DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins
R

dsh-rayrun-computer

Rayrun Computer

适用于 DeepSeek Harness (DSH) 的 Rayrun 云电脑:侧边栏中的 Linux 云电脑,配备 noVNC 桌面、代理沙盒、用于执行命令、处理文件和委派整个任务的 rayrun_* 工具,以及按会话进行云端/本地路由。云电脑 / 远程桌面;令牌保存在 Harness vault 中。

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add github:RayrunOS/dsh-rayrun-computer#343b1afc92232364794df32b583c075581d8809d
README兼容性版本

兼容性与来源证明

Rayrun Computer 以 dsh-rayrun-computer 发布,当前版本为 2.0.0。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
web
发布来源
github
Registry 更新时间
2026/11/3

版本

1.0.0stable
2026/11/3
2.0.0stable
2026/11/1

相关插件

正在加载相关插件…

最新版
2.0.0
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
未提供
文件数
未提供
Surface
web
许可证
MIT
发布源
github
GitHub
★ 3
周下载
0
最近提交
2026/11/3
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 developer-tools 分类下经过校验的插件。

Ssh@linxin666/dsh-sshdsh Web GUI 的远程 SSH 操作:主机配置存储(~/.dsh/dsh-ssh.json,可从 ~/.ssh/config 导入)、支持跳板主机的持久化 ssh2 连接池、exec / PTY Web 终端 / SFTP 传输 / 本地端口转发隧道 / 集群执行Opsdsh-ops适用于 Windows x64、Linux x64 和 macOS arm64/x64 的原生文件和 PTC 工具;仅限 Windows 的可选 Bash 负载和主机 PowerShell 集成Update@linxin666/dsh-update用于 dsh Web GUI 的自更新插件:探测 npm 上是否有更新的系列版本,并在原地运行所属配置的 pnpm 更新;可通过设置图标旁侧边栏中的触发器启动,并显示发布说明面板Tui@deepseek-harness-tui/dsh-tui用于 DeepSeek Harness 智能体、会话和工具的交互式终端界面。

README

Rayrun Cloud Computer

dsh-rayrun-computer

Rayrun cloud computers, inside DeepSeek Harness.
A real Linux desktop in your sidebar — and a sandbox the agent can drive.

English · 简体中文

Rayrun sells cloud Linux machines by the second: disposable boxes with their own CPU, memory and a persistent workspace. This bundle turns them into cloud computers inside DeepSeek Harness (DSH) — create one from the sidebar, open its desktop in the page, or let the agent run commands, move files and hand off whole tasks on it.

The rule is local-first. The cloud is a worker, not a second home: your checkout stays the source of truth, pushes are verified down to the patch SHA-256, and anything pulled back lands in .dsh/incoming/ for you to read before applying.

What you get

  • Cloud computers in the sidebar. Create one with a wizard (image, vCPU, RAM, and a model credential if its agent will call a model), then start, pause, resume, shut down, rename or destroy it. Cards show status, image, spec, IP and machine hours; the header shows balance and total hours.
  • A real desktop, in the page. Machines created with a remote desktop publish their noVNC port: open it inline, in a new window, or fullscreen. One click reveals the VNC password. Images whose empty /etc/hosts breaks websockify (the WebSocket closes with 1011) are repaired automatically when the desktop connects.
  • Tools for the agent. rayrun_sandbox, rayrun_exec, rayrun_files, rayrun_agent — plus rayrun_dsh and rayrun_workspace for the cloud worker layer.
  • Cloud or local, per session. The composer toggle is a real route, not a prompt: in cloud mode the host refuses local pwsh / bash / write / edit, so the agent cannot quietly work locally. Read-only tools stay available for review.
  • A worker that matches your DSH. Push a worker layer into the machine's headless profile and verify it by hash; delegate a whole task with an objective and acceptance criteria; get the results back, round after round.
  • Sync you can check. push ships commits as a git bundle, then dirty and untracked files; the patch digest is recomputed on both sides and compared. pull writes the cloud diff into .dsh/incoming/<timestamp>/ and applies nothing.
  • Login without copy-paste. Username and password, or WeChat. A token is created for you and stored in the Harness vault, host side only.
  • Optional auto-stop and updates. Stop idle machines after a task (never destroy), and update the bundle from the page once a new version is published.

