A multi-CLI agent sidebar for DSH on macOS and Windows. Each CLI retains its own account and model service; tasks can continue by agent name.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-10-18
License
MIT
01What can it help you accomplish?
Coordinate tasks across external AI CLIs from DSH
Named agents with their own conversations and task status in the sidebar
People already using several AI CLIs
02How to install into DeepSeek Harness
Prerequisites
- DeepSeek Harness Desktop on macOS or Windows; enable dsh from the Desktop command-management menu.
- Node >=22.19.0. Install the native external CLI and prepare its own login or API configuration; npm OMP requires Bun >=1.3.14.
Installation steps
- 01
End running tasks and completely exit Harness before installation.
- 02
$ dsh plugin --profile desktop add dsh-cliworker-now@latest
- 03
Cold-start Harness after installation. With pnpm 11, newly published versions may wait 24 hours; check the actual installed version.
Verify the integration
- dsh plugin --profile desktop ls dsh-cliworker-now --depth=0
Rollback
- End tasks and completely exit Harness, then run dsh plugin --profile desktop remove dsh-cliworker-now and cold-start Harness. Local accounts, history and preferences remain.
03DSH integration and capability boundaries
Independent DSH multi-CLI agent plugin with task dispatch and sidebar conversations
Named agents and role presets
CLI choice, model, reasoning strength and role→An agent that starts after all selections are confirmed
Continue the same task
An agent name in the current main conversation→Continuation of the same CLI session
04Who is it for? When not to use it?
Good for
- People already using several AI CLIs
Not for
- Model services, subscriptions and API quotas are not included; each CLI sends model requests through its own provider.
- No additional OS process sandbox is supplied. The plugin uses native CLI protection modes and refuses launch when Harness is in planning or read-only mode.
05Compatibility, maintenance and safety notes
- Model services, subscriptions and API quotas are not included; each CLI sends model requests through its own provider.
- No additional OS process sandbox is supplied. The plugin uses native CLI protection modes and refuses launch when Harness is in planning or read-only mode.
README claims; MIT license
06Frequently asked questions
Does this DSH plugin include model subscriptions or API quota?
No. Install the external CLIs and use their own login or API configuration; requests go to their respective providers.
Can I continue a named agent from DSH?
Yes, within the same main conversation. It reuses the same CLI session, and renaming preserves history and the role.
Must DSH be restarted after installation?
Yes. End tasks and completely exit Harness before installation, then cold-start it afterwards.
07Related DSH workflows
archify
by tt-a1i
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
openviking
by volcengine
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
nocobase
by nocobase
NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.
learn-harness-engineering
by walkinglabs
Harness engineering beginner tutorial, from 0 to 1
08Data and sources
dsh-cliworker-now 是 **DeepSeek Harness 的独立多 CLI 智能体插件**。
项目采用 [MIT License](LICENSE)，是独立社区插件。
项目使用 **TypeScript ESM + React**
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-10-18. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.