vision

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.

Near-native image understanding for DeepSeek Harness

给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。

Free image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2 / v0.1.2-alpha.3) — paste-image reading with auto vision transcription, DeepSeek-V4-Flash-Vision-Exp / GLM-4V-Flash / SenseNova / Gemini failover, Kolors + U1 Fast generation. No keys in repo.

Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the benchmark behind that judgement — four fixtures, 23 injected defects, and every raw model transcript. Retires itself when DeepSeek ships vision.

Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel

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。

Auxiliary model system for DeepSeek Harness: unified aux-LLM routing (per-task model, timeout, concurrency, failure cooldown, main-model fallback) + vision_analyze / web_extract / compress_text tools, settings page, and session image lifecycle cleanup.

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.

DeepSeek Harness 插件：DeepSeek Pro 大脑 + 自动识图。GUI 附加图片默认经官方 deepseek-v4-flash-vision-exp 原生识图，转译成文字后交给 DeepSeek 作答（纯文本的 V4-Pro 也能看图）；支持百炼/智谱/OpenRouter 等任意 OpenAI 兼容 VLM，无 key 自动探测本地 Ollama；安装时有一问式确认

DeepSeek Harness 插件：让 deepseek-v4-flash 等不能看图的模型也能处理聊天图片，内置识图工具。安装：dsh plugin --profile web add dsh-image-pathify

see_image tool for DSH: lets text-only models 'see' images by routing them to a configurable vision model (default Zhipu GLM-4V-Flash, free)

A lightweight DeepSeek Harness vision delegation tool for text-only routes, with native OpenAI Responses, Chat Completions, and Anthropic Messages adapters.

Free GLM vision for text-only DeepSeek Harness: paste images in the GUI (auto-transcribe route) + vision tool + skill

为 DeepSeek Harness 增加外挂识图模型：圆形鲸鱼按钮、发送图片识图自动回传、模型自主截图+识图工具、多协议自动适配、小白一键安装（未装 Node.js 自动下载）

DSH 插件:图片与文件直达纯文本模型——图片保留原生附件体验,PDF/Office/压缩包/视频/音频显示为附件栏方块,点击发送时自动转为工作区路径,配合 dsh-vision-toolkit 粘贴即看图。A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep the native attachment UI, other files show as square chips in the rail, paths append on send — pairs with dsh-vision-toolkit.

一个工具 = MiniMax 全部多模态能力：DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover/search/quota) for DeepSeek Harness (DSH)

DSH 轻量截图插件：轻 ： 纯 PowerShell 实现，零依赖、零二进制；截图能力独立维护，不随任何上游更新而失效。 摆 ：一键全屏即拍；框选前整个桌面保持可操作，所有窗口像布置画面一样自由移动、缩放；鼠标悬停任意窗口即亮起吸附边框，点一下直接截该窗口，被遮挡也能拿到完整内容，所得即所见。 自助：Agent 可随时自行截屏；接上 modlens（选装），截屏 + 识图一步产出结构化内容（OCR/版面/语义），纯文本模型也能消费。

Local OCR, color-statistics, pixel-scan, and metadata bridge for text-only DeepSeek Harness models; no external vision API.

图片识别插件 for DeepSeek Harness：自动判断当前模型识图能力，支持多供应商视觉模型管理与检测

DeepSeek Harness 视觉增强插件：将图片交给外部视觉模型分析，输出带坐标化视觉原语的纯文本证据，使不支持多模态的文本模型也能在对话中理解图片、截图与文档。

Vision for DeepSeek Harness: Doubao Web by default (zero-cost, no API key), Antigravity IDE quota (flash/pro), any IDE CLI, Gemini — auto detail escalation, evidence memory

专供 deepseek-v4-flash-vision-exp 的高清识图增强插件：放宽 DSH 图片限制 + highres_read 分块识图工具。

为DSH（DeepSeek Harness）量身打造的视觉插件，现已支持agent调用图片显示/Vision plugin for DSH(DeepSeek Harness),support Proactive Image Display.

Silent vision bridge for DeepSeek Harness: route chat images to a fixed vision model, preserve UI originals, and reuse observations across compaction and restarts.

