AnyListen/tools-ocr
树洞 OCR 文字识别（一款跨平台的 OCR 小工具） observed · 2026-08-28
Health v2 · maintenance only
23/100
- Activity 0
- Release rhythm 8
- Longevity 100
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 2721
- days_rel: n/a
- days_push: 839
- n_releases_24m: 0
Adoption not part of the score
3065 stars · 482 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
Tree Hole OCR is a cross-platform desktop OCR tool built with Java and JavaFX that performs offline text recognition using Paddle OCR models via DJL and PyTorch. It supports screenshot-based region selection with hotkeys, image text recognition, and PDF recognition.
Use cases
- extract text from screenshots with a hotkey
- recognize text in images offline without internet
- copy text from PDFs that don't allow selection
- OCR a selected screen region
- extract Chinese and English text from images
When to choose
- you need offline OCR on Mac or Windows
- you frequently copy text from screenshots or images
- you want a lightweight desktop tool rather than a cloud OCR API
- you need to extract text from PDFs
When to avoid
- you need OCR on Linux (only Mac and Windows are supported)
- you need a programmatic OCR library or API to embed in your own code
- you require batch server-side OCR at scale
- your macOS is older than 12.6
Facets
application · maturity active
ocr image-processing pdf gui computer-vision image-processing pdf developer-tools cross-platform windows cross-platform jvm screenshot-ocr javafx paddle-ocr offline-ocr text-recognition macos desktop
1 source
- readme: https://github.com/AnyListen/tools-ocr · fetched 2026-08-28 · 5d144916e14a
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| AnyListen/tools-ocr | main | 23 |
For agents
markdown · JSON · MCP: product_card(name="AnyListen/tools-ocr")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem