Chandra
OCR model that handles complex tables, forms, handwriting with full layout.
Chandra scores 5.8/10 (Solid) in Data Extraction.
Language Python License Apache-2.0 Stars 11.4k★ Type model Self-host Yes Repo datalab-to/chandra Homepage https://www.datalab.to
Quality
Solid 5.8
Adoption 51
Activity 47
Maturity 77
Community 53
Capability 50
Show the math
Overall 5.8/10
value = 5.8/10
score = value
Adoption 5.6/10
value = 51.4/100
score = 1 + 9 * value / 100
Activity 5.2/10
value = 46.9/100
score = 1 + 9 * value / 100
Maturity 7.9/10
value = 76.8/100
score = 1 + 9 * value / 100
Community 5.7/10
value = 52.5/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
11.4k★ GitHub stars
7/90d Recent commits
3 devs/90d Recent contributors
9mo Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- New project
New (9mo)
Created within the last year — promising but less battle-tested.
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
ocr vlm markdown tables document