Vision & Multimodal plugins

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

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

Transparent image preprocessing route for DeepSeek Harness

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

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

DSH 插件:vqa_ask 双模型视觉问答 —— 主模型提问 → 视觉模型看图回答,UI 实时展示 QA 过程,支持多模态视觉模型选择

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

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

DeepSeek Harness plugin. 支持直接把图片、文件等拖入到dsh中。更方便地拖拽；image & file drop.

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

DSH 插件:让纯文本模型对话也能拖图/贴图——图片自动保存到会话工作区,以文件路径交给模型(多模态模型不受影响)

DeepSeek Harness: vision

Synesthesia Encoder (通感编码器) — give any text-only LLM (DeepSeek, etc.) the ability to see images via structured spatial text encoding. A Pi agent extension.

DSH plugin: pixel-diff two screenshots into diff.png + triptych (pixelmatch) — 像素对比工具

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。

DeepSeek web vision bridge plugin for DeepSeek Harness (DSH)

Community plugins for DeepSeek Harness: local-vision (Ollama image description) and claude-to-dsh (Claude Code migration). MIT and Repetition guard and content cleaner plug-in.

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

DeepSeek Harness 宿主插件：让纯文本主模型也能通过 describe_image 工具“看图”

DeepSeek Harness 多服务图片生成与编辑插件，支持 OpenAI Images、Gemini Interactions 与顺序故障转移。Multi-provider image generation and editing for DeepSeek Harness.

图邮 (imgpost)：让你的 DSH 能发图给你 —— 本地图片、网页图片、AI 生图，一键发进对话里。

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

DSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see images

修改DSH的背景，支持静态动态背景，支持网页图片视频，支持修改透明度

CLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.

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

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

DSH 插件：为纯文本模型提供本地看图能力（llama.cpp / Ollama / LM Studio / vLLM 全兼容）｜Local vision for text-only LLMs on any OpenAI-compatible local server

Vision + smart model routing for DeepSeek Harness. Gemini sees. DeepSeek codes.

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。

Vision toolkit for DeepSeek Harness -- give text-only agents eyes

DeepSeek Harness 视觉能力全家桶：vision_understand 工具 + 粘贴/拖拽/按钮三入口识图

DSH 图片/音视频托管插件：自动拉起 8899 静态服务 + 3080 /files/ 路由（HTTP Range 流式）+ WebUI 内点击即播（视频静音/音频 20% 音量/互斥懒加载）

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 视觉插件：让纯文本模型拥有视觉能力 / Vision plugin for DSH: vision_analyze tool + automatic image transcription for text-only models.

DSH 视觉模型插件：为无视觉能力的文本模型提供图片识别。粘贴/拖入/导入的图片自动交给 OpenAI 兼容视觉模型识别为文字并发送进对话，支持多轮复核（vision_ask）、多提供商配置。

KoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.

DeepSeek Harness(DSH) web plugin: paste files into the composer, inbox storage, thumbnails. Text via read_inbox; image understanding needs your vision skill (bundled image-reader + ARK_API_KEY).

Native Windows Computer Use and configurable vision tools for DeepSeek Harness.

Community plugin for DeepSeek Harness: give text-only models eyes - paste images natively, described via an OpenAI-compatible vision API

ClawShell vision as DeepSeek Harness plugins: self-perception, closed-loop self-adaptation, trust/niche swarm, insight mining, knowledge genome

DSH 极简模式视觉辅助：保持灰测体验所需的首轮干净上下文，同时通过隐藏上下文和按需 Bash 工作流提供视觉分析 | Vision assistance for DSH minimal mode: preserve the clean first-turn context behind the gray-test DeepSeek experience while adding on-demand visual analysis through a hidden-context Bash workflow.

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).

添加deepseek harness生图识图能力插件

让不支持图片输入的主模型通过已配置的视觉模型理解图片的 DSH 插件：自动桥接、像素坐标描述、vision_ask 追问工具与设置页

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。

Windows-first vision suite with image understanding, OCR, screenshot diffing, and multi-provider routing for DeepSeek Harness.

DeepSeek Harness (dsh) vision plugin — a fork of ModLens adding multi-engine image reading (Gemini, Volcengine Ark/Doubao, Claude) with per-call engine selection.

DSH 识图桥接插件：让 DeepSeek 等纯文本模型会话也能发送图片，图片自动经视觉模型识图转文字（识图桥接，read_image 工具兼容）

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

DeepSeek Harness plugin: multimodal vision (OpenAI-compatible) + Android adb UI automation for real-tap mobile app testing

On-device macOS OCR and Apple Vision for DeepSeek Harness — one native plugin with a bundled Skill.