ArchivedThis repository is archived and may no longer be actively maintained.
← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-windows-ocr

Privacy-focused DSH plugin that extracts text from image attachments locally via Windows.Media.Ocr before sending requests to LLMs.

VisionUI & ProductivityTerminal & TUIDeveloper ToolsSecurity & PolicySkills & WorkflowsRemote Execution
9GitHub Stars1ForksUpdated2026-09-13

Install

$ dsh plugin --profile web add dsh-windows-ocr

Plugin 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.

source-grounded
dsh-windows-ocr is a DeepSeek Harness plugin designed to enable text-only language models to process attached images privately. It intercepts image attachments, executes optical character recognition locally using the native Windows OCR engine (Windows.Media.Ocr), and replaces image data blocks with recognized text before the API payload is dispatched. Image bytes are never sent upstream unless vision passthrough is explicitly enabled.

Key Capabilities

  • Locally extracts text from image attachments using Windows.Media.Ocr via PowerShell
  • Intercepts agent/pre-step lifecycle to substitute image payloads with parsed text blocks
  • Shims llm capability resolution so text-only models can accept image inputs
  • Caches recognition results per attachment ID for process lifetime efficiency
  • Ensures fail-closed privacy defaults with optional raw vision passthrough

Useful For

  • Feeding screenshots or document photos to text-only language models without leaking raw image binaries
  • Extracting textual content from images while running DeepSeek Harness in air-gapped or privacy-conscious Windows environments
  • Reducing token and bandwidth costs by transmitting extracted text strings instead of heavy image payloads

Who It Fits

  • DeepSeek Harness users running on Windows 10/11
  • Developers seeking privacy-preserving OCR integration for text models
  • Teams working with sensitive documents who need local image text extraction

Documented Limitations

  • Requires Windows 10/11 with relevant OCR-capable Windows language packs installed
  • Only processes the first frame of animated GIF images
  • Requires PowerShell execution access for invoking the local OCR script
  • Repository is archived on GitHub

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 4 development, 3 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Prepare Script Detected

package.json declares a prepare lifecycle script that may run during relevant package installation workflows.

info
Repository Archived

GitHub reports this repository as archived.

medium
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
maxwell-feng/dsh-windows-ocr
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
e20ebb6 · 2026-09-14

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
9GitHub stars
Forks
1
Open issues
0
Last commit
2026-09-13
Last release
2026-09-13
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app