dsh-mimo-vision-hint
DSH plugin: prompt the agent to dispatch image recognition to an opencode-go mimo-v2.5 subagent
43 results
DSH plugin: prompt the agent to dispatch image recognition to an opencode-go mimo-v2.5 subagent
Vision recognition plugin for DeepSeek Harness: paste images into the composer, recognize them via GLM-4V on the host side, and inject the result into the conversation.
Session-scoped full-duplex voice assistant with tool-controlled drafting and Agent submission for DeepSeek Harness.
Aura Vision — free vision OCR plugin for DeepSeek Harness web profile: Zhipu GLM-4V-Flash (free tier), adaptive tile recognition for long documents, history with favorites and Markdown/Excel/Word/PNG export.
DSH vision/image-recognition plugin: enables AI to understand images with a configurable vision model
A microphone button for DeepSeek Harness that writes browser speech recognition into the composer draft.
Persistent voice conversations for DSH with cloud speech recognition, Edge TTS, and background Agent delegation
Offline Parakeet voice input for DeepSeek Harness
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,把识别文字喂回主模型,无感、可配置、升级不丢
识别昆虫或其他节肢动物名称(或所属目, 科, 属, 种)。
对含有动物的图像进行标签识别,无需任何额外输入,输出动物的类别标签。
Kepos Speech plugin for Alibaba and ByteDance Chinese speech synthesis plus short-audio recognition in DeepSeek Harness Web
Editable local and desktop dictation for DeepSeek Harness
识别植物名称(或所属科, 属, 种或亚种)。
对包含主体物体的图像进行标签识别,输出主体物体的类别标签,目前已经覆盖了5万多类的物体类别。
泰山识图 Taishan Vision - 让 DeepSeek Harness 纯文本模型也能识图:GLM 视觉识别 + 所选模型推理(静态插件包,重启永久生效;由鲸晴 JingQing v1.1.8 魔改)
Optional Web UI enhancements for DeepSeek Harness
DSH vision plugin: image recognition (Codex + Zhipu fallback) and generation (GPT Image + CogView fallback), text-only-model safe
DSH 插件:通过硅基流动(SiliconFlow)视觉大模型识别/分析图片,支持本地文件路径、http(s) 图片 URL 与 base64 data URL。含持久化的粘贴识别面板(web 端)。