// Read docs & web pages
Indra OCR
A ~1M-parameter OCR model from Datalab (makers of Marker / Surya) that runs on CPU via ONNX Runtime: PDFs and images to Markdown, text or JSON with boxes, 80+ languages, handwriting and rotated pages, with layout blocks and reading order. Benchmarks are vendor-reported; model OpenRAIL-M, code Apache-2.0
Open source Maintained For agents
IN ONE PARAGRAPH
Indra OCR is A ~1M-parameter OCR model from Datalab (makers of Marker / Surya) that runs on CPU via ONNX Runtime: PDFs and images to Markdown, text or JSON with boxes, 80+ languages, handwriting and rotated pages, with layout blocks and reading order. Benchmarks are vendor-reported; model OpenRAIL-M, code Apache-2.0.
Good for: Developers who want their agent (Claude Code, Codex, Cursor…) to read docs & web pages.
Not for: people who don’t want to install and run tools themselves.
01How to start
- 1Read the official README / docs for requirements and permissions.
- 2Install it as the official guide describes.
- 3Tell your agent the command exists (e.g. in AGENTS.md / CLAUDE.md) so it knows when to call it.
02Alternatives & comparison
Compare side by side →03Related
Versions, why it is listed, for AI to read
For AI agents
- Interfaces:its own app or website
- Machine-readable record:/api/v1/software/indra-ocr.json · llms.txt
- Added 2026-10-21