dsh-vision-bridge
Universal vision bridge for DeepSeek Harness providing multimodal image attachments and ~40 visual analysis tools for any model.
Install
$ dsh plugin --profile web add @goodandready/dsh-vision-bridgePlugin 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
- Modality bridging that augments model definitions to accept image attachments across text-only chat models
- Multi-channel routing with fallback, parallel racing, and LRU description caching
- Native vision passthrough that dynamically exposes or hides redundant bridging tools
- Publishing PDF pages, video frames, and URLs as conversation attachments
- Suite of ~40 specialized visual tools including local Tesseract OCR, LaTeX formula extraction, table extraction, QR/barcode decoding, and UI flow diagrams
- Enterprise security controls including masked secrets, CSRF checks, SSRF fetch policies, and origin validation
Useful For
- Attaching screenshots, documents, and images to conversations powered by text-only language models
- Extracting tables, formulas, or UI diagrams from images and PDFs directly into markdown
- Running offline or multi-channel visual OCR and QA pipelines with Ollama or external OpenAI-compatible endpoints
- Comparing visual outputs across multiple vision providers via consensus tools
Who It Fits
- DeepSeek Harness users working with text-only models who need image attachment support
- Developers needing automated OCR, document structure extraction, and UI layout inspection
- Teams configuring multi-backend vision fallback pipelines
Documented Limitations
- Requires configured external vision models or local endpoints (such as Ollama or OpenAI-compatible backends) when bridging text-only chat models
- Model-supplied image URLs are restricted by SSRF protection policies unless explicit allowlists are configured in allowedUrlHosts
- Certain media extraction features depend on host dependencies such as Poppler and FFmpeg for PDF and video frame operations
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 0 runtime, 1 development, 7 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
- GooDAnDReaDY/dsh-vision-bridge
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- c11af2a · 2026-10-14
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
- 2GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-12
- Last release
- 2026-10-12
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Vision routing and pixel-level tools for text-only DeepSeek Harness agents with built-in free fallback.
View plugin →DeepSeek Harness web-search plugin that adds web search, X search, and focused page fetching with structured evidence.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →Use ChatGPT, Claude, Grok, GitHub Copilot, and Antigravity subscriptions as DeepSeek Harness LLM providers via OAuth.
View plugin →