Plugins
Browse, filter, and install DeepSeek-Harness plugins.
1447 plugins found
dsh-plugins (dsh-workbuddy-turn-credits)
yggizz/dsh-plugins
Shows what each completed turn actually cost, on that reply's action row: WorkBuddy sessions show credits, sessions on the official DeepSeek routes (account login or API key) show an amount in CNY. It measures instead of estimating — the matching balance is read at the start and again at the end of every turn, and the difference is that turn's charge — so each turn costs two read-only balance queries (no credits spent) plus about a second of settle time before the number appears. A switched account, overlapping requests, or an unsettled balance shows an em dash rather than a guessed figure, and a session that uses none of these routes shows no row at all. It reads the DeepSeek balance endpoint and the WorkBuddy credits route; the Host side answers only loopback requests. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-plugins (sidebar-pins)
yggizz/dsh-plugins
Remembers which left-sidebar panel launchers you unpinned and re-applies that choice on every start, so the entries you folded away stay folded instead of coming back as a full row of buttons. It adds no interface of its own: it only restores the sidebar's own display state, writes nothing outside the profile, and does not reach the network. Disabling it returns the sidebar to stock behaviour without deleting the saved choice. This is the unpin list only — for panel reordering, grouping, search or drag-and-drop, a fuller sidebar manager is a different plugin.
dsh-sidebar-narrator
gcwarmman/dsh-sidebar-narrator
A right-sidebar narrator for DeepSeek Harness that says what the agent finished, is doing, and will do next, plus a read-only explain channel, a non-interrupting steer, and a stop that reports what it kept. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-tts
leiboss/dsh-tts
Long-form voiceover pipeline for DeepSeek Harness: chapter planning, spoken-script adaptation, subtitles, manifest, and resumable jobs. Turns a document into a publishable audio set.
dsh-decision-engine
leonhardthust/dsh-decision-engine
dsh-decision-engine: a cheap judgement layer for DeepSeek Harness — a small decision model answers structured questions before the main model acts, so calls can be allowed, escalated, rerouted to a cheaper model, or skipped. All eight decision points (too
DSH_PlainRiceWhale (whale-aside)
zjdqtjs/dsh_plainricewhale
Whale-girl persona for DeepSeek Harness: a `whale_aside` tool turns one short inner monologue per new task into a chat bubble, with an optional mood sticker and Edge TTS voice line.
undohaven (log-gate)
antipas/undohaven
Registers an exclusion with the built-in session-log plugin so chosen sessions skip session-log upload, either every live session or those whose cwd matches a project name, directory or glob; includes a local status endpoint and an audit command. Does not patch dsh or hook the network. Unofficial.
dsh-py-runner
amzingluo/dsh-py-runner
VSCode-style Python console in the DSH sidebar: it opens .py files in an editor with line numbers and Python syntax highlighting, lets you pick the interpreter, and runs the file with Run / Debug / Stop while stdout, stderr and the exit code stream into a panel below. Debugging drives a real DAP session through debugpy: click the gutter to set breakpoints, then step, pause, inspect the call stack, expand variables and evaluate watch expressions; a missing debugpy can be installed from the panel in one click. Ctrl+Enter runs, Ctrl+Shift+Enter starts debugging. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
workfiles-assistant
songshun1021/workfiles-assistant
Voice-first macOS work-documents assistant for DeepSeek Harness. It keeps a local 7-day ledger of the apps you choose, searches documents only inside folders you approve, and opens the file or page you saw recently from what you say. Window titles and HTTPS addresses are separate per-app opt-ins; it does not take screenshots, run OCR, or read the clipboard or the browser-history database.
phone-use-dsh (dsh)
mig-everything/phone-use-dsh
Agent tools for connected HarmonyOS, Android and iPhone devices, with native controls, on-demand screenshots and OCR, and a multi-device sidebar.
feiyu-memgate (dsh-feiyu-memgate)
n0rmal-114/feiyu-memgate
Long-term memory through the bundled feiyu-memgate gateway, which the plugin starts on 127.0.0.1 (needs Python 3.11 or newer, nothing to pip install): recalls related memories at the start of each user turn and appends them after the user message as a marked data block, gives the model memgate_remember and memgate_search tools, and adds a /memgate command and a settings page where each feature can be switched off. By default memories are written only when the model calls the remember tool. Keyword retrieval over SQLite by default, with no model and no download; an OpenAI-compatible embeddings endpoint or the optional dsh-feiyu-memgate-embed add-on (local CPU embedding models, downloaded on request) adds semantic retrieval. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-connect-loomy
diudiu62/dsh-connect-loomy
Registers the Loomy desktop app's locally signed-in chat models as a `loomy` provider in DSH. Several accounts can be signed in at once and switched from a drawer on the composer badge, with each account's points shown per row, optional per-call rotation between healthy accounts, a settings section with per-model toggles and an upstream diagnostics table, and a status/doctor CLI. Shares the `loomy` provider id with 2239058652/dsh-loomy-connect, so the two cannot be installed together; this one differs by the account drawer, the per-account points breakdown and the CLI.
