DSH Marketplace

The catalogue

Vision & Multimodal

Synced from the community registry and the dsh-plugin GitHub topic. Star counts and last-push dates come straight from GitHub.

534 plugins

84% install-verified on DeepSeek Harness 0.2

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 packageJavaScript24d 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

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.

DeepSeek Harness 0.2.2-rc.1 refuses the latest release

npm packageTypeScript23d ago

AI review

dsh-vision-toolkit

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.Read the source
Details

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
512

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

GitHub sourcePython1mo ago

AI review

watch-skill

What it is — Watch Skill is a local-first perception and verification stack that lets AI agents understand video, audio, and screen activity while generating timestamped evidence for independent tool verification.

Who it is for — When building or running agents with DeepSeek Harness that require observing screen activity and verifying tool execution, Watch Skill fits your needs. It supports integration through MCP, CLI, and REST interfaces. Developers who do not need to separate perception from verification can skip it.

Watch out — Installation must come from GitHub source. The plugin executes shell commands. Sandbox testing passed: installed into a fresh profile and registered into the harness profile. No obvious pitfalls were found.

The verdict — I would install it because it provides independent deterministic verification to ensure agent tool results are accurate.

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

filens

IceWhaleTech

253

📄 Office / PDF / iWork / CAD / 3D / RAW / 360° 🔒 Browser-local preview & conversion 🤖 Agent CLI with OCR, structured text & layout extraction ⚡ Rust + WebAssembly 🧩 Vue 3 integration. Open-source, local-first. Your files, your device.

Installed cleanly when we ran it

GitHub sourceTypeScript13d ago

AI review

filens

What it is — filens is a local-first Agent CLI that supports file OCR, search and preview.

Who it is for — When your Agent needs to process complex files like Office, PDF and CAD for OCR and structured extraction, filens is suitable. Developers who do not prioritize local-first file handling can skip installation because filens keeps files on your device.

Watch out — Installation from GitHub source requires manually allowing the build script. Sandbox test passed with successful registration in a new profile. No obvious issues found.

The verdict — I would install it because the sandbox test confirmed successful registration and no issues, but the premise is accepting the source-based installation with build script approval.

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
Source

dsh-see-now

SAOS-3624

170

Lets a text-only agent watch a live screen or camera feed: every frame is scored by how much the picture changed, only the ones that matter are packed into one numbered sheet with an audio envelope, so the model looks at what actually changed instead of a screenshot every few seconds.

Installed cleanly when we ran it

npm packageJavaScript14d ago

Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.

Installed cleanly when we ran it

GitHub sourceShell22d ago

AI review

deepseek-harness-docker

What it is — DeepSeek Harness Docker packaging provides hardened image, Compose stack, Helm chart, Web UI and headless CLI for containerized deployment using official npm release in Node.js 24.

Who it is for — It is suitable when running DeepSeek Harness Web UI in Docker needs persistent profile, sessions and workspace. Users requiring only headless mode or without container boundary needs are not suitable.

Watch out — Manual build script approval is required from source installation. Shell commands are executed. Sandbox testing passed in a new profile and registered by harness.

The verdict — I would install it because it handles official release container boundaries like PTY and host binding without forking upstream.

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
131

AI image generation for the DSH Web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with an api_url/api_key settings card and a sidebar split-pane generation studio.

Installed cleanly when we ran it

npm packageTypeScript28d ago

AI review

dsh-imagegen

What it is — Integrated AI image generation plugin for DeepSeek Harness Web GUI, supporting text-to-image and image-to-image.

Who it is for — Users requiring image generation in DeepSeek Harness Web GUI are suitable to install this plugin. Users not using the DSH host process for API proxying need not install this plugin.

Watch out — Sandbox test passed in a fresh profile after installation and registration. API URL and key must be configured in the settings card. No obvious issues found.

The verdict — I would install it because it supports cross-device sharing of image history records.

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

Photo-to-editorial Skill with Original (Codex) and V3 Adaptive editions. Scene-aware layouts, creative controls, Strict Fidelity composition, structured QA, and a validated DeepSeek Harness capability path.

Installed cleanly when we ran it

GitHub sourcePython22d ago

AI review

photo-abstract-editorial

What it is — Converts a photograph into an editorial composition with original photo, abstract memory panel, and poetic English title.

Who it is for — When using DeepSeek Harness for photo editing tasks requiring scene-aware layouts and creative controls, this plugin is suitable. If you want the fixed Codex-only workflow without adaptive features, you do not need this plugin.

Watch out — Sandbox test passed: installed in a new profile and registered by Harness. No obvious issues found.

The verdict — I would install it because it includes a validated DeepSeek Harness capability path for photo-to-editorial tasks.

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

dsh-comfyui

fandc520

115

Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object_info / comfyui_workflow tools generate and edit images and videos, with a workflow library (graph extraction: per component / main flow / all), a load area with resolution auto-match, a live queue, SDXL and Wan 2.1 templates, a companion skill, and a same-origin media proxy.

