Plugins
Browse, filter, and install DeepSeek-Harness plugins.
1906 plugins found
dsh-quick-send
1250589385/dsh-quick-send
Shortcut buttons in the composer row that send preset text into the current conversation in one click. Button label, size, opacity, shape and payload are editable in place, and the whole group moves left or right of the context meter by right-click dragging, persisted in localStorage. The group takes only the width it needs, so the context meter and the usage area stay clickable.
dsh-ssh-view
k0me1j1fan/dsh-ssh-view
SSH server view plugin for DeepSeek Harness: browse and edit files, inspect processes, and tail logs on a headless Linux server over SSH.
dsh-debate-simulator
jcy0chenyuan0/dsh-debate-simulator
Multi-agent Chinese debate simulator with eight debaters, live two-column discussion and draft notes, judges and scoreboard, single-side clocks, per-round ZIP archives, a training side with a configurable end condition (win-rate threshold or fixed rounds), and a Word prep package.
dsh-rice-on-a-stick
leawind/dsh-rice-on-a-stick
Rice on a Stick: Expose control over DeepSeek Harness (dsh) through MCP (Streamable HTTP) and dsh's native tools, with a configurable list of allowed models. Long-tail host endpoints can be invoked via a generic, audited bridge. By default, it listens only on 127.0.0.1, with an optional access token.
dsh-danger-guard
jayyuen666/dsh-danger-guard
Pre-execution guard on `ctx.tools.guard`: dangerous `bash` and `pwsh` commands and `terminal_send` input are allowed, asked about or refused according to the current permission preset (git hook bypass, catastrophic `rm`, download-and-run, long-running dev servers, git and infrastructure destruction), while edits to credential paths and edits of files the turn never read are refused before dispatch with the missing evidence attached; every refusal returns a model-facing reason, naming the offending flags or targets where the rule can.
dsh-thinking-zh
minutiae3/dsh-thinking-zh
Registers system-prompt sections that make the model reason in Simplified or Traditional Chinese, with strict/prefer modes and an optional reply-language policy. Adds a /thinking-zh command for per-session switching. Zero runtime dependencies.
dsh-modes
xiaohai-78/dsh-modes
Settings page for agent modes (presets): switch up to 15 capabilities per mode (commands, files or read-only files, web, subagents, and more) or individual plugin rows; edit each mode's system prompt with variable checks, a full preview, version history, optional live updates for running sessions, and an approval-gated mode_prompt chat tool; create modes from four starter templates or copies; merge built-in updates after a dsh upgrade while keeping your changes, and turn off rows that fail to load.
dsh-complex-project-preset
sueqet/dsh-complex-project-preset
Agent preset for DeepSeek Harness: the standard tool stack plus four working rules written into the persona prompt — a project keeps at most four documents (intro, decisions, change log, current state and next steps), those documents describe only the current state with no AI edit history or superseded decisions, no git commit or push or pull request until the user explicitly asks, and a careful-coding workflow (restate the goal and done-criteria first, surgical diffs, evidence before claiming success) with plain-language reports.
DSH-SkillsHub
wlx2007/dsh-skillshub
Skill center panel for the DSH web GUI - search online skill registries (SkillHub, skills.sh, GitHub), install skills to user or project roots, and manage local skills with enable, create, edit, delete and preview.
dsh-kill-ai-slop
yiyunet/dsh-kill-ai-slop
Kill AI Slop for DSH — score a received document on three weighted axes (expression, execution, decision), audit work-slop with a delivery-obligation ledger, and machine-verify every quote against the source. Reads docx, pptx, xlsx, pdf, txt, md, csv, json and html. Zero runtime dependencies, zero network, fully local.
dsh-docchain
wct-lab/dsh-docchain
DocChain knowledge base, document conversion and knowledge-graph toolkit — filename, content and metadata search, locate-by-doc_id/name with content reading, topic listing, bulk document upload, document-to-Markdown conversion, image-similarity search, per-document image descriptions saved to a sidecar markdown (flowcharts and architecture diagrams are turned into PlantUML sketches, other images into text descriptions; the original image is replaced by a clickable link), a deep-research workflow, and a knowledge-graph layer (ontology inspection, read-only Cypher, ontology/entity/relation writes). Every script-backed capability also ships as a native DSH tool executed in-process: doc search, content search, filename search, topic info, metadata search, upload, image search, image describe, doc2markdown, plus kg schema / kg cypher / kg upsert node / kg upsert relation / kg delete node / kg delete relation. All graph operations go through the DocChain API, so no Neo4j password is needed. The configuration page keeps several docchain environments (each with its own address and credential), switches between them in one click, and pre-selects topics per environment. Needs a docchain service URL and API key (except doc2markdown); image descriptions additionally need an OpenAI-compatible multimodal endpoint (defaults to an internal gateway model, configurable).
