DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-image-vision

Image vision and OCR plugin for DeepSeek Harness with automatic vision detection, multi-provider routing, and UI attachment support.

VisionUI & ProductivityDeveloper ToolsSkills & Workflows
2GitHub Stars0ForksUpdated2026-09-04

Install

$ dsh plugin --profile web add https://github.com/xiaoyuink/dsh-image-vision/releases/latest/download/xiaoyuink-dsh-image-vision-latest.tgz

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-image-vision adds full image perception and optical character recognition capabilities to DeepSeek Harness. It automatically detects whether the active primary model natively supports image vision; if not, it seamlessly delegates image analysis to configured external vision model providers. The plugin adds drag-and-drop/paste image attachments to the chat interface, integrates permanent DSH attachment storage, and exposes four specialized vision tools alongside domain-specific presets for biomedical, research, and general vision tasks.

Key Capabilities

  • Automatic detection of current LLM vision capabilities with seamless fallback routing
  • Provides four vision tools: image_vision, image_vision_ocr, image_vision_ground, and image_vision_crop
  • Native chat UI integration for pasting, uploading, and drag-and-dropping images
  • Domain-specific analysis presets including histopathology, cell biology, anatomy, clinical, and scientific figures
  • Multi-provider vision model management with balance checking, test execution, and auto-discovery
  • Image format preprocessing including TIFF/SVG via sharp and optional Python conversion for AI/EPS

Useful For

  • Enabling pure-text LLMs to analyze and interpret images through external vision providers
  • Biomedical research and clinical imaging analysis using preconfigured specialized prompt presets
  • Precise OCR extraction, target grounding, and cropped inspection of dense diagrams or screenshots
  • Analyzing multi-panel scientific charts and publication figures

Who It Fits

  • DeepSeek Harness users needing seamless visual inputs without switching their primary chat model
  • Biomedical and academic researchers analyzing histology, Western blots, and scientific figures
  • Developers needing programmatic OCR, bounding-box grounding, and image crop tools

Documented Limitations

  • Converting Adobe AI and EPS formats requires a local Python environment with PyMuPDF and Ghostscript
  • Free OVHcloud tier is rate-limited to 2 requests per minute per IP
  • Uploaded attachments are stored permanently in local storage (~/.dsh/attachments) and require manual disk cleanup if needed

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
xiaoyuink/dsh-image-vision
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
a445f84 · 2026-09-18

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
2GitHub stars
Forks
0
Open issues
0
Last commit
2026-09-04
Last release
2026-09-04
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