Installed cleanly when we ran it

npm packageTypeScript1mo ago

DSH-Spicy

kingcharleslzy-ai

92

完美适配 Purge 的 NSFW content creation 插件。在 DeepSeek Harness 中用自托管模型创作成人向图像、有声视频与多镜头短片,支持参考图编辑、LoRA 风格控制和 Agent 分镜剪辑。

Installs, but needs a build approved first

GitHub sourceTypeScript3d ago

dsh-qwen-paint

wonderandyou

66

DSH 插件:在对话里调用本机 ComfyUI,用千问 Qwen-Image 2.1 出图。纯本地、不出网、不需要 API Key。

Installed cleanly when we ran it

GitHub sourceJavaScript1mo ago

DeepSeek Harness 素材浏览插件:按工作区查看 MUSE AV 素材与出图记录,复制素材直链。DSH asset browser for MUSE AV workspaces, image libraries and generation history.

Installed cleanly when we ran it

npm packageJavaScript29d ago

dsh-directorx

LaplaceYoung

46

DirectorX as a DeepSeek Harness plugin: AI video/image/audio skills, knowledge corpus, and configurable vision/image/video/audio model tools.

Installed cleanly when we ran it

GitHub sourceJavaScript1mo ago

AI review

dsh-directorx

What it is — DirectorX is a DeepSeek Harness plugin integrating AI video/image/audio skills, knowledge corpus, and configurable vision/image/video/audio model tools.

Who it is for — When making multi-shot video projects in DeepSeek Harness that require storyboard planning and editing, this plugin provides the necessary tools. For users who only need simple one-time generation without canvas or editing workflows, this plugin is not required.

Watch out — Sandbox test passed: Installed in a new profile and registered into the profile. No obvious pitfalls found.

The verdict — I would install it because it enables local ffmpeg-based editing that can be iterated without re-generating, but only if confirmation is done before placing on canvas.

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

dsh-design-qa

sunxin-ai

44

Design-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.

Installed cleanly when we ran it

npm packageJavaScript27d ago

AI review

dsh-design-qa

What it is — The dsh-design-qa plugin enables text-only models in DeepSeek Harness to read images using the deepseek_vision tool.

Who it is for — If you need to have the model judge whether an implementation matches its mock in DeepSeek Harness, this plugin is suitable. If you do not have an OpenAI-compatible vision route, you cannot use this plugin.

Watch out — Sandbox testing installed and registered in a new profile. The plugin will execute shell commands.

The verdict — Provided that the model supports tool calling, I would install it because it includes the benchmark and questioning discipline needed for the judgment.

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

Turns a video (a local file, or a Bilibili/yt-dlp link) into one addressable storyboard grid — numbered cells with exact timestamps, per-cell transcript and an audio envelope on the same timeline — and video_zoom re-reads any window at higher resolution, so a text-only model can look at the video instead of reading a summary.

Installed cleanly when we ran it

GitHub sourceJavaScript20d ago

dsh-qwen-paint

yanfei0725

38

面向 DeepSeek Harness 的本地图像生成插件(优化版):经本机 ComfyUI 调用 Qwen-Image 2.1 生成图像,全部流量限于 127.0.0.1。本版增强推理性能、NVIDIA/Intel/AMD 显卡适配与 Windows/Linux 兼容。原作者 @奇迹与你,优化版 @yanfei0725。

Installed cleanly when we ran it

npm packageJavaScriptyesterday
36

Image "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.

DeepSeek Harness 0.2.2-rc.1 refuses the latest release

npm packageJavaScript1mo ago

AI review

picturereader

What it is — picturereader gives text-only models the ability to read images by converting them into text grids via downscaling and color reduction.

Who it is for — When using text-only models such as DeepSeek to analyze images, picturereader is suitable. Users performing purely text tasks do not need it because they require no visual information input.

Watch out — Sandbox testing passed, with successful installation and registration into the profile by DeepSeek Harness. ZCode version has additional overhead from MCP process communication. No other obvious issues found.

The verdict — I would install it because it provides an image-reading methodology skill verified through extensive real image iterations, enabling text models to autonomously verify image content.

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

DSH-vison

hisence999

35

DSH-vison is a DeepSeek Harness plugin that adds image understanding for text-only models by converting images into descriptions from a configured vision-capable model.

Installed cleanly when we ran it

GitHub sourceJavaScript3mo ago

AI review

DSH-vison

What it is — DSH-vison provides image understanding for text-only models by converting images into descriptions from a configured vision model.

Who it is for — When you use a text-only model to process user messages containing images, you need image understanding capability. If you use a multimodal model, you can skip installing this plugin.

Watch out — Sandbox test passed: it was installed in a fresh profile and registered by harness. No obvious pitfalls found.

The verdict — I would install it because the sandbox test passed and it enables global image handling for text models.

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
LINUX DO1Details

dsh-vision

william-jin-cmu

30

dsh 插件:给纯文本 DeepSeek 加视觉——view_image 工具桥接任意 OpenAI 兼容 VLM(默认智谱免费档,实测 4 厂商 10 模型)

Installed cleanly when we ran it

GitHub sourceTypeScript3mo ago

AI review

dsh-vision

What it is — dsh-vision plugin registers view_image tool to bridge any OpenAI compatible VLM for text-only DeepSeek.

Who it is for — When using DeepSeek-V4-Flash to describe desktop images in DSH web, install dsh-vision. Users without need for visual analysis can skip this plugin.

Watch out — Sandbox test passed: installed in new profile and registered by harness. Source install requires manual linking of host dependencies. No obvious pitfalls found.

The verdict — I would install it because it enables DeepSeek-V4-Flash image description, but only after configuring the backend apiKey.

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