How it fits together

flowchart LR
  subgraph you["Your computer"]
    page["DSH page<br/>sidebar · desktop · toggle"]
    host["Plugin host<br/>same-origin RPC · tools"]
    page <--> host
  end
  host -->|"HTTPS · token stays local"| api["Rayrun API<br/>api.rayrunos.com/v1"]
  api --> vm["Cloud computer<br/>Linux · persistent workspace"]
  page -.->|"noVNC over ingress"| vm

Quick start

Requirements

  • DeepSeek Harness 0.2.1-rc.5 tested — the desktop app or dsh web.
  • A Rayrun account from rayrunos.com; the plugin creates an API token for you.
  • Chrome or Edge only for WeChat sign-in; otherwise optional.

The package is not on npm yet, so install from a checkout:

git clone https://github.com/RayrunOS/dsh-rayrun-computer.git
  1. Add the checkout in Plugins → Add plugin (give it the absolute directory), or from a terminal: dsh plugin --profile web add /abs/path/dsh-rayrun-computer
  2. Restart DSH. The client half only loads when the page starts.
  3. In Cloud Computer → Connection settings, sign in with your Rayrun account or paste an API token.
  4. New computer → image, at least 2 GB of memory, remote desktop on → Create and open (about 15 seconds).

The desktop app and dsh web use different profiles (desktop and web), so install into the one you actually open. More install paths and fixes: installation guide.

Sanity check: ask the agent to list your machines. With no token it must answer token_required, never pretend the work happened.

Tools

ToolWhat it does
rayrun_sandboxcreate · list · inspect · start · stop · pause · resume · destroy
rayrun_execrun a non-interactive command (/bin/sh -c or argv); returns exit code, stdout, stderr
rayrun_fileslist, upload and download files in the machine's workspace
rayrun_agenthand a whole task to the agent inside the machine and wait for the stream
rayrun_dshsync the worker layer, status compare it, delegate a task to the cloud worker
rayrun_workspacepush a verified copy of your checkout, pull the cloud diff for review

Configuration

Bundle defaults live in cordis.patch.yml; override only what you need in your profile:

# $DSH_HOME/profiles/<profile>/cordis.patch.yml
- id: rayrun-cloud
  name: 'dsh-rayrun-computer'
  config:
    sandboxName: dsh-workspace
    idle_stop_minutes: 15    # stop idle machines; never destroys
    egress_allow:            # machines start with no outbound network
      - api.deepseek.com

Every key is documented in the usage manual; the token lookup order is here.

Docs

The detailed docs are in Chinese for now.

ReadFor
Installationevery install path, first connection, troubleshooting
Usage manualdesktops, cloud/local routing, worker layer, workspace sync, delegation, auto-stop, full config and tool reference
Parity designwhy the cloud worker layer exists, what syncs and what does not
Developmentmodule map, checks, tests, live integration

Security and caveats

  • The token stays on the host. The page talks to /plugins/rayrun/rpc (same-origin, checked) and never receives it; passwords live in memory only.
  • destroy is irreversible — the machine and its workspace are deleted together.
  • No outbound network by default. A new machine cannot reach anything until you list hosts in egress_allow.
  • The cloud image is already root. It ships without bubblewrap, so the worker layer sets danger-full-access to make shells work. That is a workaround, not isolation.
  • A bundle's host code runs inside the DSH process. Install it from a source you trust.

Development

node --check index.js
node --check client.js
node test/security.mjs
node test/tool-routing.mjs

No build step and no runtime dependencies; client.js only loads modules DSH provides. Full check and test matrix: docs/development.md.

License

MIT © RayrunOS — see LICENSE.