
NanmiCoder/dsh-agent-teams
AgentTeams
Agent team orchestration for DeepSeek Harness. Split a long job across sub-agents.
Install
npx @deepseek-ai/dsh plugin --profile web add github:NanmiCoder/dsh-agent-teamsRestart `dsh web` after install. Bundle APIs can change during the developer preview.
README badge
[](https://dshhub.dev/plugins/dsh-agent-teams)Paste this into your README. The star count updates with every catalog sync.
From the README
Excerpt from NanmiCoder/dsh-agent-teams, cleaned of badges and images.
<strong>English</strong> · <a href="./README_ZH.md">简体中文</a>
One prompt. A working team.
dsh-agent-teams turns the current DeepSeek Harness session into a captain that can assemble durable sub-agents, split a goal into dependency-aware tasks, and coordinate work through direct messages.
Ask in natural language. The plugin provides the team protocol, 14 coordination tools, persistent state, an automatic shared-task scheduler, and a live Web UI—without requiring a separate workflow engine.
Releases
v0.1.21 brings teams into the native Harness workspace, restores View team in chat, and fixes narrow layouts. This is the npm latest release; the recommended host is Harness 0.1.7-rc.2 (its next channel). See the exact support matrix.
Why AgentTeams?
| Capability | What it changes |
|---|---|
| Captain-led delegation | The current session creates the team, assigns roles, and consolidates the final result. |
| Durable members | Members are continuable DSH sub-agents that can be woken for focused follow-up turns. |
| Dependency-aware tasks | Tasks move through explicit states and cannot be claimed before their dependencies finish. |
| Automatic reuse and safe takeover | Idle members claim the next ready task; reassignment revokes stale attempts before new work starts, and cold recovery retries stranded open attempts. |
| Direct messaging | Members send durable mailbox messages directly to teammates or the captain—no relay required. |
| Live activity panel | The Web UI combines segmented progress, a collapsible roster, and an interactive task DAG; running tasks show the member's model, and completed archives retain their full member and task history. |
| Plan before execution | Normal /agent-teams runs stage an unspawned roster and DAG first. The Web panel uses the host model catalog for member routes. Returning to chat stops the planning turn, asks what should change, and revises the same draft; discarding archives the draft, aborts the turn, and explicitly prevents automatic recreation. Only Approve & Run enables scheduling; each member starts with its first ready task. |
| Quality gates | Opt-in quality tasks support requirements → implementation → verification → review → integration contracts, automatic repair/re-review, and explicit resume. Scope control is a completion-time audit, not host write interception. See docs/quality-gates.md. |
The conversation card and activity panel use Harness's official locale service. They follow live language changes between English and Simplified Chinese—including status labels, dynamic summaries, controls, archive markers, and accessibility text—without a page reload or a separate plugin setting.
Install and choose versions
Recommended pair: DeepSeek Harness 0.1.7-rc.2 + AgentTeams 0.1.21. Harness remains a prerelease.
| Use case | DeepSeek Harness | AgentTeams plugin |
|---|---|---|
| Recommended | 0.1.7-rc.2 | 0.1.21 |
| Legacy RC | 0.1.5-rc.1, 0.1.5-rc.2, 0.1.5-rc.3 | 0.1.21 |
| Retaining an older RC | 0.1.2-rc.1 | 0.1.21 |
| Developer Alpha testing | 0.1.2-alpha.5 | 0.1.21 |
| Retaining an older Alpha | 0.1.2-alpha.2 | 0.1.21 |
1. Install DeepSeek Harness
npm install --global @deepseek-ai/[email protected]
dsh --version
…
