<p align="center"> <img src="assets/hero-v2.png" alt="DSH Vision Toolkit helps text-only DeepSeek Harness agents understand images and complete visual tasks" /> </p> <div align="center">

DSH Vision Toolkit

<a href="https://trendshift.io/repositories/149708?utm_source=trendshift-badge&amp;utm_medium=badge&amp;utm_campaign=badge-trendshift-149708" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/149708/daily?language=TypeScript" alt="Anionex%2Fdsh-vision-toolkit | Trendshift" width="250" height="55"/></a>

Recommended by dshfind dshfind score: 94 — highest-rated plugin agentic leaderboard

npm MIT DSH

A more powerful vision toolkit—give text-only models in DeepSeek Harness eyes: image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks in one toolkit and Skill.

🚀 Paste an image and ask directly | Install with one command | Broad use cases

Highlights | Quick start | Toolbox | Configuration and limits | Troubleshooting | Community

🌐 English | 中文

</div>

🏆 This project is the first comprehensive vision-tool plugin in the DeepSeek Harness ecosystem: it was initiated before internal beta and built during the beta with reference to agent-vision-toolkit.

Original work: The system and division of responsibilities behind these visual tools, together with the vision-skills Skill, were personally created and continuously refined by the author through long-term real-world use and repeated iteration.

If this project helps you or gives you some inspiration, feel free to star 🌟 & fork.

Highlights

• Paste an image and ask directly. In DSH Web, pasting an image switches the text-only model to its (Vision Toolkit) variant automatically — no manual path copying or model changes. Native thumbnails, session history, and workspace paths stay intact; Web can preview artifacts.
• One command to install. After installation, configure a vision provider in Settings → Vision Toolkit and start using the tools.
• Not just a caption — the content that matters. The model does not produce a generic description; it extracts evidence around the current task, such as “Where is the error?” or “Where is the button?”.
• A battle-tested visual-task methodology. The bundled Skill tells the agent what to look at for different visual tasks, which tool to choose, how to proceed, and how to verify the result.

agent-vision-toolkit gives an agent more than image captions: it can read, locate, crop, trace, rebuild, and verify visual work. DSH Vision Toolkit is its native DeepSeek Harness integration, bringing that workflow into Web and Headless Profiles.

This project has two layers:

1. Visual tools and a Skill: the agent learns when to inspect, ground, OCR, crop, trace, or compare pixels.
2. Native DSH integration: those capabilities live inside Profiles, sessions, Settings, Artifacts, and the Web UI.

dsh plugin --profile web add @anionex/dsh-vision-toolkit

Upstream toolkit: Anionex/agent-vision-toolkit · Project website: agent-vision.anionex.me

❤️ Sponsor

Want to sponsor this project? See FUNDING.md or email [email protected].

<details open> <summary>Click to collapse</summary> <table> <tr> <td width="220" align="center" valign="middle"><a href="https://aihubmix.com/?aff=sinZ"><img src="assets/logo_aihubmix.png" alt="AIHubMix" height="48"></a></td> <td valign="middle">Thanks to <a href="https://aihubmix.com/?aff=sinZ">AIHubMix</a> for sponsoring this project! AIHubMix is a stable, high-concurrency AI model API gateway that connects Claude, GPT, Gemini, DeepSeek, and other mainstream models through a single API key, compatible with multiple protocols, with <b>free model options</b> available. To sign up, use the <a href="https://aihubmix.com/?aff=sinZ">AIHubMix entry</a> outside mainland China or the <a href="https://inferera.com/?aff=sinZ">Inferera entry</a> within mainland China.</td> </tr> <tr> <td width="220" align="center" valign="middle"><a href="https://api.ewo.so/register?aff=U6PT7J"><img src="assets/logo_eapi_dark.png" alt="E-API" height="48"></a></td> <td valign="middle">Thanks to <a href="https://api.ewo.so/register?aff=U6PT7J">E-API</a> for sponsoring this project! E-API aggregates mainstream AI models behind OpenAI-, Anthropic-, and Codex-compatible APIs, with selected Claude models up to <b>98% below official prices</b> and DeepSeek V4 models about <b>25% below official prices</b>.</td> </tr> </table> </details>

Contents

• Highlights
• Recent updates
• Who it is for
• See it in action
• Quick start: three steps
• Toolbox
• Configuration and limits
• Troubleshooting
• Donation
• Development and community

