Best · Curated
Best DSH Vision & OCR Plugins
Vision plugins give text-only coding agents image understanding, OCR and structured evidence extraction.
Editor's pick
Editor's pick
An editable diagram canvas in the DSH sidebar plus two agent tools (diagram_read, diagram_apply) that read and edit the workspace in place, using native .drawio files: the canvas opens and saves them losslessly — cells it does not understand are preserved byte-for-byte — and a file-fingerprint revision powers optimistic locking against concurrent edits.
Ranking
Tools & Capabilities plugin ranking
018616,530 downloads/mo027411,161 downloads/mo038710,331 downloads/mo04727,191 downloads/mo05857,191 downloads/mo06726,875 downloads/mo07795,449 downloads/mo08594,599 downloads/mo09694,057 downloads/mo10673,522 downloads/mo11643,286 downloads/mo12773,141 downloads/mo13672,757 downloads/mo14672,698 downloads/mo15692,666 downloads/mo16692,649 downloads/mo17642,250 downloads/mo18692,235 downloads/mo19772,180 downloads/mo20642,090 downloads/mo21671,992 downloads/mo22641,714 downloads/mo23721,611 downloads/mo24691,508 downloads/mo25671,456 downloads/mo26691,412 downloads/mo27741,315 downloads/mo28621,219 downloads/mo29671,207 downloads/mo30621,201 downloads/mo31691,174 downloads/mo32661,174 downloads/mo33641,139 downloads/mo34421,139 downloads/mo35711,095 downloads/mo36711,091 downloads/mo37541,037 downloads/mo38691,035 downloads/mo3959995 downloads/mo4061948 downloads/mo4166906 downloads/mo4259836 downloads/mo4366823 downloads/mo4434808 downloads/mo4569807 downloads/mo4664750 downloads/mo4764723 downloads/mo4874687 downloads/mo4964644 downloads/mo5066635 downloads/mo5164583 downloads/mo5261367 downloads/mo5366335 downloads/mo5461312 downloads/mo5566288 downloads/mo5661220 downloads/mo5766212 downloads/mo5861148 downloads/mo5968141 downloads/mo606371 downloads/mo61550 downloads/mo62550 downloads/mo63550 downloads/mo64570 downloads/mo65100 downloads/mo66550 downloads/mo67550 downloads/mo68590 downloads/mo69100 downloads/mo70620 downloads/mo71500 downloads/mo72620 downloads/mo73570 downloads/mo74550 downloads/mo75450 downloads/mo76270 downloads/mo77100 downloads/mo78650 downloads/mo79100 downloads/mo80550 downloads/mo81570 downloads/mo82100 downloads/mo83500 downloads/mo84100 downloads/mo85520 downloads/mo86500 downloads/mo87100 downloads/mo88590 downloads/mo89520 downloads/mo90100 downloads/mo91100 downloads/mo92520 downloads/mo93100 downloads/mo94400 downloads/mo95500 downloads/mo96550 downloads/mo97100 downloads/mo98650 downloads/mo99780 downloads/mo100100 downloads/mo
fourzkw/dsh-drawai
An editable diagram canvas in the DSH sidebar plus two agent tools (diagram_read, diagram_apply) that read and edit the workspace in place, using native .drawio files: the canvas opens and saves them losslessly — cells it does not understand are preserved byte-for-byte — and a file-fingerprint revision powers optimistic locking against concurrent edits.
Scorp1o117/dsh-plugin-marketplace
Browse and search GitHub dsh-plugin repositories from Web UI Settings, sort by stars, and install plugins through the DSH CLI.
czcdr/dsh-plugin-rea
Third-party adapter that registers the upstream REA (Reverse Engineer Anything) MCP server into DeepSeek Harness as mcp__rea__* tools. 2.x provisions its own runtime (Node, the REA CLI, a JDK, Ghidra) under <DSH_HOME>/plugins/rea-bundle and launches REA through a shim, so a machine with nothing pre-installed works after one setup run; 1.x (branch v1, npm 1.0.6) is configuration-only and expects REA and Ghidra to be installed already. Analysis is upstream's: native binaries (Hopper/Ghidra/IDA), JavaScript/Electron apps, .NET assemblies, websites, Android APKs and adb devices, firmware, and process captures.
qphotoai/dsh-computer-use-windows
Windows-ready DSH computer-use plugin with singleton host dependencies, safe UIA input, and CUA Driver vision fallback.
