indra vs marker
CPU-focused OCR and structured document conversion compared
indra and marker convert documents into structured outputs such as Markdown and JSON. indra focuses on CPU-based OCR with line-level coordinates and layout details, while marker supports a broader range of formats and offers configurable conversion workflows with local models.

indra: Fast CPU OCR with Datalab’s Indra Model
Indra OCR uses Datalab’s compact model with ONNX Runtime to turn PDFs and images into markdown, text, or structured JSON on CPU. It adds line boxes, layout labels, and reading order for fast document parsing without a GPU.

marker: Convert Documents into Structured Text
Marker converts PDFs and other documents into Markdown, JSON, HTML, or chunks, preserving structure such as tables, equations, and images. It suits developers building document-processing workflows who can run its local models and inference backend.
| indra | marker | |
|---|---|---|
| Language | Python | Python |
| License | Apache-2.0 | Apache-2.0 |
| Stars | 421 | 40.2k |
| Forks | 33 | 2.9k |
| Last analyzed | Oct 16, 2026 | Oct 3, 2026 |
Key differences
- indra uses a compact ONNX Runtime model and does not require a GPU; marker uses the Surya vision-language model through a local inference server, with hardware needs varying by mode.
- indra supports PDFs and images; marker also supports formats such as PPTX, DOCX, XLSX, HTML, and EPUB with additional dependencies.
- indra outputs Markdown, plain text, or JSON; marker also offers HTML and chunked output.
- indra returns line boxes, confidences, layout labels, reading order, and page source; marker processes elements including tables, equations, code, links, and images.
- Both codebases use Apache-2.0, but both projects describe separate modified OpenRAIL-M terms for model weights that should be checked before adoption.
- The supplied data lists 421 stars for indra and 40.2k for marker; indra's health notes also describe a very recent repository with contributions from one person in the measured data.
Choose indra if you…
- need CPU-focused OCR for clean printed PDFs and images without a GPU.
- want line boxes, confidence data, layout labels, and reading order in structured output.
- need to combine digital PDF text with OCR for scanned pages or text inside images.
Choose marker if you…
- need conversion across PDFs and additional document formats such as DOCX or EPUB.
- want Markdown, JSON, HTML, or chunked output with elements such as equations, code, and images.
- need configurable local workflows, including custom processors or optional LLM-based correction.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.