dsh-qwen-voice
leaveimagination
Voice control and multi-session task dispatch for DeepSeek Harness, powered by Qwen Audio Agent
80 个条目 · 第 2 / 2 页 · 数据快照 2026-08-14
leaveimagination
Voice control and multi-session task dispatch for DeepSeek Harness, powered by Qwen Audio Agent
lyh9712
DSH (DeepSeek Harness) Web 背景图插件:自定义网页背景壁纸,侧边栏/聊天区半透明磨砂,带设置界面
me9rez
DeepSeek Harness (dsh) bundle plugin: vision_analyze tool lets text-only LLM agents read images via SenseNova VLM, with Schemastery config and single-source credentials
MicroHEROX
Kimi WebBridge for DeepSeek Harness — a third-party dsh plugin bundle that turns the local Kimi WebBridge daemon into 15 native kimi_webbridge_* browser tools (navigate, click, fill, snapshot, screenshot, evaluate, network, upload, PDF).
mindcarver
DeepSeek Harness plugin: image_gen tool backed by Codex CLI (gpt-image-2)
moon09300731
DeepSeek Harness 视觉能力全家桶:vision_understand 工具 + 粘贴/拖拽/按钮三入口识图
qizhen2021
dsh-plugin-vision — DeepSeek Harness Plugin.
realguan
Render Mermaid fenced code blocks as diagrams in DeepSeek Harness (dsh) web — a dynamic Cordis client plugin, no shell changes needed.
sala003
dsh-tool-describe-image — DeepSeek Harness Plugin.
sliverp
DingTalk Stream text and image channel plugin for DeepSeek Harness
SPYQWER1
dsh-imagecraft — DeepSeek Harness Plugin.
tangbut1
DeepSeek Harness Web 语音输入插件
visail
Paste an image into the chat box and text-only DSH models can "see" it — auto-rewrite of pasted images + analyze_image tool routed to a Kimi vision model.
whyihaveyou
Hands-on, screenshot-rich bilingual guide to DeepSeek Harness plugin development. DSH 插件开发实战指南(中英双语,全真实截图)。
Xin-Zhang-IceMan
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.
ycp424c
DSH adapter that transcribes native image attachments with Codex Luna before delegating to DeepSeek
zhuiyueya
Give text-only DeepSeek models eyes — a DeepSeek Harness plugin that transparently converts chat images into OCR text + vision-model descriptions before they reach the LLM. Configure vision backends (GLM-4V, Qwen-VL, Gemini, Ollama…) right in the Models settings page; multi-backend fallback chain, double-layer caching, no config files.
zimai233
Multi-engine reverse image search aggregator for DeepSeek Harness. Turn one public image URL into Google Lens / Baidu / Yandex / TinEye / SauceNAO / IQDB / Ascii2d search links.
zimai233
Media downloader for DeepSeek Harness. Detect and download video/audio from Bilibili, YouTube, Douyin, Xiaohongshu.
ZRui-C
DSH bundle plugin: screenshots, screen recording, Markdown→Xiaohongshu image cards, dev.to publishing, and human-in-the-loop review for DeepSeek Harness