988hj7tczd-oss/dsh-computer-use
Cross-platform Computer Use for DeepSeek Harness: virtual-mouse human-like operation (screen_observe + computer_click + type + key + scroll + drag, 11 tools), AX-tree zero-vision-cost mode with free GLM-4V-Flash vision fallback, safety guards (snapshot TTL / app whitelist / dangerous-action approval / password-box protection).
lqq151510/dsh-computer-use
macOS computer use with eight computer_* tools: accessibility-tree and Vision OCR screen reading, actions by element index or visible label that also reach background windows, and CoreGraphics mouse and keyboard events with a resident low-latency daemon for game-grade input sequences; its Swift helpers compile on first use, so there is no runtime dependency.
lujianjun19/dsh-llm-github-copilot
GitHub Copilot LLM adapter: OAuth device-flow sign-in, live model discovery from the Copilot API, vision support for image-capable models (gpt-4.1, gpt-4o), and two wire protocols (Chat Completions and Responses API) with automatic endpoint routing per model.
csukingzq/dsh-pdf-translator
Windows PDF translator for DeepSeek Harness: a vision model locates and translates text, tables, figures and formulas; output is a Chinese PDF and a LaTeX source zip. Requires a vision-capable OpenAI-compatible API.
drscrewdriver/dsh-llm-openai-completions
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).
mokuyoaxis/dsh-iris
Media and vision workspace for DeepSeek Harness: image, video and speech generation, image Q&A and element locating, long-image OCR, pixel diff, HTML-screenshot verification and video summarization, with DashScope and OpenAI-compatible providers, model pools and a workbench client.
dsh-plugins/dsh-auxiliary
Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes. DeepSeek Harness 辅助模型插件:为视觉理解、上下文压缩、审批审查、子代理、会话标题与图片生成提供独立的模型路由、工具与系统提示,全程不触碰主对话模型。
gychen-NJU/dsh-game-daily
Daily game automation on Windows for Genshin Impact, Honkai Impact 3, Honkai: Star Rail and Zenless Zone Zero: a scheduled task per game drives BetterGI, the game-daily skill family, March7thAssistant or ZenlessZoneZero-OneDragon, with per-game switches, a foreground guard, in-run supervision that only steps in on trouble, and one report session per game that later results are appended to. Requires the DSH desktop app and the matching external engine installed.
Flyvhidbwo/dsh-vision-proxy
DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.
PerryLink/dsh-site-log-check
Checks supervision logs for cross-day continuity and for on-site supervision coverage, against GB/T 50319-2013 and other published documents. Reports gaps and coverage differences for a human to review.
heswy/dsh-video-editor
AI video creation and editing inside DeepSeek Harness, with conversation-driven revisions, multitrack timelines, audio waveforms, and MP4 export. Requires Node 22, FFmpeg and Chrome; audio generation calls a Qianwen MaaS endpoint only after you add an API key.
jiuaiwo/dsh-expert
Expert roster for DeepSeek Harness: 636 experts across 22 divisions with full Chinese names and bios, summoned as subagents from the @ menu or by the model through list_t_experts / summon_t_expert / summon_t_experts, plus custom experts and a skill on/off switch.
Ck-epsilon/aura-vision
Aura Vision - free vision OCR plugin for DeepSeek Harness web profile (permanent bundle, GLM-4V-Flash free tier, tile-based long-document recognition)
NOirBRight/dsh-llm-opencode-go
OpenCode Go subscription chat for DSH with per-model Completions, Responses, or Anthropic protocol selection, model discovery, context, vision and thinking metadata, effort defaults, and usage meters.
insideyou-0501/dsh-mech-workbench
A workbench for engineering and math problems, with nine tools for reading images, solving, plotting and verifying answers, plus four bundled skills. Needs Python with numpy and Pillow. Image reading, figure checking and formula typesetting rely on a vision provider you have configured a key for, so those images are sent to it, and without a key they fail while the other tools still work.
moon09300731/dsh-vision-tools
Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.
siegfly/dsh-deepseek-vision
A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.