Recent updates

• 2026-08-20 · AIHubMix setup guide: Added a screenshot-based guide for getting an API key through the Inferera entry and configuring the Gemini 3.7 Flash vision model; Settings now links directly to this guide.
• 2026-08-19 · Transparent routing by default: The model selector keeps one entry per model with the original name, and image input (paste, history, read_image) works without manually switching to a (Vision Toolkit) variant. Disable “Transparent variant routing” in advanced settings → image input to restore the explicit entries.
• 2026-08-16 · Windows Python: Added Microsoft Store Python support, fixing first-time isolated-runtime setup failures for affected Windows users.
• 2026-08-17 · Vision upgrade: Switched the default model to Gemini 3.7 Flash and fixed Qwen/Gemini bounding-box coordinate order.
• 2026-08-16 · Image paste: Text-only routes now switch to a (Vision Toolkit) variant and keep a workspace path, fixing blocked pastes and images that could not be reused later.
• 2026-08-16 · Service stability: Expanded service capacity to reduce peak-time 429 responses.
• 2026-08-16 · Real model test: Added a full image-request test in Settings, fixing the false confidence caused by a successful /models request to a model that still cannot process images.

Who it is for

1. Want an interaction experience similar to a multimodal model: paste an image directly and ask a question or make a request.
2. Want more than image Q&A — complete more complex, high-value visual tasks such as turning a sketch into a front-end page, converting an image into HTML, or extracting chat messages from long screenshots; more scenarios are added over time.

The bundled vision-skills Skill carries the complete upstream playbooks, explaining when to use each workflow, in what order to call the tools, and how to verify the result:

Playbook	What the agent learns to do
Read long screenshots, chat histories, and scrolling pages	Find low-content cut bands, OCR each chunk in order, preserve chat speakers/timestamps/quotes, merge only duplicated overlap, and surface risky boundaries for verification
Rebuild a UI from a screenshot or design	Reuse project components and assets first, then combine code-native UI, extracted visuals, rendered screenshots, and visual comparison to align a page or component
Restore an icon, logo, illustration, or other graphic	Extract a transparent PNG from the source image, or rebuild an editable/scalable SVG when needed, then verify shape, color, and alpha edges
Turn a sketch, diagram, or whiteboard into structured code	Recover nodes, labels, connections, and directions as editable Mermaid, Graphviz, or another structured representation
Operate a GUI from screenshots	Locate a control, perform one action, capture the screen again, and verify the resulting state before continuing

See it in action

Paste an image directly into DSH

<p align="center"> <img src="assets/dsh-view-example.png" width="82%" alt="A text-only DeepSeek model answering a question about a pasted image through Vision Toolkit in DSH Web" /> </p>

Paste an image into the conversation. A text-only model can switch to its Vision Toolkit variant and inspect the image in the context of the user's question.

Screenshot to editable page

<p align="center"> <img src="assets/upstream/infographic-reference.webp" width="49%" alt="Reference infographic screenshot used for restoration" /> <img src="assets/upstream/infographic-result.webp" width="49%" alt="Editable HTML and CSS reconstruction created from the reference screenshot" /> </p>

Prompt example: “(Use vision-skills) Rebuild this image into HTML.”

Left: the reference screenshot. Right: an editable HTML/CSS result. The result can continue into screenshot rendering and pixel comparison instead of ending as an image description.

Sketch to working interface

<p align="center"> <img src="assets/upstream/ui-sketch.webp" width="49%" alt="Hand-drawn JupyterLab interface used as the restoration reference" /> <img src="assets/upstream/ui-result.webp" width="49%" alt="Working JupyterLab-style interface reconstructed from the sketch" /> </p>

Left: a hand-drawn reference. Right: the working interface reconstructed from it.

Prompt example: “(Use vision-skills) Turn this sketch into a working front-end page.”

Fast UI restoration: an approximate first pass

<p align="center"> <img src="assets/upstream/ui-fast-restore-reference.webp" width="49%" alt="Original YouMind homepage used as the fast UI restoration reference" /> <img src="assets/upstream/ui-fast-restore-result.webp" width="49%" alt="Approximate YouMind homepage produced with fast UI restoration mode" /> </p>

Prompt example: “(Use vision-skills) Quickly rebuild this image into HTML.”

Left: the original page. Right: a fast reconstruction that preserves the main layout, content, and visual hierarchy while allowing approximate colors and library icons. Fast mode targets a first screenshot in about three minutes.

Quick start: three steps

1. Install

dsh plugin --profile web add @anionex/dsh-vision-toolkit

You can install it into a Headless Profile too:

dsh plugin --profile headless add @anionex/dsh-vision-toolkit

Using DSH Desktop? It bundles its own dsh CLI and intentionally does not add it to your system PATH. Open DSH Terminal from the tray and run the command there, targeting the Desktop profile:

dsh plugin --profile desktop add @anionex/dsh-vision-toolkit

Then restart DSH Desktop. The built-in plugin marketplace in DSH Desktop 2.0.1 has