DeepSeek Harness 图像理解插件 · 8 种分析模式 · 支持任意API接口 · 内置免费视觉模型 | DeepSeek Harness vision plugin · 8 analysis modes · works with any OpenAI- or Anthropic-compatible API · built-in free vision model

为 DeepSeek Harness（DSH）里的每一条模型路由做图片模态调度，并且贯穿整个 agent

Universal vision bridge for DeepSeek Harness: multimodal attachments with text-only chat models

Media generation and visual understanding for DeepSeek Harness, with multi-provider routing and the integrated Iris workbench.

On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

DeepSeek Harness plugin: describe_image — give a text-only model vision through an OpenAI-compatible VLM endpoint

该仓库暂未提供项目说明。

DeepSeek Harness plugin that bridges session images to pluggable vision APIs while keeping DeepSeek as the primary model.

DSH 插件：让纯文本模型也能看图。Web 端直接粘贴图片即可发送，无需指定图片路径；模型自主调用视觉技能查看，多模态模型原生直通，零skill绑定。

Paste images into DeepSeek Harness with a four-model vision race, OCR, and an automatic text bridge.

Vision for text-only LLMs in DeepSeek Harness (DSH): describe images / OCR / VQA via free Gemini & GLM vision APIs

DeepSeek Harness EAC 视觉全家桶:15 个像素级视觉工具(增强版 dsh-tool-vision)+ 桥接内联预览 + 拖拽文件上传,单端点驱动,对话干净,EAC 原生设置适配

Vision skill plugin for DeepSeek Harness (image analysis and OCR)

给 DSH 文本模型装眼睛：图片自动调用 mmx（MiniMax VLM）识别，识别结果注入模型上下文

在dsh中接入智谱 GLM 视觉模型，让 DeepSeek 等文本模型通过 glm_vision 工具看图。

Bridges images into text for non-vision DeepSeek Harness models — your message stays untouched, zero manual setup.

Official enhancement suite for DeepSeek Harness — Vision, Soul/Persona, Long-term Memory & Plugin Marketplace.

DeepSeek Harness (DSH) 自主视觉插件 —— 给智能体屏幕/窗口视觉 + 电脑使用能力（see/ocr/list_windows + 鼠标键盘操作），跨语言调用捆绑的 Python cvision，Windows / macOS 可用。

DeepSeek Harness usage dashboard with API balance, daily spend, external vision-call accounting, per-model stats, call logs, cache rate, TTFT, and CSV export.

【已停止维护】DeepSeek Harness 视觉桥接插件：新版 Harness 已原生支持图片识别，请使用原生能力，本仓库仅作历史参考。

DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.

本地 OCR 插件：让纯文本生成 LLM 也能读懂图片 | Local OCR plugin: give text-only generative LLMs the ability to read images

Vision routing and image generation for DeepSeek Harness through a fixed Mix model.

给 DeepSeek 安装一双眼睛和一支画笔:会话里直接贴截图/图片,GLM 视觉模型先精确转写图片内容(报错信息、代码、界面逐字保留),然后 DeepSeek 继续处理你的问题——同一轮完成,全程无感;需要配图时,DeepSeek 自动调用文生图后端出图并显示在会话中。

在DeepSeek Harness网页中控制鸿蒙手机并让AI识别内容

Vision sidecar for DeepSeek Harness: accept pasted images on text-only models.

Eyes for text-only DeepSeek on DeepSeek Harness: model-invokable vision tool + wrapper adapters + general VLM channels (OpenAI-compatible / Gemini / local Ollama)

Native vision, gpt-image-2 and Seedance plugins for DeepSeek Harness via Xiapan Cloud

Plug-in vision for text-only DeepSeek Harness (dsh) models: built-in free/cheap VLM presets + multi-image batch analysis

Config-only DeepSeek Harness bundle for OpenAI-compatible vision models.

