DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Agents & Orchestration DSH plugins — Page 24

CATEGORY

Agents & Orchestration DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1030Memory & Context1285Coding & Developer Tools2778UI & Customization3631Integrations & Communication1886Vision & Media611Search & Research855Security & Access1258Models & Usage1662Productivity & Workflow2224

All plugins

1035 plugins
Av2.0.0
dsh-agents-in-the-loop

Agents In The Loop

DSH agent coordination: named session messaging, persistent spawning, authenticated MCP access, external poll/ack inboxes, and session-backed workspace identities. Optional capabilities ship disabled.

agents-orchestrationintegrations-communicationsecurity-access★ 0↓ 0
Updated 10/10/2026
v0.1.2
dsh-plugin-subagent-model-route

Plugin Subagent Model Route

Annotate every subagent with the model route it actually ran on: a badge line in each parent-catalog row and a readout in a child session's own header.

models-usageagents-orchestration★ 0↓ 0
Updated 10/10/2026
Rv0.6.6
recruiting-copilot

Recruiting Copilot

AI Recruiting Copilot — DeepSeek Harness profile bundle: registers recruiting workflow skills (job requirement organization, dual-channel sourcing and initial screening, interview scheduling, résumé evaluation, tracking and daily reports), and provides a boss/liepin browser observation panel on the

search-researchagents-orchestration★ 0↓ 0
Updated 10/10/2026
Tv0.4.1
@local/dsh-taskforce

Taskforce

DSH Imperator (dsh指挥官) — A multi-agent production tool where the main session directs decisions and a legion of sub-agents carries out execution (DSH agent preset)

agents-orchestration★ 0↓ 0
Updated 10/10/2026
Dv0.4.0
dsh-duck-fleet

Duck Fleet

DuckFleet: one flock of machines, one command. Add a machine once and its ACP delegation tool appears — drive one, several, or all of them from natural language. ／ 鸭群：一群机器，一声令下。添加一台机器即自动获得它的派活工具，用自然语言让某个／某几个／全部机器干活。

agents-orchestrationintegrations-communication★ 0↓ 0
Updated 10/10/2026
v0.4.1
dsh-agent-picker

Agent Picker

Agent mode selector: choose an external Agent CLI (Claude Code / Codex / Qwen / Gemini / Aider / Goose / Hermes / OpenClaw / Ollama…) as the default executor, like selecting a reasoning level. The Agent catalog is data-driven: adding a new Agent only requires adding one data entry, with no code chan

agents-orchestrationdeveloper-tools★ 0↓ 0
Updated 10/10/2026
v0.6.1
dsh-subagent-codex-pro

Subagent Codex Pro

A Codex delegation tool for DeepSeek Harness that can carry a model and a reasoning effort per call.

agents-orchestrationmodels-usage★ 0↓ 0
Updated 10/10/2026
Av1.0.0
amberflow

Amberflow

Frozen-plan browser automation middleware: the LLM plans only once, laya executes step by step, and completion is recognized only by DOM signals

agents-orchestrationproductivity-workflow★ 0↓ 0
Updated 10/10/2026
Wv0.3.0
dsh-workbuddy-project

Workbuddy Project

Configure DSH projects with experts, skills, rules, connectors, and optional shared capability libraries.

agents-orchestrationintegrations-communication★ 0↓ 0
Updated 10/10/2026
Jv0.1.4
dsh-jev-judge

Jev Judge

A judgment kernel for coding agents: bounded questions a small Jev judge answers, so the main model keeps its context and tokens for real reasoning.

agents-orchestration★ 0↓ 0
Updated 10/10/2026
Av0.1.0
dsh-agent-prompt

Agent Prompt

Agent Prompt — edit the user-global and per-workspace AGENTS.md files DSH actually loads, from a left-sidebar panel in the DeepSeek Harness GUI

agents-orchestrationui-customization★ 0↓ 0
Updated 10/10/2026
Tv0.1.0
@agi321/dsh-temp-chat

Temp Chat

Temporary Q&A: /single-turn and /multi-turn use independent sub-agents to search the web and answer questions. Results remain only in the current conversation and do not enter the main model context.

search-researchagents-orchestration★ 0↓ 0
Updated 10/9/2026
v0.3.5
@hanphone/dsh-a2a

A2a

Agent2Agent (A2A) v1.0.1 dual-end plugin for DeepSeek Harness: multiple inbound servers (per-instance agent presets; skills derived from each preset's skill directory), multiple outbound connections, GUI-managed instance lifecycle.

integrations-communicationagents-orchestration★ 0↓ 0
Updated 10/9/2026
Ev0.1.0
dsh-expert-suite

Expert Suite

DSH「专家体系」plugin: single-role experts (persona + methodology + tool whitelist) and multi-Agent expert teams (team lead orchestration, sequential/parallel execution, integrated delivery), supporting manual creation / file import / AI generation.