LR611415/visionforge
Vision understanding + image generation/editing for DeepSeek Harness (read images with Qwen/OpenAI/Anthropic/Gemini, generate and edit with Qwen-Image). A rework of liustack/modlens (MIT). Remove @liustack/modlens first — both register the same vision providers and image interception hooks, so co-installation breaks image reading.
sunxin-ai/dsh-design-qa
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.
kaixinbaba/dsh-vision-recognizer
Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.
thanderming/dsh-auto-vision
Reads images with a vision model on the same provider when the selected model cannot see them, and passes that description to the text model.
Isanti2016/dsh-quicksight
Two-tier image reading for text-only models: fast local OCR (RapidOCR, offline) first, vision-model fallback (modlens).
AngelosZou/dsh-pdf-reader
A content-aware PDF reading plugin for vision models: profiles each page for figures (vector and raster), tables, formula risk and double-column layout, then applies content-aware hybrid extraction, rendering figure/table/formula pages as high-DPI region crops. Provides a low-resolution preview to understand the page layout, and renders a specified region at high resolution. Packaged as multiple tools for agents.
stallenlu/dsh-docx2md
Converts formula-bearing Word documents into Markdown with LaTeX, handling OLE equation objects, native Word OMML equations and image-based formulas; keeps equation numbers and structure. Needs Python 3.9+ (or uv); OLE and image formulas are transcribed by a vision-capable model from rendered images, and rendering needs Windows or LibreOffice.
Viger1/dsh-preview
Headless-browser verification tools so the agent opens the page it just built, reads the rendered DOM and computed styles, checks the console, and screenshots the result; ships a frontend-verify skill.
XXGJ666/dsh-feiyu-vision
Image understanding for DSH: describe an image and read the text in it through Zhipu GLM-4V (needs a Zhipu API key, free tier), with optional person identification through Volcengine Ark and anime-only reverse image search through SauceNAO or trace.moe (each needs its own key); ffmpeg must be installed for GIF/WebP input. Keys and the ffmpeg path are set on the plugin's own settings page.
xiaoshihou514/dsh-vision
Native vision capability extension, using either Zhipu (free) or Qwen-VL (local).
zzy6-a/vision-use
Desktop computer-use for DSH: captures the Windows screen into the agent vision channel and drives mouse/keyboard through a Codex-style overlay with Esc abort; auto-detects Windows native or WSL hosts.
charovo0059/dsh-model-vision
Fills in the vision capability that DSH's "fetch models" step drops, so image-capable models stop being declared text-only, and marks them in the model name.
vitas/dsh-ocr-free
Local OCR using Apple Vision on macOS: text from screenshots, photos, and scans, with no install, no network and no API key.
xie129716/computer-user-vision
Windows computer use forked from computer-user: 13 computer_* tools that read the screen and drive the mouse and keyboard. Image-capable routes get the screenshot as a real image with an exact image-to-screen mapping, so no external OCR; elements return as UI Automation refs so a click lands on the exact control rectangle; Ctrl+Alt+Esc stops every call.
GodD6366/dsh-sub2api
Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vision/image tools.
xuanyuanluoxue/computer-use-vision
Windows computer-use capability for DSH: screenshot → vision model → simulated mouse/keyboard with self-evolving knowledge base. Dual-mode plugin tools + skill-only pwsh fallback.
maxmilian/dsh-grafana-query
Read-only Grafana tools that query metrics through the data source proxy: instance health, data source listing, instant and range PromQL queries, current alert state, and provisioned alert rules. Range queries downsample to a point budget; an explicitly supplied step that would exceed it is rejected rather than silently changed, so the model never receives data at a resolution it did not ask for.
