Discover The Best DSH plugins

Agent collaboration · DeepSeek Harness plugins — Page 68

7205results

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

dsh-git-forge

GitHub/Gitea (and other forge) accounts with project-scoped grants and push policy for DeepSeek Harness better-sidebar

Agent collaboration · Interface extensions · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:OMSociety/dsh-git-forge
dsh-gittree

History (package and row `dsh-gittree`, kind/address `gittree` / `sidebar://gittree`): a READ-ONLY git history tab type for the vncode right bar (dsh-rightbar). Lists the session workspace's commits (short id, subject, author, date) in the bar's own dress, with the branch and the current commit kept in the file bar above it; every row sits beside a rail drawing the commit GRAPH - one column per branch lane, a node per commit, the line running up to the newer commit above it, and the curves where a branch leaves a merge or rejoins it - from the parents and ref decorations the history route carries, with a pull-request chip when a merge names one. Picking a commit shows its message and the files it touched, and any of those files opens through the ordinary file address (so the editor or a shipped preview claims it). A page type like the editor: one guide entry on the tab strip's + / Start page, no core patches, nothing forked, and no git command that can write. Alpha.

Agent collaboration · Interface extensions · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:vecnode/vncode#b3a6a0d53b96ef29d452af3962e8d726a122db3a&path:packages/dsh-gittree
dsh-goalmesh-plugin

Installable DeepSeek Harness bundle for goal-driven multi-agent orchestration.

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Jarad-z/dsh-goalmesh#e342c5350bbb4a8c3b43d804d564a379ea3afb8f&path:packages/goalmesh-plugin
dsh-gui-last-session

DeepSeek Harness plugin: remember the conversation you were last in and reopen it after a restart — implemented as a first-class plugin (host half persists the pointer, client half records and reopens) instead of patching engine files.

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:itchenshi/dsh-ready-gui#a886d1165b9c44e9887ad9fd6a8993e23449a0c4&path:plugins/dsh-gui-last-session
dsh-ha-orchestrator

Model high-availability failover + subagent orchestration (fanout/pipeline/supervisor) for DeepSeek Harness

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Saktawdi/dsh-ha-orchestrator
dsh-hardssh

SSH remote workspace + SSH operations for the dsh web GUI: enter SSH mode from the session header, browse/edit remote files in a new left panel, let the local harness operate the remote server through remote_* agent tools, and manage hosts through the ssh_* tools and the SSH panel (legacy dsh-ssh merged in).

Agent collaboration · Interface extensions · Developer tools · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tiphareth0/dsh-sshworkspaces#d5d11e6c02ca02a46961da7c166f78ea6b371099&path:packages/dsh-hardssh
dsh-holdem

Six-max No-Limit Hold'em for DeepSeek Harness: one human and five LLM agents.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:BubblePtr/dsh-holdem
dsh-hooks-plugin

Claude Code style hooks for DeepSeek Harness: run shell commands on agent/tool lifecycle events from .dsh/hooks.json (CC-compatible JSON shape).

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

Humanize Mode for DeepSeek Harness — the humanfia flow philosophy (draft → check → lock → review → run/resume, SHA-256 lock identity, HMAC review gate, event-sourced resumability) as an agent preset. Installing this bundle auto-installs the preset into the DSH preset root.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Guard42/dsh-humanize
dsh-image

Image viewer: a real image tab type for the vncode right bar (dsh-rightbar). PNG, JPEG, GIF, WebP, AVIF, BMP, ICO, SVG and TIFF open in a viewer that FITS the pane, zooms on a ladder (5%-800%) with fit-to-pane and 100%-actual-pixels, wheel-zooms at the pointer with Ctrl/Cmd, and is dragged to pan with a real grab cursor - the image is laid out at its true size in a scrollable box, so a zoom moves the layout and never a CSS transform, and a zoomed picture stays scrollable to its edge. A checkerboard shows PNG transparency, pixelated rendering past 300% makes pixel inspection honest, and the status line names the file's dimensions, size, format and the pixel under the pointer with its colour. Bytes are read through the harness's own workspaceFiles remote, so no new host route, no new surface and nothing shipped is disabled: the type registers in the extension band and REPLACES the shipped preview's bare intrinsic-size image only for image addresses. Alpha.

