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.
Install
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
Installed cleanly when we ran 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 ago.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
What it is — DSH Vision Toolkit enables text-only models to process images for Q&A, OCR, UI reproduction and related visual tasks.
Who it is for — When using text-only models in DeepSeek Harness web for screenshot analysis, element grounding or multi-image comparison, this plugin is suitable. Users with native vision models do not need this to enhance text models.
Watch out — No obvious issues found in sandbox testing. Images are processed by the author-hosted free service with 100 per machine per day by default, configurable to your own provider.
The verdict — I would install it because it integrates vision tools natively into DeepSeek Harness profiles and sessions.
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.
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.
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.
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:
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.
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
zhu1090093659
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.
Installed cleanly when we ran it
liustack
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
Installed cleanly when we ran it
Anionex
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
ysr666
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
omdsh-dev
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
oxbshw
DeepWatch, powered by Watch Skill: a local-first perception and verification stack for AI agents. Understand video, audio and screen activity, keep timestamped evidence, and independently verify what a tool or workflow actually did. MCP, CLI, REST, Web and DeepSeek Harness.
Installed cleanly when we ran it