Elohia/dsh-plugin-image-input
Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).
hige6/imgpost
Let the DSH assistant send local, web, and AI-generated images directly to users in chat, with external vision support for text-only models. On Windows it runs through PowerShell.
ruby1304/dsh-vision-subagent
Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.
ld-1101/dsh-vision-plugin
Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).
SPYQWER1/dsh-codex-tools
Codex-backed `web_search`, `image_gen`, and `image_vision` tools for DeepSeek Harness, reusing ChatGPT OAuth login state.
bingbinggod369/dsh-skill-ballistic-simulation
Interior and exterior ballistics paper reproduction and code generation skill. Requires LibreOffice Kit for PDF rendering and a vision API key (e.g. Qwen-VL) for formula OCR.
gugu123a/dsh-tool-see-image
Provides the see_image tool for DSH: send an image file to a configurable OpenAI-compatible vision model and relay its description back to a text-only model.
1997liuyh-boop/dsh-desktop-tools
DSH Desktop toolkit with separate settings for each feature: a selection toolbar, a floating assistant, and screenshot, long screenshot and screen recording modes opened by global shortcuts from a toolbar at the top of the screen. Screenshots support shapes, pen, arrows, text and numbered markers, mosaic, pin to desktop, saving, and forwarding to a DSH conversation or the system share panel (Windows and macOS); recordings capture an area, a window or a full screen as MP4, GIF or WebM with optional system sound and microphone. Extract text, Translate and Knowledge graph on captures use the OCR tools of dsh-vision-router, which is installed separately (the settings page offers a one-click install). Requires DSH Desktop >=0.2.2-rc.1 <0.3.0-0. The features run in a separate Electron helper process and the plugin does not download Electron: with the installer build of DSH Desktop you must provide a standalone Electron through the electronExecutable setting, the DSH_DESKTOP_TOOLS_ELECTRON environment variable or $DSH_HOME/electron/; a DSH Desktop started from a bare Electron reuses it. System sound recording is not available on Linux.
wang-bool/visual-review
Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.
jyh20030112/dsh-visual-plugin
Gives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.
Junkrat9527/dsh-autovision
dsh-autovision: paste an image into a text-only model composer and a configured multimodal model transcribes it to text automatically. Twin-provider auto-routing + agent-callable read-image tool. No built-in keys, no relay.
XMoon/dsh-profile-settings
Per-profile settings overlay for DeepSeek Harness: global settings.yaml stays the baseline while each profile overrides any namespace through its own profiles/<name>/settings.patch.yml — object sections merge recursively, scalars and arrays replace wholesale, and !unset masks an inherited value. The overlay is transparent to existing plugins (they keep reading ctx.settings unchanged), writes land in the profile overlay only, and official schema validation, revision semantics, expectedRevision conflicts, watchers and events are untouched. Ships a settings command family (get/set/unset/mask/unmask/promote/demote/migrate/diff/layers) plus a Profile Settings section in the web Settings panel over a loopback RPC channel.
nyantused-cpun/gewu-tools
Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.
kmyy350234-dz/dsh-tool-drawer
On-demand tool groups for DeepSeek Harness, with optional role-scoped tool surfaces. Role masks are off by default; Settings can enable or disable review/build/research, and add custom roles with a group allow-list. The role key comes from the host's session label, subagent marker or preset, so an orchestrator's child agents each see only their own allow-list. Also auto-groups tool families by name prefix, lets the agent classify ungrouped tools once, restores a hidden tool when it is actually called, and reports per-session visibility health.
linenxi-ctrl/dsh-vision
External vision plugin for DeepSeek Harness: whale-button config panel, image recognition with auto-reply, and agent screenshot/recognize tools.
zhaoqiminggg/dsh-instruction-optimizer
Instruction optimization for DSH: an instruction optimizer that turns rough, colloquial drafts into complete, executable instructions, with prompt optimization, session context, multi-round revision, and attachment preservation.
