DSH Marketplace

dsh-vision-toolkit

Anionex/dsh-vision-toolkit

Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.

90646TypeScriptMITSource

Install

Add dsh-vision-toolkit to DeepSeek Harness

Install into

via npm

Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.

via GitHub · npm package

Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.

What happened when we ran it

DeepSeek Harness 0.2.2-rc.1 refuses the latest release

From 0.2 DeepSeek Harness checks a plugin's dsh range before installing anything, and refuses the whole command when the running version is outside it. The latest release asks for >=0.1.0-rc.8 <0.2.0 || ^0.1.1-rc.1 || ^0.1.2-alpha.1 || ^0.1.5-rc.1 || 0.2.0-rc.2 || 0.2.1-rc.2 || 0.2.1-rc.3; we ran 0.2.2-rc.1.

No release of it accepts DeepSeek Harness 0.2.2-rc.1 yet. `dsh plugin allow-version … --accept-risk` forces one in, at the risk the harness itself warns about; otherwise wait for an update.

Why DeepSeek Harness refuses plugins, and every way around it ›

Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 11d agoon DeepSeek Harness 0.2.2-rc.1.

Due diligence

Before you install dsh-vision-toolkit

  • Source of record: Anionex/dsh-vision-toolkit — present in the community registry that DSH's own plugin market installs from.
  • Licensed under MIT.

Security

What installing dsh-vision-toolkit runs

Build scripts

Not measured — DSH refused the latest release before running anything.

Source: our sandbox install on DeepSeek Harness 0.2.2-rc.1, 11d ago.

Install hooks

package.json declares no preinstall, install or postinstall script.

Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.

README mentions

Neither shell commands nor credentials.

Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.

Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.

The AI take

What it is — A DeepSeek Harness plugin that, on image paste, switches a text-only model to a Vision Toolkit variant for Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI, element grounding, and pixel diff.

Who it is for — You are on a text-only model in DSH Web, cloning a UI or tracing a bug from a screenshot dropped into the session. Skip it if you already stay on vision-capable models and will not drop back to text-only.

Watch out — DeepSeek Harness 0.2.2-rc.1 refuses every published release before install: none declare a DSH range that includes 0.2.2-rc.1. Images default to the author's free host at 100 calls per machine per day, or you point it at your own provider.

The verdict — I'll keep it on the shortlist until the range is widened; I will not pin latest onto 0.2.2-rc.1.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.

What dsh-vision-toolkit does

dsh-vision-toolkit is a DeepSeek Harness plugin that gives text-only agents task-focused access to images, screenshots and visual comparison results. It packages agent-vision-toolkit as a native DSH plugin. In DSH Web, an agent can receive a pasted image; text-only routes switch to a Vision Toolkit variant, retain a workspace path, and send the image together with the reason for inspection to the configured vision service. The default path uses a free Gemma 4 service without an API key. Operations such as cropping, pixel diffing, colour analysis, foreground extraction, SVG tracing and HTML screenshot rendering run locally. Outputs can include task-focused answers, original-image coordinates, OCR in Markdown with chunks and manifests, crops, transparent PNGs, palettes, editable SVGs, screenshots, heatmaps and JSON.

It is intended for agents handling screenshots, UI reconstruction, long-image OCR, element grounding and visual verification rather than generic image captioning. The toolkit is a good fit when a text-only model needs evidence it can use in a subsequent action, such as locating a button or diagnosing a visual mismatch. It is less suitable when an existing vision-capable model already covers these workflows, or when images must not be sent to the default vision service. The shared free service also has documented limits of 100/day, 400/day and 20/minute for per-client, global and burst usage. dsh-vision-toolkit is MIT-licensed and has no detected risk flags in this listing.

dsh-vision-toolkit documentation

How it behaves

The plugin integrates agent-vision-toolkit into DSH. In DSH Web, pasting an image causes text-only routes to use a Vision Toolkit variant and preserve a workspace path so the image can be reused. The request includes the inspection reason, allowing answers to focus on questions such as an error location or a button colour instead of returning only a general caption.

Capabilities and outputs

The documented workflows cover intent-aware image Q&A, element grounding with original-image pixel coordinates, long-screenshot OCR, UI reconstruction, asset extraction and screenshot comparison. The toolkit can produce:

  • OCR Markdown, chunks, manifests and resumable run state;
  • crops, transparent PNGs, colour palettes and editable SVG traces;
  • HTML screenshots, difference percentages, ranked regions, heatmaps and JSON.

Service and local processing

New installations use the built-in Gemma 4 vision service and do not require an API key. Cropping, pixel diffing, colour analysis, foreground extraction, SVG tracing and HTML screenshots run locally rather than consuming vision API requests. A real image-request test is available in Settings; checking /models alone is not sufficient to verify image support.

Limits and platform notes

The README documents free-service limits of 100/day per client, 400/day globally and 20/minute for bursts. Windows first-time isolated-runtime setup supports Microsoft Store Python. The provided excerpt does not specify additional configuration keys or standalone tool command names.

Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub

Same category

Alternatives to dsh-vision-toolkit

10k

A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceTypeScript2d ago

AI review

dsh-tool-describe-image

What it is — dsh-tool-describe-image is an image description tool for text-only models. It sends local paths, URLs or attachments to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.

