MonkeyOCR
A lightweight LMM-based Document Parsing Model
MonkeyOCR scores 5.1/10 (Solid) in Data Extraction.
Language Python License Apache-2.0 Stars 6.6k★ Type model Self-host Yes Repo Yuliang-Liu/MonkeyOCR Homepage https://github.com/Yuliang-Liu/MonkeyOCR
Quality
Solid 5.1
Adoption 46
Activity 30
Maturity 80
Community 43
Capability 50
Show the math
Overall 5.1/10
value = 5.1/10
score = value
Adoption 5.1/10
value = 45.5/100
score = 1 + 9 * value / 100
Activity 3.7/10
value = 30.1/100
score = 1 + 9 * value / 100
Maturity 8.2/10
value = 79.9/100
score = 1 + 9 * value / 100
Community 4.8/10
value = 42.6/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
6.6k★ GitHub stars
3/90d Recent commits
1 devs/90d Recent contributors
1.1y Project age
2mo ago Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
ocr vlm layout document parsing