DSH plugin: text-only models (e.g. DeepSeek-V4) automatically see images via a vision model. Official surface-replace, cache-friendly, human transcript untouched. 纯文本模型自动识图桥

DeepSeek Harness 识图插件：为不具备原生识图能力的模型提供识图能力（阿里云百炼 qwen3.5-omni-plus，失败自动切换智谱 glm-4.6v-flash）。由 claude-vision-skill 移植适配。 | Vision tool for DeepSeek Harness

DeepSeek Harness plugin for image upload, in-chat rendering, and vision analysis with cloud or local models. 图像上传、显示与解析。

Model-agnostic Computer Use for DeepSeek Harness: isolated browser, Windows native helper, third-party vision perception, and a Chrome Cookie Bridge.

DeepSeek Harness all-in-one: no model switching — regular DeepSeek auto-routes to vision & image gen. Multi-backend: Gemini + any OpenAI-compatible (GPT-4o, Qwen-VL, GLM-4V, gpt-image, DALL-E, Flux, OpenRouter). gemini_vision/gemini_generate_image/gemini_optimize_image with vision self-check. Better than modlens.

DeepSeek Harness plugin: turn UI screenshots into structured, implementation-grade web frontend specs. Deterministic geometry (sharp) + optional vision-model semantics, merged into one JSON + Markdown spec.

Reliable vision + OCR for text-only models on DeepSeek Harness: describe_image (normal/critical) + extract_text tools, auto-preprocessing, retries, and a persistent answer cache.

Let your AI agent see and operate a real Android phone — vision + UI-tree fusion over adb, for any MCP client (Claude Code, Codex, dsh…)

DeepSeek 的"自动挡"：有图切 Vision，无图回 Pro/Flash，一键都不用点。 DeepSeek's "automatic transmission": image in → Vision, image out → back to Pro/Flash — not a single click.

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

DSH plugin: text-only chat models get local Ollama VL image descriptions (qwen3-vl:8b), VRAM cooling

DeepSeek Harness plugin - session screenshots route by model capability: inline for vision models, VLM-read for text-only models (tool/auto modes)

DeepSeek Harness (dsh) 官方 bundle 规范插件集合: dsh-vision 看图 + dsh-sensenova-image 生图 + dsh-client-stats-decimal 统计两位小数

给 DeepSeek Harness 纯文本模型加视觉：采用codex风格聊天框拖图自动分流给用户配置的视觉模型转文字，v4 不切换模型即可识图。 Vision for text-only DSH models: routes chat-box images to a user-configured vision model and returns text descriptions, deepseek-v4-pro reads images without switching.

DeepSeek Harness (DSH) plugins. qwen-image gives a text-only coding model eyes: an image goes to a Qwen-VL route through ctx.llm and comes back as text, so DeepSeek keeps coding while Qwen looks. Pure ESM, no build permission at install. | DSH 插件集：qwen-image 让纯文本模型借千问 VL 读图，返回文本；纯 ESM，安装无需构建授权。

该仓库暂未提供项目说明。

该仓库暂未提供项目说明。

DeepSeek web vision bridge plugin for DeepSeek Harness (DSH)

Aura Vision - free vision OCR plugin for DeepSeek Harness web profile (permanent bundle, GLM-4V-Flash free tier, tile-based long-document recognition)

GLM-4.6V 图像理解 MCP：识图/OCR/图表解析，原生接入 DeepSeek Harness（dsh-mcp-client），也兼容 Codex/Cline 等

Local-first vision for DeepSeek Harness: structured JSON evidence (OCR/layout/semantics) from local VLMs (LM Studio/Ollama), zero API cost, images never leave your machine.

DeepSeek Harness (DSH) 本地视觉眼睛插件:screen 工具(截图/图片交给本地视觉模型描述)+ ocr 工具(Windows 内置 OCR 逐字提取文字)。零云端、OCR 零 GPU、图片不出本机。

DSH 自建插件集合：微信桥接器 + GUI 微信入口补丁，一键安装

DeepSeek Harness（DSH）视觉插件：Edge+豆包网页版识图，零成本免 API Key。通用识图 + 数学建模图专项（几何/流程图/图表/表格/公式）+ 不确定项澄清闭环。Vision plugin for DeepSeek Harness: image understanding via Edge + Doubao Web, zero cost, no API key. General recognition + math-modeling diagrams (geometry/flowcharts/charts/tables/formulas) + clarify loop for uncertainties.

