MrMaii/knotline
通过画线来编排AI代理——把Agent从对话框搬到一张图上
Project Overview项目介绍
Knotline, also known as 运筹, is a DSH-native plugin that adds a project operating map canvas to the DeepSeek Harness sidebar. All requests, agents, execution steps, reviews, and deliverables are organized on a single interactive canvas, where each line connects nodes to trigger real agent work. It supports resumable DSH conversations that only advance status through structured lifecycle tools, with no fake execution of tasks. To install locally, you clone the repository, run npm install to pull dependencies, then build the bundle with npm run build, and add it to your DSH profile using the official DSH plugin command.
The typical workflow starts when you drag a Request node onto the canvas and connect it to an Agent node. Knotline supports six root node types out of the box: Request, Agent, Skill, Backlog, Approval Pool, and Scheduled Trigger. You can combine multiple Agent nodes into a Team that holds internal discussions before starting work, queue unassigned tasks in Backlog pools for idle agents to pick up, and set scheduled triggers that persist across restarts. All transcripts from running tasks are embedded directly on the map, so you never lose context from previous work. Execution follows a governed design that requires independent review, so self-approval is blocked by default.
Knotline requires Node.js version 22.19 or newer, or version 24 and above, to build and run correctly. It is released under the permissive Apache 2.0 open source license, and is an independent community project not affiliated with DeepSeek. When you first launch Knotline from the DSH sidebar, it opens a workspace picker, then provides a three-step guide for new users to get oriented. You can run npm run check to verify the build before installing it to your DSH profile, which runs linting, type checks, 55 tests, and bundle validation.
Knotline(运筹)是一款专为 DeepSeek Harness(DSH)侧边栏打造的原生插件,提供项目运行可视化地图功能。它通过画布整合请求、智能体、执行、评审和交付全流程,每一条连线都对应实际的智能体工作执行,所有任务都通过可恢复的 DSH 会话推进,不存在虚假执行环节。
用户可以拖拽请求节点到画布,连接对应智能体节点,按需求分类生成回答、评审反馈、复杂任务规划或调试任务台。所有对话记录都会保存在地图上,执行流程默认需要经过独立评审环节,不允许自审批,只有可信智能体能够执行已批准的计划。
该项目要求 Node.js 版本为 22.19 及以上,或是 24 及以上,采用 Apache-2.0 开源许可,是独立社区维护的项目,与 DeepSeek 官方无关联。安装可按照官方步骤编译后,通过 DSH 命令添加插件,首次打开会有三步新手引导。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:knotline(MrMaii/knotline)
仓库:https://github.com/MrMaii/knotline
本站详情页:https://www.yhbd.top/plugins/mrmaii-knotline/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 Apache-2.0 · ⭐ 3 · 最近提交 2026-08-18 · 主语言 JavaScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- Only 3 stars - very few users, little community feedback星标只有 3,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
npx @deepseek-ai/dsh@0.1.0-rc.6 plugin --profile web add (Resolve-Path .).Path
把 MrMaii/knotline 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
English · 简体中文
Knotline (运筹) is a project operating map for the DeepSeek Harness sidebar.
Requests, agents, execution, review, and delivery live on one canvas — a line is a command: it runs real agent work.
One line runs one real execution
Drag a Request onto the canvas and connect it to an Agent. Classification derives an Answer for questions, Review Feedback then a Plan for complex work, or a live Task Bench for Debug — then a real, resumable DSH conversation does the work. There is no fake execution: status only advances through structured lifecycle tools.
Everything a chat gives you, on the map
|
|
|
Chat-grade visibility. Running Task Benches embed a live transcript (you / agent / tools); finished work carries the agent's full reply, delivery summary, and validation evidence — nothing is lost. |
Governed by design. Execution flows through a pre-review artifact and an independent reviewer — self-approval is rejected by the backend. Approval pools let a trusted agent execute only approved plans. |
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
poiuyjie/dsh-md-preview
Devin-AXIS/iPolloWork
EthanYoQ/AI-Novel-Writer
tong-io/tongflow
shanliuling/dsh-image-gen
ZSeven-W/dsh-ios
ZSeven-W/dsh-crew
jsdvjx/dsh-strata