Install
$ dsh plugin --profile web add @anionex/dsh-vision-toolkitPlugin 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
- Direct image paste handling with task-aware vision routing for text models
- Element grounding and visual detection returning precise pixel coordinates and preview overlays
- Long-screenshot OCR with low-content boundary cutting and overlap deduplication
- UI and sketch restoration into editable HTML, CSS, and SVG vector graphics
- Pixel-level diffing with difference metrics, ranked change regions, and heatmaps
- Local HTML and web document screenshot rendering with full-page support
- Foreground extraction and dominant color palette analysis
Useful For
- Pasting screenshots into DSH chat to diagnose errors or ask task-focused visual questions
- Extracting clean, structured Markdown from lengthy chat logs, feeds, or scrolling pages
- Converting UI mockups, hand-drawn wireframes, or reference designs into working code
- Automating GUI testing and verifying visual changes between baseline designs and rendered implementations
Who It Fits
- DeepSeek Harness users needing multimodal vision analysis with text-centric models
- Front-end developers and designers generating code from visual references
- Agent workflow engineers building automated GUI inspection and testing routines
Documented Limitations
- Requires a configured OpenAI-compatible or Anthropic-compatible vision model API or local endpoint
- HTML screenshot rendering requires a locally installed Chrome, Chromium, or Edge browser
- Configured POSIX shared storage roots are currently unsupported on Windows
- Requires Python 3.11+ or an active network connection on initial run to download isolated standalone runtime assets
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 4 runtime, 16 development, 22 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
- Anionex/dsh-vision-toolkit
- Registry source
- Registry curated
- Registry classification
- Plugin Bundle
- Source checked
- ce64f6e · 2026-09-30
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
- 887GitHub stars
- Forks
- 47
- Open issues
- 1
- Last commit
- 2026-09-26
- Last release
- 2026-09-10
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Multimodal vision router and deep pixel tools for text-only DeepSeek Harness agents with free fallback chains.
View plugin →Automates invoice retrieval from IMAP mailboxes, OCR extraction, categorization, and Excel summary report generation.
View plugin →A DeepSeek Harness vision plugin that turns pasted images into structured OCR, layout, and semantic evidence for supported text-only models.
View plugin →DeepSeek Harness web-search plugin that adds web search, X search, and focused page fetching with structured evidence.
View plugin →