DeepSeek Harness Plugin Hub

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

Explore

Plugins Presets Docs News

Community

Publish a plugin Contact Report an issue

Resources

Plugin Hub on GitHub DeepSeek Harness System status Privacy notice

© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

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

CATEGORY

Agents & Orchestration DSH plugins

Verified manifests and exact versions in this category.

All categories

All plugins Agents & Orchestration1.5k Memory & Context2.1k Coding & Developer Tools3.9k UI & Customization5.6k Integrations & Communication3k Vision & Media908 Search & Research1.2k Security & Access1.8k Models & Usage2.4k Productivity & Workflow3.6k

All plugins

1531 plugins

Novel Writer

Multi-Core Collaborative Novel Writing — a DeepSeek Harness (DSH) preset plugin that installs a multi-agent novel-writing mode: one conductor plus five specialized subagents (多核协同写作模式).

Updated 11/4/2026✓ Scan passed

whale-persona

Whale Persona

Persona engine for AI coding harnesses (DeepSeek Harness; the ZCode adapter is retired as of 2026-09-19 and kept for history only): self-name per model, self-image (appearance) and reply tone per model (both opt-in), user address, stance, character, per-i

↓ 1.2k★ 7

Updated 11/4/2026✓ Scan passed

dsh-acp-server

Acp Server

Agent Client Protocol (ACP) server plugin for the DeepSeek Harness (dsh) — drive dsh agents from Zed and any ACP client

Updated 11/4/2026

Taskfold

Keeps long coding-agent sessions lean: wrap a stretch of work in a named task, and when it ends, fold that whole span into one short titled summary. The conversation stays readable, context costs stay low, and any fold's original content can be read back

Updated 11/4/2026✓ Scan passed

@banana-peeljj12/dsh-trellis

Trellis

Self-contained Trellis workflow trigger for DeepSeek Harness: per-turn breadcrumb injection via agent/pre-step, a bundled skill provider, and DSH-native task/phase state resolution. No Trellis AGPL code is vendored; workflow semantics are rewritten and li

Updated 11/4/2026

Sgme

SGME memory engine bridge for DeepSeek Harness — multi-agent shared long-term memory via HTTP.

Updated 11/4/2026✓ Scan passed

dsh-global-rules

Global Rules

Edit the user-global AGENTS.md ($DSH_HOME/AGENTS.md) from the web settings panel.

Updated 11/4/2026✓ Scan passed

Auto Pwa

AI-driven partial wave analysis for DeepSeek Harness: physics-gated config editing, ctpwa fit execution, numeric evaluation, and goal-driven iterative convergence. Physics knowledge (PDG-2026) as pure functions; DSH integration as a thin pwa_* tool plugin

Updated 11/4/2026✓ Scan passed

@lemoncat7/dsh-partner

Partner

Long-lived AI companions with QQ, WeChat, Matrix and Mattermost channels for DeepSeek Harness

Updated 11/4/2026

Workplan

Automatic task decomposition, real department subagents, and a responsive workplan dashboard for DeepSeek Harness.

Updated 11/4/2026

@aident-ai/cli

Cli

Aident CLI — umbrella access to Loadout integrations, Playbook automation, Intern tools, and the Aident platform.

Updated 11/4/2026✓ Scan passed

dsh-whale-soul

Whale Soul

A soul for DeepSeek Harness: an in-character Whale Chan agent preset with layered long-term memory and dream-like consolidation.

Updated 11/4/2026✓ Scan passed

@ryubyte/dsh-a2a

A2a

Agent2Agent (A2A) protocol v1.0 plugin for DeepSeek Harness (DSH): outbound client (remote AgentCard skills as ctx.tools), inbound server (A2A JSON-RPC + AgentCard endpoint), and a settings dashboard of live A2A connections

Updated 11/4/2026

@morlay/dsh-subagent

Subagent

Thin-shell fork of @deepseek-ai/dsh-subagent: takes over the `subagent` row only to replace the continuable-child return guidance with Chinese wording; everything not intentionally changed is imported from the vendored upstream source

Updated 11/4/2026✓ Scan passed

dsh-switchman

Switchman

Autonomous Agent Teams doctrine for the four shipped DeepSeek Harness presets, plus language preferences, dispatch pools with model ranking, and context watermark control.