Agent collaboration · Vision tools · Interface extensions · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:vecnode/vncode#b3a6a0d53b96ef29d452af3962e8d726a122db3a&path:packages/dsh-image
dsh-image-gen

DSH 对话内生成图片:Agent 调用 generate_image 工具,经自定义 OpenAI 兼容端点调用图片模型(gpt-image-1 / gpt-image-2 等),图片保存到工作区

Agent collaboration · Vision tools
dsh-image-subagent

让纯文本主模型(DeepSeek V4 等)也能接收图片附件:图片投影为显式占位文本,由主模型委托视觉子代理经 read_attachment/read_image 读取。零核心补丁,纯插件实现。

Agent collaboration · Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yuqingsh/dsh-image-subagent
dsh-incognito

无痕会话(incognito)插件:DSH Web 里的临时子 Agent——独立 preset 不继承父会话、全量工具集、窗口可拖动、关闭即焚毁、磁盘零痕迹

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:HuiHuitie-zhu/dsh-incognito
dsh-island

自带 macOS 菜单栏灵动岛的 DSH 插件 — 鲸鱼娘桌宠 + DSH 浅蓝胶囊托盘(blue-fantasy 配色),实时显示会话/工具/审批,点击展开可直接批准/拒绝

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:cdxiaodong/dsh-island
dsh-jev-prune

Jev-judged context compaction for DeepSeek Harness. Two layers: prune stale tool results (semantic instead of size-only), and replace spent tool-call ranges with a deterministic receipt instead of a model-written summary.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yangyu666/dsh-jev-prune
dsh-keys-setting

DeepSeek Harness plugin: choose whether Enter, Shift+Enter and Ctrl/Cmd+Enter send the message or insert a line break, from the Settings window's General page.

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:itchenshi/dsh-ready-gui#a886d1165b9c44e9887ad9fd6a8993e23449a0c4&path:plugins/dsh-keys-setting
dsh-kimi-formula

Kimi (Moonshot AI) official Formula tools for DeepSeek Harness: a ctx.web search provider backed by the Formula API chat loop, plus model-facing tools for the remaining official formulas (convert, rethink, random-choice, mew, memory, excel, date, base64, fetch).

Memory and knowledge · Agent collaboration
dsh-lark-channel

Lark/Feishu IM bot channel for DeepSeek Harness: chats drive agents, replies and approvals return as messages and cards

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JunguangJiang/dsh-lark-channel
dsh-lark-claw

A standalone Lark/Feishu gateway and persistent cron bundle for DeepSeek Harness

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Illuminated2020/dsh-lark-claw
dsh-lit-search

Academic literature search, citation and BibTeX tools for DeepSeek Harness and any agent (Crossref + OpenAlex + Semantic Scholar).

Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Flan246/dsh-lit-search
dsh-llm-headers

Inject custom HTTP headers (user-agent etc.) into DeepSeek Harness LLM provider requests, configured through cordis.yml or the Web UI settings surface.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:QiE2035/dsh-llm-headers
dsh-llm-verifier

Best-of-3/5 orchestration and LLM-as-a-Verifier selection for DeepSeek Harness

Agent collaboration · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Web0926/dsh-llm-verifier
dsh-llm-vision-bridge

DeepSeek vision bridge for the dsh web GUI: route image attachments to a vision model (pi-ai / llama.cpp Qwen3-VL) and continue the conversation with the text description on a text-only LLM (DeepSeek)

Agent collaboration · Vision tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Einskyle/dsh-llm-vision-bridge
dsh-macos-desktop

Retro macOS (System 7 / Mac OS 9) desktop UI for DSH web: chat, files, terminal, browser, docs and knowledge base inside one pixel desktop

Memory and knowledge · Agent collaboration · Interface extensions · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Taylor-Cat/dsh-macos-desktop

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.