DeepSeek Harness 识图插件：保持 DeepSeek 对话，15+ 供应商视觉模型把图片转译为文字，可在 设置→插件 配置

Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, and GUI automation, through layered evidence memory and cache.

A DeepSeek Harness tool plugin that lets text-only agents "see" local images — auto-detects the real format and returns a detailed text description via any OpenAI-compatible vision model.

Give text-only DeepSeek models on-demand vision: upload images, DeepSeek answers by calling a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).

DeepSeek Harness vision plugin: analyze_image (structured OCR evidence) + capture_image (USB camera visual loop). 摄像头视觉闭环 + 结构化证据，支持 Ollama / DeepSeek / Xiaomi 三后端。

Transparent image preprocessing route for DeepSeek Harness

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

DeepSeek Harness 视觉桥：自动发现你已配置的多模态模型，给纯文本主模型装上 vision 工具，识别结果以纯文本返回。零配置，一条命令安装。

DeepSeek VisionPlus — official-grade vision extension for DeepSeek Harness. Routes image understanding to a free vision-model pool (Zhipu GLM, SiliconFlow Qwen) with automatic fallback, rate limiting, one-click platform tests and live status lines; text stays on DeepSeek. One-command install. MIT.

Qwen-MM-Plugins integration bundle for DeepSeek Harness (dsh) — multimodal MCP tools (vision, OCR, ASR, search, video, Blender, FreeCAD) + image attachment bridge. 让 DeepSeek Harness 原生支持多模态。

DeepSeek harness多模态插件，接近原生体验。

Scene-aware vision routing layer for DeepSeek Harness (dsh): decides which engine/backend an image should go to (chat/UI/table/code) before other vision plugins route it. Switch-gated, front-loaded, never touches other plugins' tools. 场景级识图路由层。

Route-preserving image understanding for text-only models in DeepSeek Harness (DSH).

让你能通过deepseek harness调用LM studio加载的本地视觉模型

Browser tool for DeepSeek Harness that can SEE the page: browser-use over CDP driven by deepseek-v4-flash-vision-exp. Reads canvas text, text inside images and rendered charts, returns schema-validated JSON, and reports per-run cost.

DSH plugin: image_describe (识图) tool over the DashScope OpenAI-compatible vision API (qwen3.7-flash). Bring your own DASHSCOPE_API_KEY.

Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.

DeepSeek Harness Vision Helper/DeepSeek Harness 视觉辅助方案

Native interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid / zoom / annotate / measure / diff / color / OCR) + MiMo V2.5 multimodal backend, zero external MCP servers.

DeepSeek Harness (dsh) 模型视觉开关插件：为自定义模型声明图像输入能力（写入 llm-pi-ai 配置），适配 0.1.x

Give your DSH agent eyes via any OpenAI-compatible vision model - 11 provider presets (Doubao/Qwen-VL/GLM-V/OpenAI/Gemini/Ollama...), capability checkboxes that inject live prompt guidance, and analysis of images the user drops into the chat; the agent writes its own observation prompt, and base64 never enters its context.

让 DeepSeek Harness 纯文本模型也能识图：默认推荐智谱 GLM-4.6V-FLASH和 GLM-4.1V-FLASH 免费视觉模型

Vision bridge for text-only models (DeepSeek, pi-ai routes): Gemini Flash describes attached images at the llm stream seam and provides a describe_image tool.

Image & document analysis tools for DeepSeek Harness, powered by a local OpenAI Codex CLI (zero deps, 3 transports, pairs with dsh-drop-to-path)

给纯文本 DeepSeek Harness 模型加上识图能力：analyze_image 把图片转发到任意 OpenAI 兼容视觉端点 | Vision bridge for text-only DSH models

DeepSeek Harness (DSH) Web 插件：拖放文件预览 / Markdown 渲染 / 文件盒 / 智能桌面截图（全屏·区域·窗口）/ 外挂识图与识别文本入库。完整开发历史含 21 个快照标签。

Give text-only DeepSeek Harness (dsh) agents vision — pasted images auto-convert to text descriptions with persistent caching, each image converted only once.

