Discover The Best DSH plugins

DeepSeek Harness plugins — Page 307

39768results

Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.

SuperLcm

SuperLcm — Lossless Context for DeepSeek Harness: fully asynchronous, cache-friendly compaction with exact recall.

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yu381792/dsh-superlcm
tabbit-browser

DSH bundle that packages the Tabbit Browser skill and background installer

Skills · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Tabbit-Browser/dsh-plugin
think-like-codex

Codex-inspired planning, evidence, goal, and anti-loop policy plugin for DeepSeek Harness.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhangnan/think-like-codex
trae2api-dsh

Use TRAE account model quota in DeepSeek Harness, with multi-account management, check-in, rotation and usage statistics

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add https://github.com/FuSheng-cs/Trae2api-dsh/releases/latest/download/trae2api-dsh.tgz
ui-dashboard

DSH 右侧仪表盘 UI 插件:上下文占用(三色圆环)、Token 用量与人民币费用估算、会话统计、目标、待办、后台任务、工作区;支持右侧栏(details 槽位)与会话标签页(conversation.view)两种形态。

Financial data · Interface extensions · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Plocr/dsh-desktop#ae994e2aa831b2514c0510ca18f1d4903c01123f&path:packages/ui-dashboard
visual-review

DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.

Skills · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wang-bool/visual-review
wangdefa-memory

本地优先的 Agent 五层记忆体组件 - DSH 插件

Memory and knowledge · Skills · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:VinsonWild/Wangdefa.Memory
web-forager

Clean-room, robots-aware web information gathering: multi-engine search, HTML/PDF/Office/feed extraction, Bilibili/Zhihu/Xiaohongshu reading, sitemaps and resumable surfing, plus a browser mode with seven read-only playbooks. CLI + two MCP servers.

Skills · Agent collaboration · Developer tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JiamingShi-JsPhys/web-forager
weir-harness

Weir — orchestrator-centric DSH agent preset: intent gate, category delegation, todo driver, pull-based background jobs, auto-compaction, hashline edit.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add weir-harness
weir-test-harness

Dev-only integration test harness for weir-harness (scripted mock LLM + host-level mounts). Never install into a real profile.

Agent collaboration · Interface extensions · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add 'github:WeirLabs/weir#c7ef3919db53cd3c7a5898f862e6123af491829e&path:plugins/weir-test-harness'
what-sub-agents-doing-now

See what each subagent is actually doing: surface the progress notes a child wrote itself, not just running/inactive. Read-only, non-shadowing.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:REALOIYO/what-sub-agents-doing-now
what-was-that

A tiny octopus desktop pet that explains AI-jargon in plain language for the DeepSeek Harness web GUI.

Interface extensions · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SH-9999/what-was-that
worktree-mgr

dsh 插件:为任务自动创建隔离的 git 工作区,管理 创建/同步/收尾 全生命周期

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JohnXu22786/worktree-mgr
Xsdsh-purge

Crow-purge 逆向模式:跨平台逆向分析指挥体系(iOS / Android / Windows),五角色 + 五阶段 + 证据链;附外挂制作模式

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YAOXIAOYUAN0802/Crow-purge

yapa

★ 2
yapa

YAPA — Memory & Task assistant as a native DeepSeek Harness plugin

Memory and knowledge · Agent collaboration
zzy-dsh-prompt-optimizer

Direct-apply, privacy-aware prompt optimization for DeepSeek Harness.

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhengzeyong9527-droid/ai-input-enhancer
__PACKAGE__

__TITLE__

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add 'github:HYcally/dsh-preset-studio#93d132de6db1cd71fd5dd0b0056415101dda32c0&path:packages/studio/template'
@240xu/dsh-tech-lead

Tech-lead lifecycle plugin for DeepSeek Harness: 21 read-only tools (classify/state/plan/evidence/gates/release/install audits, context/evidence/progress analysis, mutation preview). No writes, no subprocesses, no network.

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:240xu/verdict-engine#b656c8e3284a9b6f1805c49a92873f473a30c976&path:packages/dsh-tech-lead
@240xu/dsh-tech-lead-bundle

Opt-in dsh profile bundle exposing the read-only tech-lead tool surface

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:240xu/verdict-engine#b656c8e3284a9b6f1805c49a92873f473a30c976&path:packages/dsh-tech-lead-bundle
@240xu/dsh-tech-lead-core

Pure, dependency-free validators for the tech-lead lifecycle (state, evidence, plan, gate, release, install audit)

Skills · Agent collaboration
@240xu/dsh-tech-lead-plugin

Read-only tech-lead lifecycle tools for DeepSeek Harness (classify, validate, lint, audit)

Skills · Agent collaboration
@2jumpsina/dsh-context-guard

DSH context-pressure guard: when a session's next request would carry a dangerously large prompt, tell the user at turn end to write the handoff and start a new session. Consumes the official token-meter contextPressure projection; injects no prompt, registers no model-facing tool, so its context tax is zero. v0.3: at 45% occupancy the host half auto-drafts a machine-facts handover block into the session working directory; v0.2 added the host state route and an opt-in (default off) WeChat push; v0.3.2 onwards ships bilingual (zh/en, auto-detected per half) runtime copy; v0.3.3 was a docs-only release that fixed the install instructions once the package was live on npm; v0.3.4 fixes cross-platform absolute-path detection in resolveHandoverPath (a Windows-style path was treated as relative on Linux) and moves publishing to CI with npm trusted publishing (OIDC).

Notifications · Financial data · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:2JumpSinA/dsh-context-guard
@4t145/lark-connector

Connect Feishu and Lark chats to DeepSeek Harness sessions

Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:4t145/dsh-lark-connector
@7dgroup/dsh-7d-tray-win

Windows-only composition bundle for DeepSeek Harness web: a system-tray icon appears while `dsh web` runs (open UI / open logs / stop / restart), plus a silent desktop launcher that reproduces the exact host invocation. Win32 only.

Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:7dgroup-ai/dsh-7d-tray-win

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.