Who it is for — When using text-only models in DeepSeek Harness on tasks involving image inputs, this plugin is suitable for installation. Users who rely on built-in vision capabilities in their models can choose not to install it, as they have native image support.

Watch out — Sandbox testing in a new profile showed successful installation and registration with no obvious pitfalls found. No issues were detected in static checks.

The verdict — I would install it because it allows text-only models to handle image inputs in the session.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

esp32-iphone-agent

onehumanbeing

4.4k

Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.

Installed cleanly when we ran it

GitHub sourceSwift11d ago

AI review

esp32-iphone-agent

What it is — Connects an OpenAI-compatible vision model to a physical iPhone: ESP32-S3 AirPlay for the screen, USB HID for taps, swipes, and typing.

Who it is for — You are inside DeepSeek Harness with an OpenAI-compatible vision model and need it to finish a live iPhone flow such as setting a repeating alarm, without a Mac, a developer account, or a jailbreak. Skip it when the phone is below iOS 18 or you have no flashed ESP32-S3 — the receiver and the HID device are simply not there.

Watch out — The phone joins the board's hotspot for AirPlay while model calls go out over cellular; AssistiveTouch stays on, and you supply the vision API key or token. The pointer is relative, so the app wiggles it to re-find and correct, and the plugin runs shell commands. A clean profile accepted the install and registered it.

The verdict — A green harness install is not a working phone; I would wait until TestFlight already shows a stable mirror and pointer before adding this plugin to a profile.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
2Source

modlens

liustack

4.4k

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

Installed cleanly when we ran it

npm packageTypeScript1mo ago

AI review

modlens

What it is — A DSH plugin that turns a pasted image into structured JSON evidence (OCR, reading-order layout, entities and relations) for text-only models.

Who it is for — You work in DSH on DeepSeek-V4-Flash, DeepSeek-V4-Pro, GLM-5.3, or MiMo Pro and need to inspect screenshots or scans those models cannot see. If your default route is already GLM-5.3-Flash or anything the host marks as native vision, skip it; those models are not wrapped and keep native paste.

Watch out — A clean-profile install registered with the harness. Reads reuse a Claude Code, Codex, OpenCode, or Pi login, or Antigravity CLI / Gemini / OpenAI-compatible keys; a free Gemini key is quoted at 5–10 seconds per read, with comma-separated keys rotating on auth, rate-limit, or quota failures. It executes shell commands. Capture hotkey is a separate plugin, dsh-screenshot.

The verdict — I'd keep it for the auto-wrapped (modlens vision) entries on every eligible provider route, including extras like opencode-go or zai, not because it ships any local vision runtime.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Installed cleanly when we ran it

GitHub sourcePython1mo ago

AI review

agent-vision-toolkit

What it is — CLI tools and a skill that let a text-only agent do multi-image Q&A, long-screenshot OCR, frontend restoration, and GUI automation.

Who it is for — You run DeepSeek in DeepSeek Harness, rebuilding UIs from mockups or driving a GUI, and the model never sees the pixels. If the agent you actually work in is already multimodal and can read a pasted screenshot, this CLI layer does not enter that loop.

Watch out — It installed on a fresh profile and the harness registered it. You pull it from GitHub source and the agent must be able to run shell CLIs. Seamless paste-in images need an extra local proxy; the ten structured DSH tools live in the dsh-vision-toolkit submodule and are absent until you init it.

The verdict — I would add it so vision sits in the harness and DeepSeek can stay the model I work with.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.

Installed cleanly when we ran it

npm packageJavaScript23d ago

AI review

dsh-vision-router

What it is — Gives text-only DeepSeek Harness agents a vision chain and pixel-level tools; enable Vision beside the composer, then attach an image.

Who it is for — You run a text-only model in DeepSeek Harness on error screenshots, UI coordinates, OCR, or mockup diffs, and the chat model cannot take pixels. Skip it if images must stay on the machine and you will not wire a local vision backend.

Watch out — In a clean profile it installed and harness registered it. A fresh install ships an anonymous OVHcloud fallback, so images or crops, the vision prompt, and request metadata leave the machine by default — no key is not offline. It also runs shell commands.

The verdict — I'd add it to the profile I already live in: seeing as a repeatable tool turn, not another chat window that accepts pictures.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

dsh-browser

omdsh-dev

809

Chrome sidebar extension that lets DeepSeek Harness operate your browser directly, no vision capabilities required. 一款 Chrome 侧边栏扩展程序,可让 DeepSeek Harness 直接操控您的浏览器,无需视觉能力。

Installed cleanly when we ran it

GitHub sourceTypeScript1mo ago

AI review

dsh-browser

What it is — dsh-browser is a Chrome sidebar extension that lets DeepSeek Harness directly control your browser without vision capabilities.

Who it is for — Users performing web page clicks, form fills and navigation tasks with models like deepseek-v4-flash benefit from this. People without browser interaction needs do not need to install it.

Watch out — Requires API key or token and shell command execution. Sandbox test passed in a new profile. Benchmark shows 5.32 s mean end-to-end latency, 20% faster than Playwright baseline.

The verdict — Not installing as I do not need browser control tasks; its value is limited to specific automation scenarios.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
2Source