dsh-noteboard
Workspace-wide sticky notes on an infinite canvas: notes are plain Markdown files, created manually, captured from conversations, or distilled by the AI, and can be handed back as context; ships 12 model tools and 5 bundled skills for creating, tagging, arranging, comparing and merging notes.
工作区级的无限画布便签：便签以 Markdown 文件保存，可手动创建、从对话中摘录或由 AI 提炼生成，并能作为上下文提供给 AI 使用；附带 12 个模型工具与 5 个内置技能，用于创建、打标签、整理、比较与合并便签。
How to install
dsh plugin add dsh-noteboard About
DeepSeek Harness（DSH）的便签画布插件：在会话视图中提供一块工作区级的无限画布。便签为 Markdown 文件，画布为 JSON Canvas 布局文件，内容与摆放分离，可由文本编辑器与 Git 直接管理。支持从对话中采集文字生成便签，以及将便签作为结构化引用发回输入框交给模型处理。 效果 📸 **画布总览** **便签引用输入** **从对话采集便签** **从便签返回会话位置** canvas-overview.png —— 画布总览：多张不同颜色的便签 + 分类标题 + 顶部工具栏 cite-notes.png —— 输入态：底部输入框展开，上方挂着 2–3 个便签引用气泡 capture-from-chat.png —— 对话视图中框选一段文字，浮出「存入画布 / AI 提炼」按钮 backlink-jump.png —— 点击便签「来源 / 打开对话」后跳转到对话视图、原文位置高亮的效果 --> 功能 ✨ **无限画布** —— 平移、缩放、框选批量移动、网格吸附，可添加自由文本与自动分类标题；同一批便签可保存多张画布布局，随时切换 **Markdown 便签** —— 每张便签是一个带 frontmatter 的 .md 文件；编辑器实时预览，七种颜色、亮暗双主题 **从对话采集** —— 框选对话文字，「存入画布」原文保存或「AI 提炼」浓缩成便签…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 1
- mo. downloads
- –
- Last push
- 2026-09-10
- Created
- 2026-09-08
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- bundle-plugin, canvas, deepseek-harness, dsh, dsh-plugin, noteboard, sticky-notes, whiteboard
Related plugins
get-shit-done
gsd-build/get-shit-done
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
markdownify-mcp
zcaceres/markdownify-mcp
A Model Context Protocol server for converting almost anything to Markdown
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
airtable-mcp-server
domdomegg/airtable-mcp-server
🗂️🤖 Airtable Model Context Protocol Server, for allowing AI systems to interact with your Airtable bases