MIT-licensed, JavaScript quantum Agent workspace on DeepSeek Harness — desktop, Web UI and messaging entry points, integrated Qiskit / FieldQKit / OriginQ / QMClaw tools, and MCP-based extensibility for custom Skills and Tools.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-01
License
MIT
01What can it help you accomplish?
Use natural language to run quantum tasks — analyze circuits, query cloud backends, run algorithms
Quantum results plus the complete execution process returned to the user
General users who want to start quantum tasks from natural language, and research institutions organizing scientific workflows
Integrate your own quantum methods and data sources into the workspace
Custom methods packaged as Skills; devices and data sources exposed as Tools via MCP Server and registered through the Harness MCP Client
Quantum companies and research institutions that want to extend OpenQuantum with their own capabilities
02How to install into DeepSeek Harness
Prerequisites
- Node.js 24 or newer — the README shows a "Node.js 24 or newer" badge
- A DeepSeek Harness (dsh) runtime, since OpenQuantum is built on DeepSeek Harness
Installation steps
- 01
Open the OpenQuantum desktop client or Web UI, or connect OpenQuantum to WeChat / Feishu to start (the README presents a desktop client, Web UI, and messaging entry points)
- 02
Expose your quantum devices and data sources as Tools via an MCP Server and register them through the Harness MCP Client
Verify the integration
- Confirm the workspace loads the integrated Qiskit, FieldQKit, OriginQ / QPanda, and QMClaw capabilities and that the MCP-ready path is registered
Rollback
- Unregister any custom MCP Tools by removing their MCP Server entry from the Harness MCP Client
03DSH integration and capability boundaries
Built on DeepSeek Harness as a first-class quantum workspace; quantum tools organized as Skills and MCP Tools, registered through the Harness MCP Client, with models connected via Provider Route
Quantum Agent workspace entry
Natural-language quantum task requests (via desktop client, Web UI, or WeChat / Feishu)→Quantum results plus the complete execution process
registers quantum devices and data sources as MCP Tools through the Harness MCP ClientIntegrated quantum tools (Qiskit / FieldQKit / OriginQ-QPanda / QMClaw)
Quantum circuits, algorithms, and cloud-backend queries→Analysis, execution, and scientific validation of quantum computations
Extensibility via Skills and MCP Tools
Custom methods, workflows, devices, and data sources→Custom methods packaged as Skills; devices/data exposed as Tools and registered via Harness MCP Client
custom MCP Tools registered into the Harness MCP Client
04Who is it for? When not to use it?
Good for
- General users who want to start quantum tasks from natural language, and research institutions organizing scientific workflows
- Quantum companies and research institutions that want to extend OpenQuantum with their own capabilities
Not for
- Custom devices and data sources are exposed as Tools through an MCP Server and registered via the Harness MCP Client; they become callable by the model, so only register trusted MCP Servers.
05Compatibility, maintenance and safety notes
- OpenQuantum runs as a desktop client, Web UI, and messaging integration (WeChat / Feishu); the README requires Node.js 24 or newer but does not detail OS-specific build steps.
- Custom devices and data sources are exposed as Tools through an MCP Server and registered via the Harness MCP Client; they become callable by the model, so only register trusted MCP Servers.
MIT · actively maintained (last push 2026-09-01, no tagged release yet)
06Frequently asked questions
How do I start using OpenQuantum with DeepSeek Harness?
Open the desktop client or Web UI, or connect OpenQuantum to WeChat / Feishu, then start a quantum task in natural language. OpenQuantum is built on DeepSeek Harness, which provides sessions, tool scheduling, permissions, persistence and execution traces.
What quantum tools are integrated?
You can directly use the integrated Qiskit, FieldQKit, OriginQ / QPanda, and QMClaw superconducting-control and quantum-algorithm capabilities.
How do I add my own quantum methods and devices?
Package your own methods and workflows as Skills, and expose devices and data sources as Tools via an MCP Server registered through the Harness MCP Client; the model connects through the Provider Route.
07Related DSH workflows
dsh-better-sidebar
by omdsh-dev
Full sidebar workbench with file rendering and editing, terminal, Git, and subagents; third-party plugins can register new tabs.
dsh-tui
by ccch1mneyyy
Claude Code 风格全屏终端 TUI：像素鲸鱼顶栏、双流光大字、实时工作状态行、思考流式展开、双击 Esc 时间回溯、上下文进度条 + TPS 仪表；接入 Agent preset（standard/code/minimal/cordis）、Skills、MCP、Goals、Todos、子代理，/ 命令注册表与随附技能（audit/bug/review/practice/pr_comments/release-notes/vuln-check）；纯插件挂载零核心改动。
openpets
by alvinunreal
Local first, desktop companion platform with animated pets, plugin SDK and coding-agent integrations.
dsh-tianshu-tui
by huiliyi37
DeepSeek Harness 交互式终端 UI 插件：会话工作区、图片端到端（剪贴板/视觉桥）、slash 下拉、审批卡片、推理可视化，纯展示层
08Data and sources
设备与数据源可以由 MCP Server 暴露为 Tool，再经 Harness MCP Client 注册，模型则通过 Provider Route 接入。
OpenQuantum 的第一版，是在 DeepSeek Harness 发布后的三天里做出来的。
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-01. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.