746 results
Customize the DeepSeek Harness web UI: theme color presets (main area, sidebar, message bubble, send button), full-page background image, plus a VSCode-style card layout engine (dock/undock/float panels, unified plugin panel with launcher + tabbed host) 鈥?all reversible and light/dark aware.
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
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.
为 DeepSeek Harness 提供外部视觉模型能力：纯文本主模型通过 describe_image 工具调用外部视觉模型看图，拿到纯文字描述（多模态补全）。静态 Cordis 插件，随 DSH 启动自动加载。
ComfyUI 驱动器（AI-first 合同制）：模型只见合同槽、不见工作流 JSON。文生图/图生图/文生视频/图生视频模板，双重预检防幻觉，官方/自定义节点活体判定。
用户消息导航条插件：在 DeepSeek Harness Web GUI 会话聊天窗左侧显示一条迷你导航条（minimap），用刻度标出每一条用户消息的位置，悬停预览消息摘要，点击/拖动即可快速跳转定位。
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
Modellix Design, LLM, and Web providers for DeepSeek Harness
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。
Paste/drop non-image files or folders into the DSH chat composer: paste inserts native @path references, drop inserts absolute paths.
DeepSeek Harness plugin: panel hotkeys for every interaction panel — Enter presses the confirm (primary) button, Esc presses the cancel button (approval, question/choice, plan review; Claude Code habits).
Unit conversion toolbox for DeepSeek Harness (dsh): length, mass, temperature, area, volume (incl. cooking), speed, time, data sizes (decimal MB vs binary MiB), data transfer rates (Mbps vs MB/s), acceleration (m/s², g-force), illumination (lux, foot-candle), pressure, energy, angle, frequency, power (mechanical/metric/electric horsepower), force, torque, typography (px/pt/em/rem), fuel economy (mpg ↔ L/100km) — zero runtime dependencies
CodeBuddy (copilot.tencent.com) provider bundle for DeepSeek Harness (dsh): 18 models (DeepSeek, GLM, Kimi, MiniMax, Hunyuan, auto) with adjustable reasoning efforts, CodeBuddy web search / web fetch backends for the stock dsh tools, and a settings card in the Web UI.
Minimal auto chess for the dsh web GUI: AI action routes, model catalog, and default prompt (node half) plus the conversation-view tab with the boards (browser half)
dsh plugin: show the estimated DeepSeek API cost of the current session in the web GUI stats strip (token usage × official pricing, peak/off-peak aware)
DeepSeek Harness native vision, gpt-image-2 image generation, and Seedance video generation via Xiapan Cloud.
Minimal session timeline for DeepSeek Harness: one dot per question, click to jump, hover to preview. 会话提问时间线：每条提问一个圆点，点击跳转，悬停预览。
Image understanding, OCR, and persistent visual evidence for text-only DeepSeek Harness models
Select a range of a DeepSeek Harness conversation and share it as a branded PNG long image, with draggable magnetically snapping range markers.
Out-of-tree Web plugin: load folder-based theme packs (tokens, CSS, fonts, images) and switch them through ThemeRuntime
One-key ClawRouters plugin for DeepSeek Harness: chat, image generation, video generation, and web search
dsh bundle plugin: grok2api image & video generation tools plus image recognition (generate_image / generate_video / recognize_image) for the DeepSeek Harness
对话内联图片:LLM 回复中输出的本地图片路径直接在消息正文内渲染为图片,支持 9 种格式、点击放大灯箱、可调尺寸
Plug-and-play image reading for text-only models: admits pasted images, projects them as [Image #N], and provides a first-class read_image tool backed by a configurable vision model, with a 读图 settings page (设置 → 读图) bridged over typert Remote.