBM Research Zurich (DS4SD)

1. Layout Analysis & TableFormer Breakthroughs

Researchers at IBM Research Zurich's Deep Search for Scientific Data (DS4SD) group created TableFormer and advanced neural layout models to solve complex PDF table extraction and multi-column reading order recovery.

Open Source & arXiv Milestone

2. PyPI Launch & Scientific Publication

IBM open-sourced Docling on GitHub under the permissive MIT License, publishing the landmark research paper arXiv:2408.09869. The library rapidly gained thousands of GitHub stars and PyPI downloads.

LF AI & Data Foundation Governance

3. Granite Docling VLM & MCP Ecosystem Expansion

Docling joined the Linux Foundation's LF AI & Data Foundation as a hosted open project. IBM integrated Granite Docling vision-language models, launched docling-serve REST API, and built native Model Context Protocol (docling-mcp) support for AI desktop agents.

MIT
Permissive Open License
100%
Local Execution Option
v2.115
Latest Active Version