Captain-led multi-agent teams that split a goal into tasks and dispatch them along an execution chain to members running in their own sub-sessions, each with its own model.
Install
# from npm (prebuilt)
dsh plugin --profile web add dsh-eteams
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:2507483326/dsh-eteams
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
ETeams
让 AI 组成一支真正的团队。
领队拆解目标,成员接力执行 —— DeepSeek Harness 的多智能体团队协作插件。
这是什么
ETeams 给 DeepSeek Harness 装上「一支团队」:你把目标丢给领队,领队把目标拆成任务、按执行链派给成员,每个成员在自己的子会话里独立干活,进度、失败、决策实时可见。
不是「一个大模型假装多个人」,而是真实的多会话协作,你可以自由调度成员,并给每个成员不同的模型。
- 包名
dsh-eteams,插件 ideteams,双端单包(宿主端 + 浏览器端)。 - 自包含:构建产物已内联全部依赖,无运行时安装负担;状态存本机 SQLite(内置
node:sqlite),不联网、不上传。
三步上手
| 步骤 | 做什么 |
|---|---|
| 1 · 添加成员 | /eteam 面试式生成角色手册,落进全局角色库 —— 每个角色就是一张岗位卡。 |
| 2 · 组件团队 | 面板「团队」页从角色库挑人进班子,指定一人为领队。 |
| 3 · 创建任务 | 对话里说清目标 → 领队拆解、你批准 → 自动派发执行,全程在面板围观。 |
特色
1. 定制 system 角色

你可以通过角色中的 system 来定制你的所有会话, 这样你就有一只专属的猫娘助手了
2. 为每个角色设置不同的会话模型

你可以为团队中的每个成员设置不同的会话模型,让不同的模型在任务中流转
界面展示

安装
方式一:插件市场(推荐)
在 DeepSeek Harness 插件市场搜索 ETeams,一键安装后重启应用。
方式二:命令行
dsh plugin --profile desktop add dsh-eteams
方式三:本地源码(开发调试)
git clone https://github.com/2507483326/dsh-eteams.git && cd dsh-eteams
pnpm install && pnpm build
dsh plugin --profile desktop add .
安装后核对装配结果,并重载客户端:
dsh --profile desktop --dump-config
Links
More in this category
loopx-project/loopx#dsh-loopx-plugin★ 6398
LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.
Q00/ouroboros#integrations/dsh-plugin★ 6260
Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.
chuspeeism/dashi-taskboard#deepseek-harness★ 3388
Embeds the active installed Codex Taskboard runtime in the DeepSeek Harness sidebar, using its launcher runtime descriptor instead of a fixed port.
NanmiCoder/dsh-agent-teams★ 2368
AgentTeams multi-agent teams.
EthanYoQ/AI-Novel-Writer#dsh-ai-novel-writer★ 1753
Installs a dedicated AI novel-writing preset and workbench: revisioned local project assets, a compact side drawer, and native approval-gated single-file changes.
Miaotofu01/Study-Mate★ 1144
Your AI learning companion: helping you plan your studies, understand concepts, and build projects to master a subject.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.