Aik358/dsh-cua-pre
Windows desktop automation for DeepSeek Harness: accessibility-first observe/act loop with 30 standard tools (element/coordinate targets, auto/a11y/event strategy routing), superseded-observations and no-replay safety semantics, persistent kill switch, RuntimeId/rect-drift stale protection, chat cards and a floating panel (live ops, frame wall, env auto-detect settings), tiled vision describe for low-res models, JSONL audit trail and a pid allowlist. Requires Windows 10+ and Python 3.9+ with uiautomation and pillow (installable from the settings page).
Elohia/dsh-plugin-mm-vision
Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.
niyongsheng/free-vision-skill
Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.
Harzva/dsh-maclens
Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.
CZX2244/dsh-bilibili
Bilibili video analysis: metadata, transcript (ASR fallback via Bijian/sherpa-onnx/whisper.cpp), comments, danmaku, and sharp keyframes with optional local vision descriptions.
JohnXu22786/model-catalog
dsh plugin: model catalog auto-discovery - fetch model listings, pricing and capabilities from OpenAI-compatible API hosts, normalized into ready-to-use config
jagathsrujan/dsh-youtube-study-notes
Turns a YouTube link into study notes: pulls the captions the video already publishes, optionally reads on-screen content with a vision model, then asks for your own notes and merges everything into one document. Requires python3, ffmpeg and yt-dlp on PATH (the skill stops with an install hint when they are missing).
PerryLink/dsh-construction-doc-check
Checks a project document archive for missing required document types, stale revisions and empty files, using folder and file names rather than document contents.
fj7937290-sys/dsh-video-eyes
Read a video with a text-only model: with ffmpeg installed, sample frames at a 0.1-10 second interval into contact sheets where every frame carries its real timecode, extract the audio track and send it to iTingnao (needs an ITINGNAO_API_KEY) for a timestamped transcript, and describe each sheet with an image-capable model in the host, so the plugin works on its own without any other vision plugin. A composer slider sets the sampling interval, and pure audio files are transcribed without frame sampling.
DSH QQ Zone
Publishes and reads QQ Zone posts through SnowLuma's OneBot qzone_* actions (SnowLuma 2.2+ signed in to QQ), and lets the agent understand images with a local vision model (OpenAI-compatible gateway) or Windows OCR.
314857493/dsh-vision#vision-tool
Model-facing `vision` tool for DeepSeek Harness: describe and OCR image files by calling the free Zhipu GLM vision API directly (glm-4v-flash fallback chain), no external CLI required.
YangRuiYangDan/dsh-media-card
Show local images and short videos in the DSH conversation card with one-click download of the original file, or offer any other local file for download; works over local and remote connections and keeps the media itself out of the model's vision context.
hanwang-ai/quantitativeTrading-source-reliable
Registry of 119 quant and crypto sources covering regulator filings, point-in-time fundamentals, macro series, exchange APIs and on-chain data, each tagged with an authority tier, verification state, five-state point-in-time, revision risk and dataset tags; ships qt_source_find and qt_source_audit tools for source lookup and for citation audits that redact credential-like URL parameters.
boheastill/phone-eye
MCP server that lets an AI agent see and operate an Android device you own over adb, for app testing and automation. Vision plus UI-tree fusion, for any MCP client.
tinqiao-oss/clawtouch-mcp#dsh-clawtouch
Computer use through an external USB HID device: name a target in plain language, a vision model locates it in a cropped window screenshot, and a Raspberry Pi Pico 2 moves the real mouse and types on the real keyboard. 7 tools. Windows has window listing, per-window cropping and automatic window raising; macOS needs pyobjc and has neither; Linux is unsupported.
Linjiangxian0203/dsh-remote-tunnel
Remote host tunnel manager: runs dsh web on a remote Linux server (systemd supervision, no root needed) behind an auto-reconnecting SSH tunnel; allocates and registers remote ports on the server, multi-user safe, with an audit view.
yimengsuper2432/dsh-auto-convert
Prepares files before read, read_image and the vision tools open them: downscales images over 2048 px or 8 MB (one retry at 1280 px within the same turn), converts BMP/TIFF to PNG, relabels mislabeled uploads by sniffing their bytes, and turns docx/xlsx/pptx, text-layer PDF, csv/tsv and html into Markdown with no external programs.