agents-orchestration★ 0↓ 0
Updated 10/9/2026
Sv1.0.0
@local/dsh-secretary

Secretary

Lets one secretary agent create projects (workspaces) and run threads (sessions) inside them.

agents-orchestrationproductivity-workflow★ 0↓ 0
Updated 10/9/2026
v1.1.1
dsh-ralph

Ralph

DeepSeek Harness plugin for the Ralph autonomous AI loop: repeatedly launches fresh sub-agents to implement the user stories in prd.json one by one until all are complete.

agents-orchestration★ 0↓ 0
Updated 10/9/2026
Av0.2.1
@dtranx/assistant-manager

Assistant Manager

Assistant management plugin for deepseek-harness: manage AI assistants with per-assistant markdown profiles, chat-integrated creation flow, and context injection.

agents-orchestration★ 0↓ 0
Updated 10/9/2026
Ov0.8.3
dsh-orquestrator

Orquestrator

DeepSeek Harness plugin: a native-looking modal on task send lets you pick the model subagents run on. The pick, a reasoning-effort ceiling and an output-token cap are enforced in code on every child DSH starts, whichever tool starts it: the subagent tools, a workflow, ralph or a one-shot background

agents-orchestrationmodels-usage★ 0↓ 0
Updated 10/8/2026
Bv0.1.0
@dsh-zcode/bridge

Bridge

Official ZCode Agent runtime and native DSH GUI bridge

agents-orchestrationintegrations-communication★ 0↓ 0
Updated 10/8/2026
Ov0.3.1
@hawk2048/oh-my-dsh

Oh My Dsh

oh-my-dsh: DeepSeek Harness multi-agent orchestration layer — OMC-style workflow skills, slash commands, and an agent preset.

agents-orchestration★ 0↓ 0
Updated 10/8/2026
Wv0.1.0
dsh-workflow-studio

Workflow Studio

Workflow Studio for the DeepSeek Harness desktop shell — launch workflows with /workflow and watch every subagent's work and structure in a live board.

agents-orchestrationproductivity-workflow★ 0↓ 0
Updated 10/8/2026
Cv1.1.1
dsh-comsol

Comsol

COMSOL Multiphysics workflow for DSH: the comsol-dsh agent skill (open a model in the desktop, edit parameters, rebuild the mesh, tune the solver, run steady or time-dependent studies with live progress, load results into the desktop plot, evaluate and export) on the bundled comsol-mcp engine. Toggl

integrations-communicationagents-orchestration★ 0↓ 0
Updated 10/8/2026
Qv0.4.0
dsh-quorum

Quorum

Mechanism-enforced discipline layer for DeepSeek Harness agent teams: role cards, quorum termination, evidence-gated reports and cost budgets.

agents-orchestrationmodels-usage★ 0↓ 0
Updated 10/8/2026
Av0.5.0
dsh-atn

Atn

ATN Agent preset for DeepSeek Harness with host-enforced artifact custody boundaries and host-derived local discovery.

security-accessagents-orchestration★ 0↓ 0
Updated 10/8/2026
Tv1.0.1
dsh-thinking-lang

Thinking Lang

DSH plugin: set the agent's reasoning language (Settings → General)

agents-orchestration★ 0↓ 0
Updated 10/8/2026
Sv1.0.7
@aa2246740/dsh-skillhub

Skillhub

DSH manager for user Skills already on disk in Agent home and DSH home

productivity-workflowagents-orchestration★ 0↓ 0
Updated 10/8/2026
Cv1.5.0
dsh-chaoxing

Chaoxing

DSH 学习通 mode: let the large model act as the commander and the script as the hands, completing course tasks in 学习通 as genuine learning (normal speed / no dragging / no fake heartbeats)

agents-orchestrationdeveloper-tools↓ 0
Updated 10/8/2026
Iv0.2.0
dsh-im-alive

Im Alive

IM Human-Like Avatar · Proactive Message Daemon: sends proactive WeChat messages to its owner at irregular intervals, like a real person who only messages when they feel like it—with interval jitter, quiet hours, a daily budget, and duplicate prevention. The LLM decides what to send in the moment us

integrations-communicationagents-orchestrationmemory-context★ 0↓ 0
Updated 10/8/2026
Sv0.1.1
dsh-subagent-concurrency-limit

Subagent Concurrency Limit

Limit concurrent DeepSeek Harness subagent turns and delegation runs

agents-orchestration★ 0↓ 0
Updated 10/8/2026
Dv0.1.1
dsh-decisions-classifiers

Decisions Classifiers

OpenAI Decisions API for DeepSeek Harness: predicate/choice/score classifiers as agent tools and an injectable service, a built-in classifier library, an opt-in pre-execution gate, a Settings page, and a "let a classifier decide" card beside ask_user_question multiple-choice prompts.

agents-orchestration★ 0↓ 0
Updated 10/7/2026
← Previous1…2223242526…35Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in