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

dsh-tesseract-ocr

DeepSeek Harness plugin that performs local Tesseract OCR on attached images for text-only models, preserving privacy.

VisionUI & ProductivityTerminal & TUIDeveloper ToolsSecurity & PolicySkills & Workflows
5GitHub Stars1ForksUpdated2026-09-13

Install

$ dsh plugin --profile web add dsh-tesseract-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-tesseract-ocr is a privacy-first DeepSeek Harness plugin that enables text-only models to process attached images. By hooking the LLM admission seam and pre-step message rewriting pipeline, the plugin locally processes images using the Tesseract OCR CLI, injects recognized text into the prompt context, and prevents raw image bytes from being uploaded to remote providers.

Key Capabilities

  • Shims LLM model capability resolution to permit image attachments on text-only models
  • Rewrites agent pre-step messages locally using Tesseract OCR
  • Prevents raw image byte transmission to external LLM providers by default
  • Provides optional passthrough mode for genuine multimodal vision models
  • Caches recognized text per attachment ID to optimize multi-turn conversations
  • Automatically cleans up temporary image files with timeout handling

Useful For

  • Using text-only LLMs (such as DeepSeek-V2.5/V3) with scanned documents or screenshots
  • Privacy-sensitive document processing where image data must remain on the local machine
  • Extracting text from diagrams, code screenshots, and invoices into LLM workflows

Who It Fits

  • DeepSeek Harness users relying on text-only models for document processing
  • Privacy-conscious developers processing confidential image data
  • System administrators and AI engineers seeking local OCR pre-processing

Documented Limitations

  • Requires system-level installation of the Tesseract OCR binary and corresponding language packs
  • Image format compatibility is tied to local Tesseract/Leptonica build capabilities
  • Must not be enabled concurrently with conflicting OCR plugins like windows-ocr

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.

No automated security signals have been published yet.

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-tesseract-ocr
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
81a2324 · 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
5GitHub 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