maxwell-feng/dsh-windows-ocr
Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.
linkingoscar/dsh-attachment-formats
Codex-style attachment formats for the DeepSeek Harness Web GUI: PDF text-layer extraction, Office text extraction, scanned-PDF OCR, long-document spill + index cards, image-to-PNG.
azwosile/dsh-highres-vision
For the DeepSeek Harness native vision model deepseek-v4-flash-vision-exp, raises image admission limits to 32 MiB / 8192 px / 600 images and adds a highres_read tool that tiles large images, then returns the whole image plus 800x800 tiles through the host read_image tool.
tedcriss/dsh-matlab
Connector for MathWorks' official MATLAB Agentic Toolkit skills and the MATLAB MCP Server. Requires a local MATLAB R2021a or later. Skill groups can be enabled individually on the settings page. The toolkit is provided by MathWorks' official repository https://github.com/matlab/matlab-agentic-toolkit; the trigger rate for MATLAB-related operations is over 90%, and it calls the native MCP server, so your AI works in a fully standardized way. Its HTTP routes have no DSH access check, so a web page open in your browser could call them. By default (autoProvision) it downloads the MathWorks MCP Server binary and the newest Agentic Toolkit release on first use; MathWorks telemetry is disabled by default.
xiaoyuink/dsh-image-vision
Image understanding for any DSH model: vision, OCR, grounding, and crop tools with domain presets for histopathology, cell biology, anatomy, clinical images and scientific figures.
BoltBlue121/dsh-moss-draw#plugin
Adds seven `art_*` agent tools plus a right-sidebar drawing workbench (series, pages, revisions, regions, camera blockout) that submits ComfyUI graphs to a ComfyUI instance you host, for MOSS/K2 text-to-image, inpaint, character references, region editing and Qwen-Image edits, with up to four caller LoRAs stacked per request. Requires a local checkout and one adapter step: after a marketplace install, run `install/adapt.mjs` (or use `install/install.ps1` on Windows) to replace the `__MOSS_*__` placeholders with an absolute `workspaceRoot` and a ComfyUI origin; until then the Host refuses to load the preset with `MOSS_CONFIG_*`.
Scodive/Paper-Agent-Skills
Evidence-aware research writing skills for DeepSeek Harness: academic paper revision against supplied experiment records and references, rebuttal preparation, and presentation storyboarding, each with bundled Python tools that package the evidence and check the edits locally.
TZHR-invest/dsh-plugins#dsh-vision-tool
Agent-callable vision tool that describes local images via any OpenAI-compatible vision endpoint you configure, with an optional multi-model cross-check and no built-in keys.
dingchenhui0618-arch/dsh-vision-diff
Pixel-level screenshot diff for visual regression. Two local PNGs in; a machine-readable first line (`PIXEL_CHANGED=true|false`, greppable as an assertion), then the difference ratio, per-region bounding boxes, maximum channel delta and mean absolute error, plus a self-contained HTML comparison page. An ignore-region list with absolute or fractional coordinates excludes clocks, cursors and other per-render noise. It deliberately does no content recognition: it answers only "did this change", which is the part that can be made deterministic. Entirely local — no model call, no network, no upload.
NagasakiSoyo-ui/dsh-llm-deepseek-vision
Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description
ankye/dsh-client-vision#tool-vision
Screen capture and external vision recognition: take_screenshot, list_windows, analyze_image and view_image tools with a configurable GPT vision channel (gpt-5.5 / gpt-5.6-sol / gpt-5.6-terra), API key via the credentials service, and a settings card; view_image shows the screenshot in the Web UI while the model context keeps text only.
wmk66ds/dsh-vision-unlock
Removes the model-capability gate that blocks image prompts: patches llm.resolveModelInfo results and adapter model tables to declare image input, so routes with no declared input modality can send and read images. No app.asar or config-tree edits.
yuna78/dsh-deck-studio#deckline
Chat-driven image-deck workbench for DSH: intent to storyboard script, per-page prompts and AI image generation with page-level revisions, nine design-style presets, and PDF/PPTX export (one full-page image per slide).
shinjiyu/dsh-plugin-multimodal
Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.
