dsh-mobile-voice-call
App-free mobile voice calls with existing DeepSeek Harness sessions
51 results
App-free mobile voice calls with existing DeepSeek Harness sessions
Configurable near-field trigger that reminds a DeepSeek Harness agent to load the J-Space Cognition Suite only when rules say it is worth it
Microphone speech-to-text input for the DeepSeek Harness Web UI
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
乔哈里认知四象限对话梳理工具 / Johari cognition-quadrant dialog prompt composer — adds a button above the composer that opens a 2×2 quadrant panel (我知道/不知道 × AI知道/不知道) to groom conversation context into a structured prompt written back into the draft.
Offline Parakeet voice input for DeepSeek Harness
Harness-native J-Space cognition preset with cache-stable scoped prompt control.
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。
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。
Optional Web UI enhancements for DeepSeek Harness
A project memory for your DeepSeek Harness agent — constrain / observe / remember / verify, built on DSH native primitives.
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)。
识别车牌号、车牌颜色、单/双层车牌、位置框。
DSH 视觉桥接插件:复用 DSH Provider 或 OpenAI 兼容直连,支持可视化配置与图片粘贴
Editable local and desktop dictation for DeepSeek Harness