Overview
Research summary
Marker converts PDFs and other supported document formats into structured outputs suitable for indexing and downstream processing. It combines layout and text extraction with formatting logic for tables, equations, references, code and images, and can optionally use language models to improve conversion. Developers can invoke command-line workflows or extend the Python processing pipeline with custom behavior; the repository also documents serving options.
It is useful for document ingestion and knowledge pipelines that need more structure than a plain text dump. Code is Apache-2.0, while the distributed model weights use a modified OpenRAIL-M license with commercial limits.
Repository summary
- Stars
- 40,158
- Open issues
- Unavailable
- Last push
- 2026-09-13
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Version
- Unavailable
Recorded catalogue figures. View repository data and provenance →
Classification
Pricing & services
Paid services available
The provider offers paid products or services. Free options may also be available.
Commercial offering checked 2026-10-02.
Licence scope
Model weights include commercial eligibility limits; the code license does not cover all deployed assets.
Implementation
Recorded implementation details and interfaces for Marker.
Implementation details
Python document conversion pipeline using Surya and optional LLM providers
- Languages
- Python
- Repository type
- source
Recorded interfaces and capabilities
Licence scope
Model weights include commercial eligibility limits; the code license does not cover all deployed assets.
Repository
Repository snapshots, release information and recorded maintenance signals.
Repository snapshot
- Stars
- 40,158
- Open issues
- Unavailable
- Last push
- 2026-09-13
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Archived
- Not recorded
Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).
Maintenance and provenance
- Catalogue snapshot
- 2026-10-06
- Stars source
- Recorded fallback
- Last push source
- Recorded fallback
Documentation
Recorded references and research provenance for this entry.
Recorded sources 5
- https://www.datalab.to Project page · Commercial offering evidence
- https://github.com/datalab-to/marker Linked repository · Research reference
- https://github.com/datalab-to/marker/blob/master/README.md Research reference
- https://github.com/datalab-to/marker/blob/master/LICENSE Research reference
- https://www.datalab.to/pricing Commercial offering evidence
Research metadata
- Research date
- 2026-10-02
- Catalogue snapshot
- 2026-10-06