Discover The Best DSH plugins

Productivity · DeepSeek Harness plugins — Page 158

5702results

Find task management, document processing and everyday workflow automation plugins.

dsh-agent-rules

Felix 项目开发规则:DSH 个人插件。在 Web GUI 右侧栏提供「开发规则」面板(与「Docker 容器」并列,全局规则 + 按项目覆盖),并把当前项目生效的规则自动注入每个会话的系统提示,让 agent 开发项目时自动遵守;另含 agent_rules 工具,便于在对话里直接维护规则。

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Grant-Felix/dsh-agent-rules
dsh-agent-selector

智能体选择器:像模型选择器一样在输入框旁勾选委派目标+具体模型,把对话任务派给外部智能体(Codex CLI / WorkBuddy 内置模型活动价 automation 桥 / WorkBuddy 自定义模型直连 / Claude Code)执行,结果流回 DSH 对话。含 agent_dispatch 工具 + composer 两步下拉 + 设置面板 + 桥健康探活 + 反冒充出处凭证。

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jiang12345-code/dsh-agent-selector
dsh-agent-sentinel

哨兵插件(从 dsh-agent-watch 拆分):监听哨兵文件(.hot-reload-flag)→ 触发时调用沙盒预检(ctx.preflight.run,消费 dsh-agent-preflight 服务)→ 通过才重启 web → 唤醒目标会话 → 清哨兵;预检失败则保留哨兵 + 落盘 incident + 通知(fail-closed,借鉴「编辑前需要阅读」——重启前必须预检)。

Agent collaboration · Notifications · Productivity
dsh-agent-teams

多 agent 团队协作:并行调试、并行功能开发、任务协调、沟通协议、团队构成。受 wshobson/agents(38k★ MIT)启发。

Skills · Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-agent-teams
dsh-agent-teams-approval

DSH web plugin: a Settings → General switch that lets AgentTeams run without the Web plan-approval click.

Agent collaboration · Interface extensions · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mimajiushi/dsh-plugins#1aa8b9d851070af475ca10703d84c000562ef8d7&path:plugins/dsh-agent-teams-approval
dsh-agent-token-stats

Cross-agent local LLM token usage dashboard for the DSH web GUI: scans Claude Code / OpenCode / Cursor IDE / DSH / OpenClaw / QClaw / CodeWhale / WorkBuddy / WPS Claude / Hermes logs (plus Codex/Gemini/Cline/Pi parsers on standby), keeps a persistent ratchet ledger in ~/.agent-token-stats, and serves a sidebar analytics panel with cache-hit rate, cost estimation, period comparison, day drill-down and CSV export.

Agent collaboration · Financial data · Interface extensions · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:skyzhao1223/dsh-agent-token-stats
dsh-agent-vision

多模态视觉插件(辅助通道):把本地图片喂给 OpenAI 兼容 VLM(默认 qwen3.8-flash)做读图/描述/双图对比——批量审图/省主会话上下文;主会话亲眼看图走官方 read_image(原生多模态)

Agent collaboration · Vision tools · Productivity
dsh-agentmail

Give a DeepSeek Harness agent its own email inbox, with inbound mail bound to per-thread sessions.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:agentmail-to/dsh-agentmail
dsh-agentmemory

DSH ↔ agentmemory session-memory bridge (backend-only). Mirrors session lifecycle into agentmemory with standard hookTypes (compression-friendly, dedup-safe), exposes memory_recall / memory_remember tools, and injects memory context via agent/pre-step. Configuration comes from the cordis.yml row.

Memory and knowledge · Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Yiipu/dsh-agentmemory
dsh-ai-collab

AI 多角色协作开发框架:文件即通信 + 教训库 + 决策日志 + 一致性审计 + 复盘持续优化(REVIEW)。注册 ai_collab_init 工具。

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tengfeizhao1219/dsh-ai-collab
dsh-ai-image-design

SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。

Skills · Agent collaboration · Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-ai-image-design
dsh-ai-memory

Closes ai-memory's consolidation loop for DSH: when a DSH session ends, calls ai-memory finalize-session so its captured observations become searchable wiki pages the other harnesses ai-memory serves can retrieve. Skips subagents, queues concurrent session ends, and sweeps sessions abandoned by a forced restart.

Memory and knowledge · Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:rasyidmmz/dsh-ai-memory
dsh-airbag

Non-intrusive safety belt for DeepSeek Harness: blocks API keys pasted to the agent, blocks secret writes, tracks leak events, and offers a workspace health scan. 非侵入式安全护栏:拦截粘贴给 Agent 的 API 密钥、写入拦截、泄露追踪与工作区安全体检。

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uwu9039/dsh-airbag
dsh-all-enhance

DSH 功能增强插件:会话删除、增强设置等(基于官方公开服务接口)

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:rangdl/dsh-all-enhance
dsh-all-warmup

Global frictionless warm-up layer plugin for DeepSeek Harness: every session (top-level, every subagent depth, after compaction) runs one independent warmup call with a minimal catalog, then exposes the full original mode from the second round on.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:brunhildzhou/dsh-all-warmup
dsh-almazom-approve-escalate

DSH web plugin: 'Approve & full access' on the approval card and a /yolo composer command — one click switches the live session to the danger-full-access preset and answers the pending approval. Isolated plugin, no core changes, no telemetry.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:almazom/dsh-almazom-approve-escalate
dsh-analytics

Agent FinOps / token analytics for DeepSeek Harness: usage collection, time-aware cost engine, cache analysis, and session drill-down

Agent collaboration · Financial data · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hccccc01333/dsh-analytics
dsh-anchor-rail

DSH Web 会话锚点导轨插件:左侧导轨展示当前模型表面全部用户问题,悬浮显示全部锚点名称(与导轨对齐),点击快速跳转。Session anchor rail for DeepSeek Harness Web.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lyfZhixing/dsh-anchor-rail
dsh-animation-studio

dsh plugin: an in-harness agent workbench for teaching animation & video production

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:YJLTF/dsh-animation-studio
dsh-anime-skins

DSH anime skin manager: 6 skins, custom message layout, floating menus and theme-adaptive UI overrides.

Interface extensions · Productivity
dsh-annotator

DeepSeek Harness 插件:在右侧栏文档预览里对图片、SVG、PDF、HTML、Office 文档直接画标注,标注可保存并填入当前会话

Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xujian519/dsh-annotator
dsh-antigravity-usage

反重力(Antigravity)额度 / 用量监控:实时额度走本地语言服务器 API,离线用量只读扫本地会话库(反重力没开也能看历史)

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kirigayakazima/dsh-antigravity-usage
dsh-any-attachment

dsh bundle: attach any file type in dsh web — text-likes inline, binaries as workspace path references, rasters via the built-in pipeline

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Zenjibad/dsh-any-attachment
dsh-aoci-panel

AOCI 认知面板:在会话视图标签中展示当前项目的 AOCI 索引概览、治理状态与条目浏览。

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:donyue7/dsh-aoci-panel

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.