dsh-mindseye
Vision plugin for text-only DeepSeek Harness models: native image paste, layered evidence memory and cache, and intent-driven tool selection.
为纯文本 DeepSeek Harness 模型提供视觉能力：原生图片粘贴、分层证据记忆与缓存、意图驱动的工具选择。
How to install
dsh plugin add dsh-mindseye About
MindsEye 让 DeepSeek 原生看图 —— model-driven vision tools for DeepSeek Harness MindsEye 是一个 DeepSeek Harness（dsh）vision 插件。粘贴图片后，图片原样显示在会话里，DeepSeek 继续负责思考，视觉模型负责看图。插件暴露一组按任务拆分的视觉工具，由模型根据用户意图选择工具，每个工具固定映射到对应的意图和模型路由，返回结构化 JSON，并通过缓存与证据复用减少重复开销。 核心体验 **粘贴即看图**：接管 deepseek-official 路由，图片原生进入会话；接管不可用时自动降级为路径粘贴，新图始终能发出去 **模型选工具，插件管模型**：mindseye_read_image、mindseye_ocr、mindseye_ground、mindseye_colors 各自固定意图，模型按用户问题选工具，插件按工具映射到对应的模型链 **图片轮自动挂载**：检测到图片消息时自动注册视觉工具；纯文本轮默认只保留一个激活入口，避免常驻占用模型上下文 **多图一次读**：批量读取多张图片，批量遇 4xx 按指数拆分降级，失败只影响单张 **旧会话不毒化**：历史带图会话在回退模式下也能正常对话，图片块自动替换为附件标记 **每次调用透明**：返回 provider、model、…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 1
- mo. downloads
- –
- Last push
- 2026-08-18
- Created
- 2026-08-16
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- agent, cache, deepseek-harness, dsh-plugin, memory, multimodal, vision
Related plugins
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-vision-router
ysr666/dsh-vision-router
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
dsh-vision-toolkit
Anionex/dsh-vision-toolkit
Vision tasks for text-only models: intent-aware image Q&A, long-screenshot OCR, UI reproduction, grounding, and pixel diff.
dsh-deepseek-vision
siegfly/dsh-deepseek-vision
A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.