datalab-to/chandra
OCR model that handles complex tables, forms, handwriting with full layout.
Recommended between 2026-08-24 and 2026-08-24. Last pushed 2026-10-22.
▲ 1 recommend · ▼ 0 criticisms
What hackers say
“Datalab Chandra was the most accurate.”
— phenomen, 2026-08-24 · strong recommendation · original comment on Hacker News ↗
show original comment
I tested many open-source and hosted OCR models and Datalab Chandra was the most accurate. It can parse complex layouts, tables, handwriting, and formulas at a fraction of the cost of Claude/Gemini. Local: https://github.com/datalab-to/chandra Hosted: https://www.datalab.to Another decent option is GLM OCR. It's slightly less accurate but faster and cheaper. Local: https://github.com/zai-org/GLM-OCR Hosted: https://docs.z.ai/guides/vlm/glm-ocr Other models such as PaddleOCR, dots.ocr and DeepSeek OCR performed significantly worse.
Badge for your README
[](https://hackerrepos.org/repo/datalab-to/chandra)
Alternatives hackers mention
- zai-org/GLM-OCR ▲ 3