Discover The Best DSH plugins

Agent collaboration · DeepSeek Harness plugins — Page 283

7551results

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

dsh-remote-sandbox

One-line DeepSeek Harness bundle that moves the execution world into a crash-resilient, heartbeat-kept, workspace-synced E2B sandbox.

Agent collaboration · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:weijiafu14/dsh-remote-sandbox#23bb0cf3787371c2430980c76a67998ae460f371&path:packages/bundle
dsh-remote-sessions

Standalone backend proxy for resident SSH agent sessions through unchanged native DSH UI; no dsh-remote dependency or core edits.

Agent collaboration · Interface extensions · Developer tools · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:atlas5301/dsh-remote-sessions
dsh-remote-sidecar

In-sandbox executor for the dsh remote-sandbox suite: a single pure-JS bundle that serves fs and process primitives over the sidecar WebSocket protocol.

Agent collaboration · Integrations · Productivity
dsh-remote-ssh-ui

Remote SSH workspaces — browser surface (workspace chooser, sidebar launcher, Settings card) and the `sshWorkspace` Remote namespace

Agent collaboration · Interface extensions · Developer tools · Integrations · Productivity
dsh-remote-ssh-worktree

Remote execution worlds for DeepSeek Harness: create a git worktree on a remote machine over a self-hosted node daemon, and run the stock read / write / edit / bash / grep tools inside it.

Agent collaboration · Developer tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lengmoXXL/dsh-remote-ssh-worktree
dsh-remote-workspace

Remote execution worlds for DeepSeek Harness: create a git worktree on a remote machine over a self-hosted node daemon, and run the stock read / write / edit / bash / grep tools inside it.

Agent collaboration · Developer tools · Integrations · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lengmoXXL/dsh-remote-workspace
dsh-remote-x

DeepSeek Harness 移动端适配插件(dsh-remote-x):向网页端注入移动端覆盖层,手机复用网页端全部功能,另附局域网反向代理 CLI

Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Mlte0907/dsh-remote-x
dsh-rename

DeepSeek Harness slash command: rename the current session with /rename, or let the model read the conversation and pick the name for you

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lmst2/dsh-rename
dsh-rename-title-after-first-turn

DSH host-only plugin: name a main session once, right after its first turn ends. Subagent and teammate sessions are left alone.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:apherchin/dsh-rename-title-after-first-turn
dsh-repeat-tool-breaker

Hard break on repeated identical tool calls: a synchronous ctx.tools.guard monotonic gate that denies the 2nd identical (tool name + canonical arguments) call per agent, with an optional same-path read guard and advisory first-repeat warning.

Agent collaboration
dsh-repetition-guard

DeepSeek Harness (DSH) 模型输出复读熔断插件:P1 通用流式复读检测(llm/stream 在线拦截)+ P2 Vision Toolkit 局部防护,命中即终止流并给出结构化错误码,避免模型复读浪费大量 output tokens。

Agent collaboration · Vision tools
dsh-replay-studio

DSH plugin: visual session replay — browse, compare, and debug agent sessions in a local web UI.

Agent collaboration · Interface extensions · Developer tools · Productivity
dsh-report-ledger

Report-and-ledger plugin for DSH: front-matter 汇报 as the first-class agent-to-agent interaction primitive, with upward/downward delivery, co-authorship, CC, and a complete transfer-path audit trail; plus a conversation timeline tab.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:stone-brick/dsh-report-ledger
dsh-request-manager

请求管理插件(bundle):按全局配置管理 Agent→LLM 请求——「请求额外间隔」(每个请求发送前固定多等 N 毫秒,0=不介入)、重试次数覆盖(留空=沿用 provider 默认)、拦截「请求失败」(终态失败后挂起等待人工决议:重试原地重发同一请求 / 放弃按原生路径终结)。入口为会话头部 utilities 槽位的「请求管理」按钮;设置跨会话全局生效,按值决定是否介入;界面跟随 dsh 语言中英切换。

Agent collaboration · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tree-func/dsh-request-manager
dsh-research-agent

通用调研智能体(DeepSeek Harness 插件 / Agent Preset):7 个调研工具 + 调研工作法提示词,零内置数据

Agent collaboration
dsh-research-first

Research-first assistant for DeepSeek Harness: gently nudge the agent to investigate docs / code / community before edits, detect blocked research, and record every hint in the session log.

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:outnever/dsh-research-first
dsh-researchcraft

ResearchCraft as a DeepSeek Harness profile: DSH web UI and agent, scientific skills, lab notebook, specialist subagents.

Skills · Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:raktim-mondol/dsh-researchcraft
dsh-reset-handoff

Standard handoff protocol so DSH never restarts itself: a host plugin that files a JSON reset request for an external ops agent (e.g. Hermes) to execute preflight-snapshot → restart → health-check → recover, then delivers the result back to the requesting session.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:nicecx/dsh-reset-handoff
dsh-restart

DSH 应用内整体重启插件:agent 自主 / 人工触发,忙碌会话协调,失败自动回滚,重启后自动恢复会话并继续任务

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Towzai/dsh-restart
dsh-restart-progress

In-page restart overlay + detached restart script for DeepSeek Harness (DSH) Web: shows a full-screen spinner overlay in the current page the moment a restart starts, auto-reloads when the server is back, and notifies the originating session so the agent reports 'restarted' by itself. Esc / close button to bail out.

Agent collaboration · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SMWHff/dsh-restart-progress
dsh-restart-task

DSH web plugin: a three-tier recovery policy for broken turns — silent in-turn retry, in-turn keep-alive for truncated output, and an opt-in continuation turn — with a round control in the composer, the shipped send button taking over as "continue", and a settings card.

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zchuxi/dsh-restart-task
dsh-result-cap

DeepSeek Harness plugin: a deterministic UTF-8 byte cap on tool results, keeping the first N bytes and carrying a sha256 of the full original so a truncated result is never mistaken for a whole one

Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jwilson411/dsh-result-cap
dsh-resume

Continue Codex, Claude Code, Cursor, Grok, and Pi work in DeepSeek Harness.

Agent collaboration · Developer tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:aa2246740/dsh-resume
dsh-resume-on-restart

DSH 插件:检测 DSH 服务重启后自动唤醒主 agent,投递提示消息让中断的工作自动恢复。仅依赖 cordis ctx 服务,兼容 DSH Desktop 打包环境。

Agent collaboration · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:nickkkkkk123123/dsh-resume-on-restart

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.