dsh-macos-vision-ocr
Offline macOS Vision OCR tool for DeepSeek Harness.
Install
$ dsh plugin --profile web add github:leozou320-ai/dsh-macos-vision-ocrPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Adds an `ocr_image` tool for OCR on local image files.
- Uses macOS Vision `VNRecognizeTextRequest` at accurate recognition level.
- Supports PNG, JPEG, WebP, GIF, TIFF, BMP, HEIC, and HEIF images.
- Accepts BCP-47 recognition languages per call.
- Compiles and caches an embedded Swift helper on first use.
- Returns recognized text, canonical image path, selected languages, and a truncation flag.
Useful For
- Extracting text from screenshots, scans, and document images in a Harness session.
- Reading Chinese or English image text with configured recognition languages.
- Performing OCR without an API key or network request.
Who It Fits
- DeepSeek Harness users on macOS.
- Users who need local image-text extraction in agent workflows.
- Developers able to install Xcode Command Line Tools and use a compatible developer-preview Harness build.
Documented Limitations
- Requires macOS 13 or later.
- Requires Xcode Command Line Tools and `swiftc` on `PATH`.
- Requires DeepSeek Harness 0.1.0-rc.5 or a compatible developer-preview build.
- Intentionally fails on Linux and Windows because Apple Vision is unavailable.
- First OCR call is slower while the Swift helper compiles.
- Does not provide general visual understanding such as object, face, or scene identification.
- Reading order may be imperfect for multi-column or highly stylized layouts.
- Recognized text enters the current session transcript and model context.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- leozou320-ai/dsh-macos-vision-ocr
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- a89e9b5 · 2026-08-26
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 1GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-16
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
DeepSeek Harness web-search plugin that adds web search, X search, and focused page fetching with structured evidence.
View plugin →Vision routing and pixel-level visual tool suite for DeepSeek Harness agents with built-in free fallbacks.
View plugin →Mobile companion and secure remote/LAN access plugin for DeepSeek Harness.
View plugin →A standalone, local persistent-memory system for AI agents, with DeepSeek Harness support provided through the separate dsh-mnemon plugin.
View plugin →