agnes-media
Registers generate_image and generate_video tools for Agnes AI media models (agnes-image-2.5-flash, agnes-video-2.5-flash) in DeepSeek Harness. Supports multi-image reference via reference_image_urls.
755 results
Registers generate_image and generate_video tools for Agnes AI media models (agnes-image-2.5-flash, agnes-video-2.5-flash) in DeepSeek Harness. Supports multi-image reference via reference_image_urls.
Windows minimal agent preset for DeepSeek Harness: a one-line fixed persona, gitbash + str_replace_editor + web_search, no runtime context, no compaction. Installs the preset into the user's agent-presets root.
AI 生图 (image generation) plugin for the dsh web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint, with multi-provider support, model discovery, and agent tool registration. 与 @xiaoyuink/dsh-image-vision 同系列的图像插件。
Labnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.
DSH plugin: 深海摸鱼 —— context 越深潜得越深,答完摸鱼集镭射生物卡 | Deep-sea slacking holo cards
波谷倒计时小组件:输入框上方余额数字徽章,悬停浮现 24 小时峰谷时间轴(峰橙/谷蓝 + 当前时刻指针),官方余额 5 秒刷新、今日消耗独立计费,10 套配色预置 + 谷/峰色自定义。Minimal peak/valley widget for DeepSeek Harness: a balance-number chip above the composer with a hover 24h peak/valley timeline, 5s official balance refresh, independent spend metering, and 10 color presets plus custom valley/peak colors.
GLM 视觉模型插件:注册 glm-vision 供应商路由(glm-4.6v 系列,image+text 输入声明)并提供 glm_vision 工具,让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。
Paste/drop non-image files or folders into the DSH chat composer: paste inserts native @path references, drop inserts absolute paths.
DSH plugin: before answering a large question, show an estimate of tokens and DeepSeek API cost as an inline row in the Web chat stream, then update it with the actual usage after the answer.
One-click DSH background switcher backed by local Wallpaper Engine images/videos (WE Web API first, Steam workshop/myprojects directory scan fallback)
Minimal first-turn conditioning for DeepSeek Harness Web sessions, with a persistent UI toggle.
Genuine Liquid Glass theme for DSH Web UI: SVG feDisplacementMap edge refraction on input card, send button, bubbles, view tabs, queue dock and sidebar. Built-in animated demo wallpaper, customizable background blur & brightness, redesigned model selector popup, glass-styled buttons, and a unique water-drop settings icon.
Vision sidecar for text-only coding agents.
SSiD (思灵) quick screenshot capture: tray/hotkey → fullscreen box-select overlay → cropped image into the current conversation composer
Draggable animated floating companion for the DeepSeek Harness web GUI, with cat and dog breed skins that react to the current session
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
对话里的图值得被认真看:点一下全屏灯箱(缩放/拖拽平移/下载另存/左右翻页),会话内一键把图收成可调列数的缩略图网格或整块隐藏,还能跳到下一张/上一张图片位置;本地图支持 TIFF/HEIC 自动转码。| Chat images get a proper look: full-screen lightbox (zoom / drag pan / download / prev-next), plus one-click conversation-wide thumbnail grid (configurable columns) or hide, jump-to-image navigation, and TIFF/HEIC transcoding for local files.
DeepSeek Harness agent preset: minimal-mode with web search and AGENTS.md loading (极简模式(网络)).
VSCode-style file explorer for the DeepSeek Harness web client: a body-mounted, draggable right sidebar with virtualized lazy file tree and text / Markdown / image preview. Does not depend on the native details slot, so it works on blank sessions.
Paper Design MCP bridge as a DeepSeek Harness bundle: paper_* tools, image screenshot support, design skills, OAuth auth, and Cursor-parity design guidance.
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
A DeepSeek Harness Plugin for Previewing Mermaid Diagram by Images in Chat Sessions. View on GitHub (https://github.com/baconbao/dsh-mermaid-image-preview).
Web-enhanced plugin for DeepSeek Harness: task board with cron scheduling, git graph, preview/files/SCM right panel, DeepSeek balance line, and image understanding for text-only models
Select a range of a DeepSeek Harness conversation and share it as a branded PNG long image, with draggable magnetically snapping range markers.