dsh-windows-ocr
Multimodalmaxwell-feng/dsh-windows-ocr
DeepSeek Harness plugin that lets text-only models accept attached images: every image is OCR'd locally with Windows OCR engine, only recognized text sent to model API, privacy-first with opt-in passthrough for vision models.
- cordis
- deepseek-harness
- dsh
- dsh-plugin
- ocr
- privacy
- windows
GitHub Stars
8GitHubViews
6DSH Plugin HubForks
1GitHubOpen issues
0GitHub IssuesManifest version
0.2.4@maxwell-feng/dsh-windows-ocrLatest push
Sep 13, 2026GitHubLicense
MITJavaScriptPlugin type
HostRuns in the DSH HostPRE-INSTALL EVIDENCE
Verification and compatibility
This section shows evidence collected by the catalog. Undeclared information is labeled as unknown.
01Exact source: npm · @maxwell-feng/dsh-windows-ocr@0.2.402Validated: Aug 23, 202603Verified Harness: 0.1.0-rc.7
- Current-version compatibility
- Verified on the catalog Harness version
- Declared Harness range
- Not declared
- Declared platforms
- Not declared
- Profiles
- web
- Build approval
- Unknown
- Permissions
- Not declared
- External services
- Not declared
- Telemetry
- Unknown
No known risk flags found
This is not a security endorsement. Review source, permissions, and configuration before installing.
View evidence and scope
Verification covers only the named source, version, and Harness environment. It does not guarantee future compatibility.
@maxwell-feng/dsh-windows-ocr@0.2.4- The manifest and static structure passed checks; a runtime load check has not completed.
Project README
README
The repository README is temporarily unavailable.
Open GitHub repository
