Plugins
Browse, filter, and install DeepSeek-Harness plugins.
231 plugins found
dsh-litnotes
nirvana-apoc/dsh-litnotes
Local-first AI literature desk for DSH: import and parse PDFs (MinerU APIs or on-device pdf.js), read original/bilingual text with in-margin annotations, ask grounded questions whose citations jump to the page, and build per-paper or library knowledge graphs; eight agent tools expose the same library.
dsh-video-watch
dungcsnd1133/dsh-video-watch
Downloads a video link, samples frames from it, and transcribes the speech with Groq Whisper so an agent can answer questions about what the video shows; long audio is split into 15-minute windows to stay under the upload limit, and frames still come back without a key, which only the transcript needs. Needs ffmpeg, ffprobe and yt-dlp on PATH.
dsh-whale-memory (dsh-school)
xiaocanglan-hub/dsh-whale-memory
She keeps the questions your chats left unanswered, then goes and looks them up later. A line she asked you that ended in "?" and never got an answer is stored as a hanging question; on a schedule inside a daily window (08:00–23:00, five a day by default; an optional mouse/keyboard-idle gate is off by default) she picks the oldest one, searches the web and Bilibili, reads what is actually readable, distils it into two or three sentences and leaves a note on her desk. Questions about its own plugins are skipped and left for you. Read-only on her events: nothing is written to her memory, her growth is untouched, and dsh-fish needs no patching. Requires the @ssamurias/dsh-fish persona plugin for her event stream and a local Ollama model; a search API key is optional.
dsh-whale-memory (dsh-memory-brain)
xiaocanglan-hub/dsh-whale-memory
Object memory for DSH: each object is broken into fourteen kinds of smallest elements (shape, material, state, part, function...), observed links are stored apart from inferred ones, and analogies stay as questions until the user answers.
dsh-native-notifications
tommy00748-tech/dsh-native-notifications
Raise native desktop notifications from DSH itself for approvals, questions, finished turns, errors and sign-in prompts, attributed to the DeepSeek Harness app with click-to-open; the chime is synthesised in-page and can be picked from presets or authored as a note sequence in Settings.
dsh-clarify-mode
xiaofeng-bm/dsh-clarify-mode
Adds a clarify mode: the agent loses its file-writing tools and can only ask questions until the required dimensions are covered, then writes a spec with acceptance criteria before implementing.
dsh-xhs-style
refreshing-czq/dsh-xhs-style
Adds a requirements-discovery gate before product selection, version choices and competitive analysis: 2–3 clarification rounds with 2–4 decision-changing questions, validation of real pain points and hard constraints, comparison of original, alternative and minimum-cost routes, and a confirmation card before research and copywriting. Confirmed reports keep the Xiaohongshu-style structure, concrete steps, audited images and source links. Ordinary lookups and explicit user skips bypass the questionnaire. Host-only static prompt sections with no config, client UI or dependencies.
thought-constellation
zhougaoang/thought-constellation
Turns scattered thinking notes into a growing constellation of themes, claims, relations and open questions, plus a written synthesis of the argument.
dsh-longevity-coach
sambazhu/dsh-longevity-coach
Daily longevity coach built on the 64 graded population studies in HowToLiveLonger: a sidebar page with three actions for today, a day timeline, nine situation guides, keyword search over all 64 records and a check-in trail, plus five agent tools that make the model state the A/B/C/D evidence grade before answering questions about sleep, diet, exercise, sitting or supplements.
cyber-self
mrlsss/cyber-self
Per-workspace personal knowledge base for DeepSeek Harness: each identity gets an isolated local library — import PDF, Word, Excel, Markdown, text, HTML and images, auto-chunk and embed into SQLite with FTS5 + vector hybrid retrieval, then ask questions in chat with numbered citations back to the source. Local-first, no cloud upload; vector embeddings need a local Ollama (default bge-m3), and without it retrieval degrades to FTS5 keyword search.
dsh-plugins (dsh-focus-notify)
sqzw-x/dsh-plugins
Focus-aware notifications for DeepSeek Harness: approvals, questions, plan reviews and finished replies appear as one alert only when the conversation window loses focus; background conversations alert at any time and subagent sessions never do.
dsh-task-decision
long-yin-zi/dsh-task-decision
Collects the open questions of each AI turn into a right-side panel; you answer them, add notes, and send the decisions back to the conversation in one message.