Renji004/dsh-omni-vision
Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.
GOU-GEE/deepseek-vision#plugins/dsh-plugin-deepseek-vision
Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.
maxwell-feng/dsh-tesseract-ocr
Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.
Kalospacer/dsh-model-capabilities
Adds a settings page for declaring per-model reasoning efforts and vision support on pi-ai provider routes.
zhiqiangme/dsh-plugins#archive/dsh-opencode2api
Runs the standalone opencode2api backend (jasonxu114514/opencode2api, Windows x64/ARM64, no Docker or OpenCode CLI) with DSH and on exit stops only the process it launched; its settings card installs, updates or rolls back the backend from checksum-verified GitHub releases, copies the initial admin password and syncs /v1/models into an opencode2api provider with context, vision and reasoning efforts, re-syncing every 10 minutes. Frozen archive: 26.10.31 is the last version, and the author points to dsh-magpie as the replacement.
zhiqiangme/dsh-plugins#dsh-opencode2api
Runs the standalone opencode2api backend (jasonxu114514/opencode2api, Windows x64/ARM64, no Docker or OpenCode CLI) with DSH and on exit stops only the process it launched; its settings card installs, updates or rolls back the backend from checksum-verified GitHub releases, copies the initial admin password and syncs /v1/models into an opencode2api provider with context, vision and reasoning efforts, re-syncing every 10 minutes.
mengge237/dsh-model-priority
Reorder your own models: drag inside a provider card on the Models settings page, or use the Model order section when another plugin already occupies that card. The order is written through the host settings service with a revision check, so the settings page and the model picker stay in sync. The settings left nav can be reordered by drag as well.
littleblakew/msds-chain-mcp#dsh
Chemical safety intelligence through the hosted MSDS Chain MCP endpoint: 23 tools for compatibility and mixing order, GHS hazards, PPE, storage, waste disposal, exposure limits, transport classification, multi-region regulatory compliance, SDS lookup and version diffs, and signed audit reports, each answer citing the supplier SDS and revision date it is grounded in.
br1nosense/dsh-vision-solution
Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.
Daphne999/dsh-media-kit
Pull frames and audio out of a local video with ffmpeg and hand back plain file paths, so the agent can look at the frames with its own vision. Five tools: probe, evenly spaced frames, one frame at a timestamp, scene-change frames (the practical version of frame-by-frame), and audio extraction. No models, no uploads, no routing guesswork.
Fucaplos/dsh-local-library
Local document library for DSH Desktop (Windows only, installed with the bundled PowerShell script): upload files once, then every conversation can search and read them through four tools (library_list / library_search / library_read / library_save); upload, download and batch download live in the Settings panel. Files stay on the machine unless you enable the optional vision model, which sends images to the endpoint you configure.
314857493/dsh-vision#vision-route
Registers a `deepseek-vision` provider route: the Web GUI accepts pasted images and transcribes them to text via the free Zhipu GLM vision API before delegating to the DeepSeek adapter.
StvLi/dsh-ros2
ROS2 debugging toolset and robot-state vision analysis for DeepSeek Harness: node/topic/service/action/interface/TF enumeration, whole-graph topology JSON, rosdep checks, approval-gated builds and custom message scaffolding, GUI screenshots and multimodal vision observation, plus headless RViz2 offscreen rendering (low-poly meshes, direct pixel read, GPU passthrough - motion rendering at 30Hz) with parallel VLM realtime analysis.
luobosibing2/dsh-jev-plugin
Integrates TypeSafe Jev for skill and file selection, task supervision, shared-finding corrections, tool-output filtering, approval assistance, and recorded-stage navigation in DeepSeek Harness; all features are disabled by default.
xing666173/dsh-vision-hub#file-drop
Drag-and-drop file upload for PDF, Word, Excel and images: dropped files are saved to a local directory and referenced by path, no base64 bloat in the chat.
View all Tools & Capabilities plugins Tools & Capabilities,Back to leaderboard dshplugins.cc。