Discover The Best DSH plugins

Agent collaboration · DeepSeek Harness plugins — Page 236

7478results

Explore agent orchestration, multi-agent collaboration and task execution plugins.

dsh-codebase-scanner

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
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-skills-bundle#453fc2cf12e007b72e48f568e0ffe1fe4e13c616&path:plugins/dsh-codebase-scanner
dsh-codebuddy-models

CodeBuddy/WorkBuddy models bundle for DeepSeek Harness (dsh): reads the local desktop login and serves the CodeBuddy subscription as a native provider route in the model picker

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:evlon/dsh-codebuddy-models
dsh-codegraph

CodeGraph for DSH — registers 13 native `codegraph_*` tools (status/init/index/sync/uninit/query/node/explore/files/callers/callees/impact/affected) wrapping the `codegraph` CLI, so the DSH agent can bootstrap, maintain, and query a pre-indexed code knowledge graph without grepping files.

Memory and knowledge · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jiangzhenguo/dsh-codegraph
dsh-codetime

CodeTime backend for the DeepSeek Harness session-telemetry seam: reports session/turn/tool/file activity to codetime.dev via /v3/agent/ingest

Agent collaboration · Productivity
dsh-codex-bridge

Expose the live web-profile session controller over loopback HTTP so external agents (e.g. Codex via an MCP server) can create sessions, inject prompts, read history and cancel turns (web profile plugin, host-only)

Agent collaboration · Integrations · Productivity
dsh-codex-compatible-pet

Codex-compatible desktop pet for the DeepSeek Harness web GUI: animated pets that follow the agent state

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:youzhoujiMrLiu/dsh-codex-compatible-pet
dsh-codex-kanban

AI-native Kanban and Codex chat fusion for DeepSeek Harness

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sonozaki7/dsh-codex-kanban
dsh-codex-media

Document and image analysis tools for agent harnesses, powered by a local OpenAI Codex CLI.

Agent collaboration · Vision tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:binsarjr/dsh-codex-media
dsh-codex-mode

Lightweight Codex-shaped coding tools for DeepSeek Harness: exec_command/write_stdin, apply_patch, view_image, OpenAI model routes, and DSH-native todo_write/ask_user_question/subagent in a native DSH preset.

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bainianlaoyao/dsh-codex-harness
dsh-codex-observability

Two small plugins for DeepSeek Harness that close the observability gap around external subagent runs. Background and upstream proposal: discussion #1493.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jeremy9682/dsh-observability
dsh-codex-preset

Codex 模式 agent preset for DSH / An OpenAI-Codex-style engineering workflow: explore → plan → implement → verify → integrate, with evidence discipline baked into the persona.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qianai05233/dsh-codex-preset
dsh-codex-reasoning-router

Luna executor with a tool-less Sol reasoning advisor for DeepSeek Harness

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chenmzh/dsh-codex-reasoning-router
dsh-codex-review

A deterministic /review command for DeepSeek Harness: a reviewer subagent pinned to a subscription-backed Codex model, with a settings card, one reviewer session per chat, and /review reset to forget it.

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:vitas/dsh-codex-review
dsh-cognition

A project memory for your DeepSeek Harness agent — constrain / observe / remember / verify, built on DSH native primitives.

Memory and knowledge · Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:scd13150/dsh-cognition
dsh-comfyui

Drive ComfyUI from DeepSeek Harness: generate and process images and videos through agent tools, with a workflow/asset/queue panel, in-chat results and a settings page. / 让 DeepSeek Harness 的 Agent 直接驱动 ComfyUI 生成与处理图像、视频,带工作流/资产/队列面板。

Agent collaboration · Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:fandc520/dsh-comfyui
dsh-comfyui-commander

让 DSH Agent 通过自然语言全自动控制 ComfyUI:工作流列表/加载/UI→API 转换、任务提交与参数覆盖、进度监控(队列+WebSocket)、结果获取与下载、批量编排。

Agent collaboration · Vision tools · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:suika009/dsh-comfyui-commander
dsh-comfyui-image

Drive a local ComfyUI image workflow (Z-Image-Turbo, Qwen-Image-2.1) from DeepSeek Harness

Agent collaboration · Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:QXingYShu/dsh-comfyui-image
dsh-command-queue

DSH 插件:让 /compact 等斜杠命令在 agent 忙碌时进入命令队列,空闲后自动执行;并在浏览器里以复刻原生队列的样式展示这份队列。

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kuyueliuhun-ctrl/dsh-command-queue
dsh-command-scout

Scans the project workspace at startup and exposes its declared build commands (Makefile targets, package.json scripts, just recipes, deno tasks) as callable agent tools.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JohnXu22786/command-scout
dsh-commandcode-quota

DSH plugin: Command Code (CC) plan quota in the top-right corner — 5-hour / weekly / monthly windows with reset countdowns, plus billing-period token totals and plan status.

Agent collaboration · Financial data · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:s11phere/dsh-commandcode-quota
dsh-commit-message

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
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:satan9394/dsh-skills-bundle#453fc2cf12e007b72e48f568e0ffe1fe4e13c616&path:plugins/dsh-commit-message
dsh-compact-model

DSH host plugin: makes /compact use a user-chosen provider/model instead of the session's chat model, configurable in Settings.

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-compact-model
dsh-companion

DeepSeek Companion — DeepSeek Harness 官方伴侣插件:对话智能导出、上下文交接摘要、API 成本优化、全局对话检索。

Agent collaboration · Financial data · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:beijingwahw/dsh-companion-dev
dsh-companion

A friendly status and context-pressure companion for DeepSeek Harness Web

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gjnzsu/dsh-companion

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.