dsh-agent-team
Run the following command in DeepSeek Harness:
dsh plugin install wowyuarm/dsh-agent-team
Paste the following prompt into your AI chat to install this plugin:
To install this plugin, run the command: dsh plugin install wowyuarm/dsh-agent-team in DeepSeek Harness, or visit https://github.com/wowyuarm/dsh-agent-team for more information.
About this plugin
In modern AI collaboration, task management often remains fragmented, with agent sessions being transient and hard to track, leading to low team efficiency. The dsh-agent-team plugin offers a structured solution for DeepSeek Harness, building a persistent team environment where humans can manage tasks in an orderly way. Its core capabilities lie in transforming agents into persistent collaborative identities, organizing resources per project through workspaces, clarifying responsibilities via channels, and linking a series of sessions into a coherent progress trajectory with task threads. It also provides a set of specialized team tools and a pull-based collaboration protocol, ensuring consistency and traceability in operations. This plugin is ideal for teams requiring complex task coordination, multi-agent collaboration, or persistent session management—such as in software development projects, research collaborations, or any scenario seeking structured AI workflows—helping users break free from chaotic task flows and focus on core creation.
Screenshots
Use Cases
- Organizing multi-agent teams for project collaboration
- Managing complex task threads and channel responsibilities
- Persistently tracking agent session progress
Best For
- Software development teams
- Project managers and team leaders
- AI collaboration researchers and developers
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.