ui-ux-pro-max

Awesome DeepSeek Harness (DSH) Plugin

English | 中文

A curated list of plugins for DeepSeek Harness (dsh).

DeepSeek Harness is DeepSeek's open-source agent harness — a runnable coding agent (Web and headless), built on a framework where everything is a plugin: models, tools, sandboxes, session storage, UI, even the agent loop itself. Plugins can extend the official coding agent, swap out its core parts, or assemble something entirely different.

This list collects community plugins that are installable via dsh plugin add (each declares a dsh.bundle manifest). PRs welcome.

🛒 Recommended: dsh-market (optional) — the plugin market inside DeepSeek Harness, with every plugin on this list. Simple, friendly UI: one-click plugin install and upgrade, one-click theme switching:

dsh plugin --profile web add dshmarket

The plugin market inside Settings — click to enlarge.

💡 Prefer chat? dsh-find-plugin lets your agent find plugins for you (dsh plugin --profile web add dsh-find-plugin).

ℹ️ On desktop clients. This list is client-agnostic. A plugin is listed because it follows the official protocol — it declares a dsh.bundle manifest and installs with dsh plugin add — not because it adapts to any particular client.

Clients worth a look: dsh-desktop, deepseek-harness-desktop, and deepseek-harness-desktop by anywhere-labs — all ship dsh-market built in, so everything on this list is one click away. Any other good third-party client works too.

[!WARNING] Installing a plugin runs third-party code on your machine with your own permissions — it can read your files, use your credentials, and reach the network. Tool approvals don't sandbox plugin code. Being on this list is not a security review: check the source before you install, and try unfamiliar plugins somewhere that doesn't hold your keys. See the full disclaimer at the bottom of this page.

An entry is added when the plugin installs with dsh plugin add, does what its one-line description says, sits in the right category, and is maintained. Every submission is checked against its own source before merging — if a description claims "46 tools", someone counts them.

That is the whole bar. This list doesn't rank plugins or judge their quality, and we don't want to. Plenty of good software will never appear here, and a slot here proves nothing beyond meeting those rules. They exist so that whatever you pick installs and behaves the way the line said it would.

A listing isn't permanent either: entries whose repos go away, stop being maintained, or turn out to be broken get removed. Full criteria and the review checklist: how submissions are reviewed.

Contents

• Plugins
  • AGI Architecture Exploration
  • UI Enhancements
  • Usage & Billing
  • Themes & Appearance
  • Models & Providers
  • Identity & Communication
  • Sessions & Messages
  • Memory
  • Tools & Capabilities
  • WSL & Windows Interop
  • Browser & Web
  • Vision & Multimodal
  • Voice & Audio
  • Docs & Rendering
  • Skills
  • Workflow & Automation
  • Git & Code Review
  • Notifications & Integrations
  • Development & Runtime
  • Security & Permissions
  • Remote & Mobile
  • Plugin Markets & Managers
  • Just for Fun
• Badge
• Disclaimer

Plugins

AGI Architecture Exploration

• AnonyJcy/dsh-j-space - J-Space Cognition Suite SV1 native agent preset and standalone Cordis plugin: 13 modules, persistent controller and decoupled workspace.
• dsh-answer-reviewer - Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config over a 127.0.0.1 HTTP server, plus a collapsed dock above the composer and an optional right-sidebar tab via dsh-better-sidebar.
• CAI-MH/dsh-quality-review - Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn and SOP-folder standards injected as an extra review dimension.
• FuRongJun-1999/dsh-memory - White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
• dsh-proactive - Host-level proactive wake-ups for DeepSeek Harness: the model schedules its own alarms (once, recurring interval, or cron, with optional random jitter), cold sessions are woken on time by session resume, model-initiated follow-ups are gated by quiet hours and a daily delivery budget, silent wake turns end with proactive_reclaim and fold out of model context as tombstones, declared schedule files glob-sync JSON schedules into host alarms idempotently, min_idle_seconds defers wakes until the destination session quiets down, and a web panel (settings section plus per-session tab, SSE live refresh) manages alarms and wake history — the heartbeat engine for AI companions and roleplay characters with their own daily routines and world evolution.
• john-walks-slow/dsh-simulated-life - Simulated life context for DeepSeek Harness: every turn injects the past 24h of simulated life events from the workspace .life/ directory (sliding-window filter, session-level deduplication with delta updates, world summary) as a collapsed context notice, and the life_react tool lets the agent record feelings, thoughts and actions back into its life log for the next round of world evolution — turning a DSH agent into a roleplay character with a persistent daily life.
• [Jonah-Wu23/dsh-gungnir#dsh-plugin](https://github.com/Jonah-Wu23/dsh-gungnir/