Updated 11/4/2026✓ Scan passed

dsh-bili-subagent

Bili Subagent

DSH plugin: Let your AI companion dispatch sub-agents to browse B站 — sub-agents read subtitles, pick out what’s worth watching, and report the details back, then the companion sends you DMs or comments @ you in its own voice.

Updated 11/4/2026✓ Scan passed

@javierfrancoleal/workflow-master

Workflow Master

Agentic-workflow trigger layer: listening mode that captures conversations, decodes the requests, and builds the workflow — automatic actions, proposals, and questions.

Updated 11/4/2026✓ Scan passed

dsh-clawrouter

Clawrouter

A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 73 models from one wallet. No accounts, no API keys.

Updated 11/4/2026✓ Scan passed

dsh-continual-harness

Continual Harness

Standalone DeepSeek Harness plugin: continual harness self-evolution. The agent persists and refines reusable prompt notes, memories, skill contracts, and subagent specs through small evidence-backed edits, with automatic refinement gates, rollback, and p

Updated 11/4/2026✓ Scan passed

dsh-worktree-space

Worktree Space

Worktree Space: one task, one space, with work proceeding in parallel. Place a task involving one or more Git repositories in an independent task space, with each participating repository getting a worktree on the same task branch. Advance multiple tasks in parallel without interference, then merge

Updated 11/4/2026✓ Scan passed

dsh-swarm-orchestrator

Swarm Orchestrator

Role-based AI swarm orchestration for DeepSeek Harness: duty-table model pinning per role, parallel task DAG with review loops, and a live Swarm dashboard tab in the web GUI.

Updated 11/4/2026✓ Scan passed

@log.li/dsh-automode

Automode

CC-style auto mode for DeepSeek Harness: deterministic deny/allow rules + pre-execute gate + model-agnostic two-stage classifier. Two-state (allow/reject) classifier since 0.8.0. TypeScript rewrite merging dsh-auto-mode v0.4.1 with Nuo-cl/dsh-auto-mode na

Updated 11/4/2026

Rolebox

Agent plugin for major harnesses — DeepSeek Harness (DSH), OpenCode, Pi and Codex: define custom AI agent roles with per-role prompts, models, skills, permissions, memory and multi-agent orchestration.

Updated 11/4/2026

dsh-auto-model-routing

Auto Model Routing

DeepSeek Harness plugin: independent Jev capability and effort decisions, enforced fresh-child routes, decision visibility and allocation feedback

Updated 11/4/2026

@anonyjcy/dsh-j-space

J Space

J-Space Cognition Suite SV1 native Agent Preset and standalone plugin for DeepSeek Harness

Updated 11/4/2026✓ Scan passed

Get Fable

A portable coding lifecycle and autonomous repository steward for AI agents with deterministic routing across 46 skills, durable state, mutation-aware verification, continuous CI healing, specialized skill packs, lifecycle hooks, DeepSeek Harness plugin &

Updated 11/4/2026✓ Scan passed

Tower

DSH-native Tower: mission planning, worktree isolation, review-gated merges, and a human-owned Tower mode.

Updated 11/4/2026

Kingdom

Clear Agent workspace: view tasks and territory sessions, dispatch tasks, and have sessions guide supervisor binding and takeover; execution results still require supervisor review.

Updated 11/4/2026✓ Scan passed

dsh-cc-ecosystem

Cc Ecosystem

One-install bundle for the whole dsh-cc ecosystem: pulls in dsh-cc-loader plus the six Claude Code adapters (skills, permissions, agents, hooks, mcp, memory) and mounts all of them in one profile layer.

Updated 11/4/2026✓ Scan passed

dsh-plugin-subagent-bridge

Plugin Subagent Bridge

Subagent bridge: lets Codex delegate a task to DeepSeek Harness the way it would spawn a subagent (one call, waits for the answer), plus a codex_dispatch tool for the reverse direction.

Updated 11/4/2026✓ Scan passed

← Previous 1 2 3 4 5…52 Next →

DeepSeek Harness Plugin Hub

Profiles Plugins Categories News Docs Sign in Manage Profiles

Profiles Plugins Categories News Docs Sign in