文件与数据
插件
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
deepseek-harness
dsh
dsh-plugin
multimodal
文件与数据
技能
[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
agent-skills
agent-vision-toolkit
computer-vision
deepseek
文件与数据
插件
Right-side file workspace for DeepSeek Harness Web.
cordis
deepseek-harness
diff
dsh
文件与数据
基础设施
DSH Web UI 文件追踪插件：记录并查看模型读取/写入/编辑的每个文件，带行号内容、终端风逐行 diff（红删绿增蓝改）与 hunk 上下文折叠；支持 present 交付文件查看（Markdown 渲染 / KaTeX / Mermaid / 图片）。适配至 dsh 0.2.0-rc.2，纯客户端零核心改动。
diff
dsh
dsh-plugin
file-tracking
文件与数据
插件
DSH Diff 工具插件：文本/JSON/CSV/Markdown 结构化比较与 unified diff，零依赖只读，注册 diff 工具
data-comparison
diff
dsh
dsh-plugin
文件与数据
插件
DSH（DeepSeek Harness）的本地 ComfyUI 图片生成插件：一个 generate_image 工具覆盖文生图 / 图生图 / 局部重绘 / 去背景，参数有智能默认值、报错可照做；零第三方运行时依赖，附 doctor 自检与 88 项测试（自带 mock ComfyUI，无需真装）。Local ComfyUI image plugin for DSH — one generate_image tool with text2img / img2img / inpaint / remove-background modes.
comfyui
cordis
deepseek-harness
dsh
文件与数据
插件
Native interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid / zoom / annotate / measure / diff / color / OCR) + MiMo V2.5 multimodal backend, zero external MCP servers.
ai-agents
computer-vision
cordis
deepseek-harness
文件与数据
插件
Windows-first vision suite with image understanding, OCR, screenshot diffing, and multi-provider routing for DeepSeek Harness.
computer-vision
deepseek-harness
dsh-plugin
ocr
文件与数据
插件
Let DeepSeek Harness generate images: call local or LAN ComfyUI workers directly from chat (status, generate, queue).
ai-image
comfyui
deepseek-harness
dsh-category-tool
