Discover The Best DSH plugins

Agent collaboration · DeepSeek Harness plugins — Page 116

7257results

Explore agent orchestration, multi-agent collaboration and task execution plugins.

@dsh-plus/subagent-model

dsh-plus service+ui plugin: 为 subagent/subagent_fork 等子代理按提供商配置模型与思考程度(或继承主代理)

Agent collaboration · Notifications · Interface extensions
@dsh-plus/ui-mobile-fit

dsh-plus ui plugin: 纯 CSS 覆盖的移动端窄屏响应式适配(不注册替代组件,跟随上游)

Agent collaboration · Notifications · Interface extensions
@dsh-plus/usage-panel

dsh-plus service+ui plugin: 全量会话 token 用量聚合面板——实时+历史扫描双通道,按日/模型报表,可选价目估算费用

Agent collaboration · Notifications · Financial data · Interface extensions · Productivity
@dsh-plus/web-files

dsh-plus ui plugin: Web 内嵌类 SFTP 文件浏览与编辑(远程/移动端无本地编辑器时预览并编辑服务器文件)

Agent collaboration · Notifications · Interface extensions
@dsh-plus/web-terminal

dsh-plus ui plugin: Web 内嵌持久化终端工作台(多会话/桌面分屏/scrollback 回放,dsh 运行期间保活)

Agent collaboration · Notifications · Interface extensions · Developer tools · Productivity
@dsh-remote/workspace-plugin

SSH-backed remote workspaces for DeepSeek Harness

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:trrrrrryg/dsh-remote-workspace
@dsh-remote/workspace-plugin

DSH SSH Forge — secure SSH-backed remote workspaces for DeepSeek Harness

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:trrrrrryg/dsh-ssh-forge
@dsh-self-evolving/candidate-baseline

Stable baseline parent candidate. Namespace-form DSH bundle; loaded through the real Cordis Loader in Gate 0. Not a profile, not a generated candidate.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:timwhitez/dsh-self-evolving#4eb3bb4058dce4330ecbfc2b96e9c2bdabb71677&path:packages/candidate-baseline
@dsh-self-evolving/candidate-v011-baseline

Evidence-first, crash-resumable self-evolution engine for DeepSeek Harness and Harbor.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:timwhitez/dsh-self-evolving#4eb3bb4058dce4330ecbfc2b96e9c2bdabb71677&path:packages/candidate-v011-baseline
@dsh-self-evolving/core

Trusted durable RSI controller: content-addressed object store, hash-chain journal, pure state reducer + snapshot, action saga, budget double-entry ledger. Crash-safe by construction; the filesystem is the source of truth (spec 06).

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:timwhitez/dsh-self-evolving#4eb3bb4058dce4330ecbfc2b96e9c2bdabb71677&path:packages/dsh-self-evolving
@dsh-squad/plugin

DSH-native delegation for distributed teams of independently owned personal Agents

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhouCode/dsh-squad#4c0bc1eea3508d46be908f8149db44960d5da356&path:packages/plugin
@dsh-survival/engine

Survival-mode rules engine: hunger/hp/day-night/mob settlement, tool gates, mining drops, save persistence and the dsh-survival settings namespace

Agent collaboration
@dsh-survival/hud

Survival-mode HUD bridge: a Minecraft-style browser status bar (hearts + drumsticks) reading the survival engine through a host-plane Typert Remote, gated to survival sessions only

Agent collaboration · Integrations
@dsh-survival/tool-survival

Survival-mode tool package: survival_status / survival_craft / survival_eat / survival_sleep plus the HUD prompt section

Agent collaboration
@dsh/dynamic-agents

动态AGENTS.md:输入框上方 Dock 的「上下文」下拉多选控件,按工作区维护可勾选的动态上下文规则,注入会话系统提示;同工作区新会话沿用上次勾选;会话开始后仍固定在输入框上方并锁定编辑、解锁需确认。

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hw-cola/dsh-dynamic-agents
@dsh/remote-control

远程控制:设置面板新增“远程控制”页,开启后通过 Node 反向代理把 DSH WebUI(默认 3080 端口)暴露给局域网,手机扫码二维码即可访问。

Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hw-cola/dsh-remote-control
@dshchem/dsh-chem-core

Host-plane chemistry engine for DSH: RDKit/ASE-backed molecular service (validate / props / convert / calc / reaction), PubChem + Crossref lookups, recipe library, and browser tool-card structure rendering. Provides the `chem` service consumed by preset tool rows.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:cloudbywu/dshchem#50f6a4224b863a5551dedee7ba665cd1c32738e6&path:packages/dsh-chem-core
@dshchem/dsh-tool-chem

Preset tool rows for the DSH chemist agent: 24 chem_* tools (molecular properties, retrosynthesis, drug-likeness, ADMET, docking, virtual screening) as thin model-facing consumers of the host `chem` service from @dshchem/dsh-chem-core.

Agent collaboration
@dshserver/dsh-deliverables

Open a managed Runtime's produced files in the browser instead of on the server's desktop

Agent collaboration · Interface extensions
@dshserver/dsh-embed-chrome

Let the page embedding a managed Runtime own its sidebar brand, hero line, and workspace switcher

Agent collaboration · Interface extensions · Productivity
@dshserver/gateway-server

Runnable Runtime Gateway server: authentication hooks, RPC lockdown and DSH traffic proxying

Agent collaboration

Find the right plugin, then get started

  1. Search by task

    Use a feature keyword or category, then sort by recent updates or GitHub stars.

  2. Explore capabilities

    Read the description, AI analysis and original README to understand what a plugin does.

  3. Check and install

    Review compatibility, dependency ranges and instructions, then copy the available install command.

Questions about DSH Hub

What is DSH Hub?

DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.

Does inclusion mean a plugin is tested and compatible?

No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.

How do I install a plugin?

Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.