Discover The Best DSH plugins

DeepSeek Harness plugins — Page 311

21799results

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

dsh-context-proxy

Thin on-demand context-retrieval layer for DeepSeek Harness: context_query / context_slice / context_grep tools over the sessionQuery and subprocess seams.

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:EvilIrving/dsh-context-proxy
dsh-context-rollover

Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable model-managed notes, a small verbatim recent tail, and targeted history recovery — no summarization.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:athif23/dsh-context-rollover
dsh-context-truth

DeepSeek Harness plugin: tells the model its real, host-measured context occupancy every turn — and keeps compaction summaries from carrying false "context is nearly exhausted" claims.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:deepseekv41flash/dsh-context-truth
dsh-continue

Composer quick-action buttons for dsh: '继续' and '讲人话' to the right of the send button. Browser-half-only plugin (the host half is inert).

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:flg1217/dsh-continue
dsh-continue

Fail-closed network recovery, recommended answers, and safe unattended continuation for DeepSeek Harness.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JuwanXu/dsh-continue
dsh-continue-on-limit

Auto-continue for the DeepSeek Harness Web GUI: when a small local model hits its output-token cap and the conversation shows the max-tokens notice, the plugin automatically sends a short "continue" message so the reply keeps flowing without a manual click.

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qwert702/dsh-continue-on-limit
dsh-continue-on-limit-host

Host-side global max-tokens auto-continuation for DeepSeek Harness with Follow-up and selectable transparent Steer tool-call policies.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Soulize/dsh-continue-on-limit-host
dsh-continuum

Persistent project memory, context-safe agent handoffs, checkpointing, evidence tracking, and long-running task continuity for DeepSeek Harness

Memory and knowledge · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:QuantumKuba/dsh-continuum
dsh-contract-drafting-agent

A staged contract-drafting skill pack for DeepSeek Harness.

Skills · Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:songoao25/dsh-contract-drafting-agent
dsh-conversation-atlas

Project-level conversation memory explorer for DeepSeek Harness with related memories, cross-session bridges, BM25 search, and exact chat navigation.

Memory and knowledge · Productivity
dsh-conversation-density-map

右侧对话密度地图:消息分布/长短/当前位置 + 点击跳转(持久静态客户端插件,纯 DOM 低侵入)

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:weien666/dsh-conversation-density-map
dsh-conversation-flat

Conversation UI upgrades for DeepSeek Harness Web GUI: document-flow layout (full-width column, user message bars, sender label, full-width tables), and a personal profile — circular avatar + display name above your messages, configured from a 个人资料 section in the settings panel (persisted to the host's settings.yaml). Compatible with dsh 0.1.2-alpha.5. Colors follow the active theme; every side effect is registered through ctx.effect so disable/remove fully reverts the page.

Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Idreamxkl/dsh-conversation-flat
dsh-conversation-manager

DeepSeek Harness(DSH)对话管家:跨工作区总表、正文搜索(中文子串 / 未打开的旧对话也能搜 / 定位到命中那句并读出上下文)、按时间批量归档,以及 DSH 界面没有的磁盘层面删除(回收站式,可恢复)。

Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Sky-lll27/DSH-chat-keeper
dsh-conversation-map

Conversation map for DeepSeek Harness web: a live tree of every session in the workspace — subagent lineage, running state, and one-click navigation. · DSH 对话地图:当前工作区全部会话的实时树状图,子代理谱系、运行状态一目了然,点击即跳转。

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xyAxzy/dsh-conversation-map
dsh-conversation-nav

Codex-style conversation turn navigation for the DeepSeek Harness web GUI: a piano-key rail at the left edge of the conversation (hover ladder, preview tooltip, click-to-jump, active-turn tracking) plus user-message send time and per-turn marks with distinct rail colors, persisted per session.

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Jaeger0624/dsh-conversation-nav
dsh-conversation-nav-dots

Conversation navigation dots for DSH Web: a vertical rail of clickable markers on the right side of the conversation view. Each marker represents a user message — click to jump, hover for preview, active marker highlighted. | DSH 网页端对话导航点:对话右侧一列可点击的导航标记,每个标记对应一条用户消息。点击跳转,悬停预览,当前点高亮。

Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yuioi666/dsh-conversation-nav-dots
dsh-conversation-rewind

Same-Session append-only conversation branches and safe message editing for DeepSeek Harness

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:DTSFO/dsh-conversation-rewind
dsh-conversation-stats

DSH Web GUI 会话统计插件:在顶部「对话」「轨迹」之后新增「会话统计」tab,列出每个对话的轮数、步数、token 用量(输入/输出/缓存)、模型调用、工具调用与耗时等数据,点击会话可查看逐条调用明细。数据直接解析 ~/.dsh/sessions 下的会话日志(zstd),无需常驻监听,历史对话同样可查。

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wellcover/dsh-conversation-stats
dsh-convmap

DeepSeek Harness web 插件:在主对话区左缘中部渲染「对话地图」刻度(每条 = 一轮用户提问),hover 梯度展开并预览该轮提问/回复摘要,点击跳转(未渲染的老轮次自动分页加载后再跳),滚动时当前轮次自动高亮。

Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:GeekRicardo/dsh-convmap
dsh-copilot-plugin

A co-pilot for your DSH agent's instructions: read the system prompt as sections, write your own house rules into it, catch the rules that contradict each other, keep a logbook of every change - and roll it all back.

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Hwayn-pixel/dsh-copilot
dsh-copy-pick

字帖选择

Other extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-copy-pick
dsh-copy-session-id

Show the current session ID in the session header and copy it to the clipboard with one click

Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Hanihahaha/dsh-copy-session-id
dsh-cordis

DeepSeek Harness engine as a lifecycle-owned Cordis plugin, extracted from ACRYL.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:acryldev/dsh-cordis
dsh-cordis-mcp

DeepSeek Harness 插件:把 DSH 的动态 Cordis 工具集(inspect/define/run/stop/undefine)以 MCP 暴露给 Claude Code。端点强制身份认证,token 可在 DSH 设置页配置。

Developer tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:GeekRicardo/dsh-cordis-mcp

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.