dsh-doc-review
caihua8669/dsh-doc-review
Document review workbench: select text in a Markdown file, leave comments saved as MRSF sidecar files next to it, and let the agent read them with doc_review_* tools and propose edits you accept or reject.
dsh-image2-plugin
544244857/dsh-image2-plugin
Registers an `image2_generate` tool that calls your own OpenAI-compatible image relay to generate or edit pictures (text-to-image via POST /images/generations, image-to-image via POST /images/edits with a local PNG/JPEG/WebP reference, accepting b64_json or image URLs), saves them in the session working directory, and renders them inline in the conversation through its `@wisdoverse/dsh-inline-media-viewer` dependency.
dsh-deai-audit
zz12hui/dsh-deai-audit
Audits Chinese copy for AI-sounding phrasing: a 0-100 score over six dimensions, sentence-level flags with rewrite hints, and per-genre weights adjustable in conversation.
dsh-mcp-link
zdkcomeon/dsh-mcp-link
Scans MCP configurations from 13 local AI clients and from project workspaces, imports selected servers into the active DSH profile, and adds connection testing, in-place reconnect, JSON import and visual add, edit and removal controls.
dsh-mcp-manager
wangbobo-coder/dsh-mcp-manager
One settings page for every MCP server on your machine. It reads the real config file of 17 other AI tools (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, OpenCode, Trae, Trae CN, Qoder, Gemini CLI, Qwen, Zed, Roo Code, Copilot CLI, Kiro, CodeBuddy, Continue) plus DeepSeek Harness itself, groups servers by the file that declares them, probes each one over JSON-RPC to see whether it starts and which tools it exposes, and gives every server a switch that mounts or unmounts it in DeepSeek Harness without editing the other tools' own files.
dsh-android-phone
lovepeace-art/dsh-android-phone
Mirrors a USB-connected Android phone in the DSH sidebar and drives it over scrcpy's control protocol: 12 agent tools for tap/swipe/type/keys, multi-frame scroll-and-stitch long screenshots, and agent-first control that hands over the moment a human touches the phone. Ships its own adb and scrcpy-server. Windows 10/11 only; the live sidebar mirror additionally requires dsh-better-sidebar.
dsh-mcp-manager
it-glen/dsh-mcp-manager
MCP server manager for DSH: add, edit, enable and disable Model Context Protocol servers from a panel, with stdio and streamable-HTTP transports, per-server tool-call timeouts, live connection and tool-count status, and persistence to a project- or home-level mcp.json. Maintained fork of @wingsky-1/dsh-mcp-manager.
dsh-prompt-enhance
istarrydust/dsh-prompt-enhance
Prompt enhancement: click the star button in the composer to have the current model rewrite the draft more clearly, with one click back to the original; the template is editable.
dsh-knowledge-base
135642-163/dsh-knowledge-base
Local-first knowledge base for DeepSeek Harness: imports Word/PPT/Excel/PDF (text or scanned), EPUB and MOBI/AZW3, builds Markdown parts with page anchors, OCR quality/confidence and column-aware PDF reading order; adds an LLM-maintained wiki layer (schema.md rules, auto index.md, append-only log.md, typed notes with sources and backlinks), adds source-trust labels (high/medium/low) with trust-aware ranking and low-trust warnings, and supports ranked search, cross-KB query, precise reading/editing, and md/jsonl/zip export. MOBI/AZW3 need Calibre; legacy .doc/.ppt need Word/PowerPoint (Windows) or LibreOffice (Linux); scanned-PDF OCR downloads models on first use.
dsh-prompt-assembler
player-minepig/dsh-prompt-assembler
Standalone prompt assembly with a source registry, custom text, strategy editing and previews, and per-session strategy snapshots through DSH public hooks.
dsh-role-prompts
justin-mai/dsh-role-prompts
Adds job-role prompts to the DSH composer: type - at the start of the input to pick a role, which becomes a reference chip in the draft and is then injected as a system prompt section on every turn of that conversation, so the instruction keeps applying without showing up in the transcript. Roles are added and edited on a Settings page and stored in ~/.dsh/dsh-role-prompts.md.
dsh-session-rescue
jayyuen666/dsh-session-rescue
Automatic recovery when a turn ends badly: resume after a transient failure, continue after `max-tokens` truncation, and re-run a completed turn whose own todo list is still open; a request-level rate-limit retry defers to the official policy, and manual actions add edit-resend, fork-resend, send-continue, retry, resume-interrupted and stop-and-re-ask, with an optional same-turn steer continuation while the todo list is unfinished.
dsh-conversation-recycle-bin
hero476/dsh-conversation-recycle-bin
Delete a DSH conversation from its sidebar menu or the conversation header, optionally cascading into that conversation's associated memory nodes when you tick the box (the confirmation dialog shows the hit count before you commit); deletes land in a plugin recycle bin with restore, every action is appended to an audit log, and batch deletes are rate-limited with per-conversation rollback.