DeepSeek Harness 插件：解除 Web GUI 图片输入限制，图片附件文本化后交给 vision skill 识图 | dsh plugin that lifts the image-input gate and hands attachments to a vision skill

Model-facing read_tiff tool for DeepSeek Harness: decodes TIFF/TIF images (multi-page, LZW/Deflate/PackBits/CCITT/JPEG compression, bilevel, 8/16-bit and float) into viewable PNGs with full header metadata, plus optional vision-model description.

Give text-only models eyes: analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible endpoint. 给纯文本模型装上眼睛的 dsh 插件。

该仓库暂未提供项目说明。

Image message bridge for text-only models in DeepSeek Harness (dsh): image blocks → text placeholder + local path, vision via qwen script

该仓库暂未提供项目说明。

DSH plugin: dispatch image-recognition tasks to an opencode-go mimo-v2.5 subagent via system-prompt injection

Zero-dependency vision OCR/Q&A toolkit (CLI + local web GUI) for OpenAI-compatible VLMs: Zhipu GLM, Qwen, OpenAI, OpenRouter, SiliconFlow

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.

DSH 本地视觉能力插件：macOS Vision OCR + ollama qwen3-vl 语义描述 + 上传图片桥接

明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别

DSH plugin: let DeepSeek-V4-Pro use V4-Flash-Vision-Exp for attached images. Install: dsh plugin --profile web add github:lasdrder0705/dsh-pro-vision

DSH 视觉桥接插件：让无视觉能力的主模型看图（会话收图 + 自动转文字 + view_image 工具）

一个可以让没有视觉的大模型拥有视觉能力的插件（当然，是通过外挂视觉模型实现的）

格物审视面：让 DSH 无视觉模型经视觉子代理完成视觉检验。Model-agnostic visual-inspection pipeline for DSH: HTML screenshots + vision-subagent briefing + source-code truth verification. Install: npm i gewu-tools

A native DeepSeek Harness (DSH) Cordis plugin that analyzes images through the reverse-engineered chat.deepseek.com vision mode (model_type=vision) — free, no third-party vision API key required. DeepSeek Harness（DSH）原生 Cordis 插件：通过逆向 chat.deepseek.com 识图模式（model_type=vision）分析图片，免费、无需第三方视觉 API key。

Automatic model routing for DeepSeek Harness: three difficulty tiers (hard/normal/easy) plus vision routing, picking models you already configured under Settings ? Models. ???? + ?????????

Vision for DeepSeek Harness agents — paste images in the Web composer, delegate reads to Kimi/MiniMax vision routes on isolated contexts; zero image bytes in the main session

Native-vision Windows computer-use for DeepSeek Harness: screenshots, UIA, OCR, and approval-gated input

Vision tool plugin for DeepSeek Harness (DSH): give text-only models like deepseek-v4-flash image recognition via Alibaba Bailian / any OpenAI-compatible vision API. 给 DeepSeek Harness 无识图能力模型加识图工具。

A see_image vision tool plugin for DeepSeek Harness — describe images through any OpenAI-compatible vision model (GitHub Copilot, OpenAI, Ollama, vLLM, LM Studio).

该仓库暂未提供项目说明。

DSH-native Vision Evidence bridge for text-only reasoning models with native image attachments and strict multi-image validation.

该仓库暂未提供项目说明。

Agnes omni-modal plugin for DeepSeek Harness: agnes_vision (image understanding) + agnes_image (text-to-image / image-to-image) + a vision bridge that lets you send images in chat. API key via DSH credentials, never in code.

DeepSeek Harness (dsh) plugin: rank similar photos with vision scoring. Install dsh-photo-pick-app.

Give a text-only dsh model eyes: pasted images recognized into text via an OpenAI-compatible vision endpoint.

该仓库暂未提供项目说明。

Windows computer-use capability for DSH: screenshot, vision, simulated input, self-evolving knowledge base. Plugin + skill dual-mode.

Vision for text-only DeepSeek: view_image tool via any OpenAI-compatible VLM endpoint. macOS/Windows/Linux, one-click install.

DeepSeek Harness 视觉补全：孪生路由解锁原生图片体验，本地 Ollama 请求层看图，零云端依赖。Vision twin + local agentic vision tools for DeepSeek Harness.