dsh-btw-marginalia
ltp414/dsh-btw-marginalia
Read-only /btw side questions for DeepSeek Harness: forks the current session, injects the running turn's task, recent tool calls and partial answer so a mid-turn question has context, denies every tool call at execution time, and keeps a per-session topic history with follow-up, stop, retry and delete.
dsh-marginalia
ltp414/dsh-marginalia
Read-only /btw side questions for DeepSeek Harness: fork the current session, ask in the margin, keep the main transcript untouched. DeepSeek Harness 的 /btw 只读旁问:fork 当前会话、答案留在页边,不污染主对话。Host + Web Client 插件。
dsh-agentic-pet
beyondgjc/dsh-agentic-pet
A model-driven desktop pet for dsh, derived from PC2005-cloud/dsh-pet (MIT): a transparent always-on-top companion that follows your agent sessions, races the Web UI to answer approvals and questions, and runs an autonomous inner voice — world-clock and self-scheduled wakes, dreams, and bond-anniversary milestones, speaking through pet_say/pet_do, with lines read aloud through BreezeBlue TTS using your own API key. Memory is a per-pet continuity journal — an append-only hash chain, rotation into an archive, self-written stage summaries, and keyword recall with tag clues — alongside letters, a shared living-room board, pet-to-pet messages, an affection ledger, and an interactions audit that records how every approval and question actually ended. Memory and ledgers live in ~/.dsh/whale598/<petId>/; the settings page adds per-pet switches and a tool-call audit dashboard (all-time / last 30 days). It uses its own /whale598 route and data directory, so it is a separate pet from dsh-pet rather than a replacement for it. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-clarify-first
skadery/dsh-clarify-first
Asks the few key questions that decide the approach before work starts — one shot, about 200 tokens per session, no tool registration and no extra model call.
dsh-tarot
auwc/dsh-tarot
Choose three cards from a shuffled 78-card tarot deck, reveal source-linked meanings, and refine the reading through follow-up questions.
dsh-study-ask
p1gg0dg0d/dsh-study-ask
Opens a dedicated question chat in the right sidebar for text selected in a DSH conversation, so follow-up questions do not push the main conversation away and never appear in the session list.
dsh-float
18840024879/dsh-float
Windows desktop floating assistant for DeepSeek Harness: an always-on-top chat panel with streaming answers, model switching, and region-screenshot questions.
dsh-command-btw
wszw142857-beep/dsh-command-btw
DSH /btw side questions: streaming selectable panel, debounced persistence, schemastery Config for route and limits.
dsh-question-tree
yearncy/dsh-question-tree
Tree-style questioning for DSH. Hover the "Question tree" tab above and a small card pops up with the whole tree — identical to the sidebar, but it frees that column and is quicker to consult (click "List / Graph" in the card to switch views). Select text in a conversation, click "Ask in tree", and a node appears in a tree you can reach three ways — hover the "Question tree" tab for a floating card that leaves the conversation in place, open the same tree as a full conversation view, or pin it in the right sidebar. Each node holds the quoted passage plus your own questions; clicking another node makes it the current parent so later selections nest under it (Alt+click opens a root node, Ctrl+click appends another passage to the same node). Double-click jumps back to the quoted text and pages older history in automatically when the passage is not loaded yet. Hover a truncated node to read the full quote, switch between a list and a horizontal branch graph (the graph scrolls sideways with the wheel as depth grows), mark nodes understood with a red/green dot — or let "mark understood once answered" do it when the reply lands. Nodes live in localStorage; nothing is injected into the prompt.
dsh-book-library
shenj13/dsh-book-library
Read books in the DSH sidebar - import EPUB/TXT/Markdown, get a five-part close reading for every chapter (paragraph summary, best sentences, what the author is doing, the AI's own opinion, what is missing), listen with TTS, ask questions while listening, and export the whole book to one HTML page. Export collects the chapters that already have a close reading rather than unread chapters.
dsh-mobile
kinocode-jp/dsh-mobile
DeepSeek Harness host plugin for the DSH Mobile Android app: pair with a QR, use DSH on the phone through its own HTTPS gateway, answer approvals and questions from notifications, push turn completion.
dsh-plugin-agent-bridge
zshqzcn/dsh-plugin-agent-bridge
Two-way agent bridge between two DeepSeek Harness hosts: either side can ask the other agent questions and run bounded dialogues over a PSK-authenticated TCP link, with a chat page on both sides and read-only tool posture by default. Both ends need the same shared key and a nodeId configured.