open-harness-plugin-openai-compatible-auto
eliotstocker/open-harness-plugin-openai-compatible-auto
Multi-host plugin (OpenCode V2, Pi, DeepSeek Harness) for OpenAI-compatible endpoints with /models auto-detection and LiteLLM browser CLI code flow sign-in
dsh-telegram-bot
soffits/dsh-telegram-bot
Telegram client for DSH sessions, one forum topic per session shared with the Web UI: streamed answers, turns from other clients mirrored in, tool approvals and ask_user_question as buttons, model and permission controls, photos, files and transcribed voice messages, and a send-to-topic API for scripts and other plugins. Maintained fork of Boobaw/dsh-telegram-bot.
dsh-poxiao-qqbot
poxiao-12138/dsh-poxiao-qqbot
Connects the official QQ bot to DeepSeek Harness and adds BreezeBlue voice replies, Obsidian memory, and role-card updates based on chat feedback. Private chats are allow-list only (empty = nobody), but group chats and slash commands such as /preset and /model are open to everyone by default; its HTTP routes have no DSH access check.
dsh-email
laynepeng/dsh-email
Mail in three tools: send over SMTP (465 or 587) or Microsoft Graph, read the inbox read-only (list, keyword search with date ranges, folders, read one message), and account status with Hotmail/Outlook device-code OAuth2. A failing Graph call falls back to SMTP automatically, a dead SMTP entry point moves to a second host, and a draft can be previewed in the chat before sending. Zero runtime dependencies; attachments are limited to the workspace. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-plugin-voice-alert
venompool888/dsh-plugin-voice-alert
Spoken alerts on macOS that name the source and project: announces approval requests automatically and adds a voice-alert skill the agent uses for verification codes, finished long tasks or when it is stuck. DeepSeek TTS via an API key (DeepSeek official, a third-party base URL, or the key already set in DSH Models), tested before saving and falling back to the macOS system voice; speaks only after 30 seconds without keyboard or mouse input and repeats until you return, with AI-written lines in a chosen tone (professional, tsundere, cute, clingy, cold or custom); a Settings → Voice page with instant previews, speech speed, 10 spoken languages and an away mode.
dsh-ai-voice-cover
vamyane/dsh-ai-voice-cover
AI voice cover for DeepSeek Harness: give any song plus about 10 seconds of reference audio and get a cover sung in that voice — dry vocal and mixed final, with the melody aligned to the original because only timbre is swapped. Supports zero-shot covers and archived voice libraries, automatic semi-tone shift synced with the accompaniment, an isolated Python venv, and runs on GPU or CPU.
dsh-hear
flyingcharon/dsh-hear
Gives a text-only agent an ear: a local audio model says what was said and how it sounded, checked against measured pitch, energy and pauses, with optional QQ voice watching. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-dafeiyu-voice-chat
dennisyang1986/dsh-dafeiyu-voice-chat
Voice chat inside DeepSeek Harness: a draggable fish launcher records from the microphone, transcribes with DeepSeek speech recognition, answers with deepseek-flash (images included), and speaks each sentence through DeepSeek speech synthesis as the answer streams. Two voices, a continuous-conversation switch, and the API key stays on the Host.
dsh-voice-input-wb-asr
baibiaowang/dsh-voice-input-wb-asr
Free speech-to-text for DeepSeek Harness. Hold the composer microphone (or Alt while the caret is in the composer) and the text is typed into the input box as you speak: the audio is cut at pauses, each phrase is recognized as it lands, and releasing the button recognizes the whole take once more and replaces the preview with the corrected transcript. Also ships wb_transcribe, which turns long audio or video into one timestamped Markdown document (an 82-minute recording in 47 seconds in a measured run). Recognition uses the WorkBuddy accounts already signed in; WorkBuddy does not bill speech input. International and domestic builds are separate settings, international by default.
dsh-voice-deepseek
asya903/dsh-voice-deepseek
Reads assistant replies aloud with DeepSeek official TTS: one speaker button in every reply action bar, stella (female) by default, tide (male) optional. Audio is cached per identical text, so replaying the same sentence costs nothing. Requires a DeepSeek API key - about CNY 1.5 per 10k characters at the current 50% discount.
dsh-jimeng
mokoking666/dsh-jimeng
Registers `jimeng_image` and `jimeng_video` tools that generate through the locally signed-in Jimeng desktop app, reading its session cookies and the account's live model catalog from two web endpoints, so new models work without a plugin update; `jimeng_models` and `jimeng_status` list models and credits for free, and `dryRun`, `minCreditsToKeep` and `allowSpend` bound credit spending.
dsh-imagegen-panel
gpta76/dsh-imagegen-panel
Image-generation sidebar panel for DeepSeek Harness: works with any OpenAI-compatible image endpoint, supports reference-image edits, and ships presets for character sheets, turnarounds and expressions.