Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

2504 plugins found

M

dsh-nuphus-mcp

mrpulor-gh/dsh-nuphus-mcp

Official DSH plugin for nuphus-mcp (by the nuphus-mcp maintainers): desktop and browser automation (38 tools) with PaddleOCR element perception and Chrome CDP browsing, via a persistent stdio MCP child process.

514 days agoTools & CapabilitiesMIT
B

dsh-ocr-local

balcoz/dsh-ocr-local

Local OCR for DeepSeek Harness: paste/attach an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline. TUI (cc-tui) and Web. / DeepSeek Harness 本地 OCR 插件:图片转文字,PP-OCRv5 + ONNX Runtime,完全离线,支持 TUI 与 Web。

53 months agoVision, Voice & Multimodal
S

dsh-vision-bridge

sfyyy/dsh-vision-bridge

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

53 months agoVision, Voice & MultimodalMIT
L

dsh-plugin-wiki-tools

lion-1209/dsh-plugin-wiki-tools

Native tools for an Obsidian wiki vault: wiki_query, wiki_write, wiki_rename, wiki_scaffold, wiki_archive, and wiki_lint cover BM25 search with link-graph context, bookkeeping writes with sha256 source tracking, vault-wide renames, mode scaffolds, source archiving, and health checks — with cross-process locks and optional git auto-commit.

52 months agoTools & CapabilitiesMIT
D

dsh-image-pathify

dami9527/dsh-image-pathify

Lets text-only models handle pasted chat images, with a native vision experience, batch image viewing, and a built-in OpenAI-compatible analyze_image tool; vision-capable models are unaffected.

512 days agoVision, Voice & MultimodalMIT
0

dsh-voice-input

0nt-one/dsh-voice-input

Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.

53 months agoVision, Voice & MultimodalMIT
W

visual-review

wang-bool/visual-review

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

53 months agoVision, Voice & MultimodalMIT
X

dsh-writing-remote

x2802490130-prog/dsh-writing-remote

Host-side Typert remote for dsh-tool-writing: serves project volumes, chapter status, corpus library, full-text search, evolution entries, and thread-graph data to the client writing panel.

53 months agoTools & CapabilitiesMIT
X

dsh-client-ui-writing

x2802490130-prog/dsh-client-ui-writing

Client-side writing panel for the Web UI: project volumes and stats, corpus library, full-text search, evolution version-chain diffs, and an SVG thread graph, shown only in writing-preset sessions.

53 months agoUI EnhancementsMIT
C

prompt-for-me

chuantianml/prompt-for-me

Context-aware next-message suggestions in the DSH composer, with repeated Trigger cycling and explicit user review before sending.

5last monthUI EnhancementsMIT
S

deepseek-harness-qqbot

sliverp/deepseek-harness-qqbot

QQ Bot text and image channel plugin for DeepSeek Harness

53 months agoIntegrations & RemoteMIT
C

dsh-telegram-relay

congchuanling-dot/dsh-telegram-relay

DSH Relay 让你可以通过 Telegram 远程与 DeepSeek Harness 对话,并接收通知。DSH Relay turns Telegram into a remote conversation and notification channel for DeepSeek Harness.

53 months agoIntegrations & RemoteApache-2.0
L

dsh-specflow

lonelymoon87/dsh-specflow

Adds specification artifacts, skills, commands, goal-backed implementation, and task-progress context.

53 months agoWorkflow & AutomationMIT
Q

dsh-rugu (dsh)

qiuyedx/dsh-rugu

Persona memory for DeepSeek Harness: one memory shared by every entry point (DSH desktop, and QQ through the dsh-qq bridge) that records what the agent itself experienced. Raw messages are kept, five recall routes (vector, keyword, people and events, time, who is present) run before each reply, and a per-context check decides whether a remembered thing may be said. Adds memory_recall, memory_note, memory_fix and memory_look tools and a Settings page; embeddings are optional (local Ollama or an OpenAI-compatible endpoint).

47 days agoMemoryMIT
F

dsh-minimax-image

ffpinkle/dsh-minimax-image

MiniMax H3-Image text-to-image generation and image-to-image editing inside DSH, using your own MINIMAX_API_KEY.

47 days agoVision, Voice & MultimodalMIT
A

dsh-rea-pro

acuteszw/dsh-rea-pro

Mounts REA's reverse-engineering MCP toolset in DeepSeek Harness behind a composer chip; it starts off after install, and switching it on registers the server while switching it off withdraws the tools and stops the MCP child process so idle sessions pay no context for them.

46 days agoTools & CapabilitiesMIT
T

dsh-chat-search

timefarer/dsh-chat-search

Global and in-session search for DeepSeek Harness: search chat history across all sessions or just the current one, and retrieve both paragraph text and file names — find it even when you only remember the file name. Filter by date range and each session recent turns; results expand as session → question → paragraph, and a jump lands on the match with the words highlighted. Defaults to the last 14 days and the latest 30 turns per session; leave either empty to search everything.

42 days agoSessions & MessagesMIT
C

dsh-snapcompact

cyberbolt/dsh-snapcompact

A DSH context-compaction plugin: when the route supports images, it renders the middle of a session history into locally generated 1-bit bitmap frames for the vision model, while the exact head and tail, a bounded exact-token index and a FILES index stay as text.

49 days agoSessions & MessagesMIT
Q

dsh-prompt-prediction

qingj01/dsh-prompt-prediction

Unofficial DeepSeek Harness plugin for next-prompt ghost text; Tab or ArrowRight fills an editable draft without sending it.

417 days agoUI EnhancementsMIT
Z

dsh-video-studio-skill

znlgis/dsh-video-studio-skill

Registers the video-studio skill in the DSH skill catalog. It builds a Chinese-narrated video from a script: edge-tts synthesizes the narration, the timeline is derived from each line's measured audio duration rather than estimated from text length, Pillow renders every frame deterministically and pipes the raw frames to ffmpeg as rawvideo, burned-in subtitles and SRT/ASS export come from that same timeline, physical-model sound effects and a generated score are mixed sample by sample with numpy, and QA runs in four layers: container, signal, temporal and page level (the page layer only when the browser engine is used). An optional Playwright-driven browser engine renders the whole film as Canvas2D instead, sending PNG frames through image2pipe. Needs network access for the narration, ffmpeg on PATH and Python with numpy, Pillow and edge-tts; the browser engine also needs Playwright with a local Edge/Chromium.

43 days agoSkillsMIT
D

dsh-image-studio

david-zdw/dsh-image-studio

Sidebar image workbench with separate Agnes / OpenAI GPT Image / Grok / OpenAI-compatible keys, text-to-image and up to five reference images, local history, an image_studio_generate tool for /image, and an in-panel GitHub update button.

4yesterdayTools & CapabilitiesMIT
L

dsh-persona-manager

linsport/dsh-persona-manager

Manage DeepSeek Harness agent presets (personas) from a Settings page: create one on top of a shipped base preset, edit a persona in place, lay it out in a rendered preview, and export or import it as JSON or Markdown. Edits to a hand-written profile patch are applied as text, so comments, quoting and loader expressions survive. Desktop app is the tested environment; creating from a base preset needs the yaml package that ships with DSH.

43 days agoIntegrations & RemoteMIT
K

dsh-redline

klaus-2/dsh-redline

Visual review for the harness browser: pick any element to comment on it, adjust styles live with rollback, sketch on a free-form annotation canvas, and send everything as structured context attached to the next message, with a cropped screenshot per pin or the whole visible viewport composited with the drawings.

416 hours agoUI EnhancementsMIT
K

dsh-visual-safety-control

kxiaoguai3/dsh-visual-safety-control

Windows desktop-control plugin for DeepSeek Harness: screenshot, local OCR and UI Automation with a content policy (dangerous labels / sensitive windows / secrets) and action verification (hit-test, expect, verifyText). Fork of qingying012/dsh-desktop-con

423 days agoSecurity & PermissionsMIT