Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

388 plugins found

K

dsh-plugin-task-coordinator

kayungko/dsh-plugin-task-coordinator

Supervisor-style workflow orchestration over top-level sessions: confirmation-gated batch dispatch, team workstreams, steering running tasks, idle-wait collection and live model-route discovery across 11 task_* tools plus a /tasks slash command.

513 days agoWorkflow & AutomationMIT
W

ncm-player

wolfgenerals/ncm-player

Floating NetEase Cloud Music player for DSH Web: draggable collapsible window with mini mode, playlist discovery with search and hot lists, synced lyrics with translations, persistent playback queue, QR-code or Cookie login, colors following the DSH skin theme.

53 months agoUI EnhancementsMIT
Q

dsh-auto-translate

qwert702/dsh-auto-translate

Full-pipeline Chinese translation for the dsh web GUI: live translation of the model reasoning as it streams, in-place Chinese below each English reply, and one-line Chinese summaries for tool outputs and tool-call glosses — a standalone provider request that never enters the session transcript.

5last monthUI Enhancements
X

dsh-quick-phrases

xianrui69/dsh-quick-phrases

Adds a draggable, position-persisted chip bar of configurable quick phrases to DeepSeek Harness, plus a /-triggered phrase menu with per-phrase pin, slash-menu, bar-visibility, and click-to-send toggles.

53 months agoUI EnhancementsMIT
Q

dotfiles

qw457812/dotfiles

Expose Pi prompt templates as DeepSeek Harness slash commands

53 months agoSkills
C

dsh-import-agents

chang-tong/dsh-import-agents

Import pi / opencode / codex / claude-code sessions, chat history, and agents into DeepSeek Harness — one-click Sync button, slash commands, session-start migration prompt

53 months agoSessions & MessagesMIT
J

dsh-interpret

jinchezuo/dsh-interpret

A DeepSeek Harness plugin for live English-to-Chinese captions. Microphone or system audio is transcribed on-device by Parakeet; translation uses the configured DSH LLM route, with a 3,050-term, eight-domain terminology RAG pass and an in-panel picker for cheap, high-quality, or open-source models. Bilingual subtitles sit beside a built-in reader for PDF, DOC/DOCX, XLSX, PPTX, CSV and Markdown; sessions persist locally and export to bilingual SRT or Markdown. macOS arm64 and Windows x64.

4yesterdayVision, Voice & MultimodalMIT
V

dsh-island

vayne-bit/dsh-island

Always-on-top status pill for DSH on Windows: shows each session's turn state (thinking with a running timer, waiting for approval, done, failed) above every window, and while DSH is in the background it draws a bubble under the pill to approve a tool request (allow once / reject) or answer the agent's questions without switching back to the app; it declines to intercept whenever DSH is in front or the overlay is hidden, so the official cards still handle those. Sessions can be listed one per row (row count configurable) or folded into a +N badge by priority, the pill collapses to a small dot after a state settles and hides itself while a fullscreen app is in front, clicking brings DSH to the foreground and dragging moves it, and it reuses the Electron build already shipped with DSH Desktop so nothing extra is downloaded. A settings card on the plugin page adjusts scale, mini size, position, layout, row count, hold times, effects, bubble toggles and per-state visibility.

47 days agoIntegrations & Remote
T

dsh-connect-qwenwork

tang-bugu/dsh-connect-qwenwork

Registers a QwenWork (千问办公) model provider that reuses the desktop client's local sign-in, runs a loopback OpenAI-compatible bridge on 127.0.0.1, and translates DSH model requests into the ACP-style control-envelope conversation protocol the upstream actually speaks.

422 days agoModels & ProvidersMIT
G

dsh-connect-cursor

greatyao/dsh-connect-cursor

Connects a locally-signed-in Cursor desktop app to dsh as a native LlmAdapter — reads the Cursor login token from state.vscdb or auth.json, drives the private agent.v1.AgentService/Run HTTP/2 bidi stream, and translates InteractionUpdate deltas into dsh StreamChunks. No loopback proxy. macOS, Windows and Linux.

427 days agoModels & ProvidersMIT
1

dsh-subagent

1373700184/dsh-subagent

Registers local Qoder, QoderCN, OpenCode, Pi and CodeBuddy CLIs as DSH subagent backends, with ordered model fallback, live progress, per-run credit display, a settings page, and slash commands. Requires the corresponding CLI installed and logged in.

415 days agoModels & Providers
Y

dsh-selection-explain

yfwu2020/dsh-selection-explain

Select text in the DSH web UI to stream a translation and an explanation of what it means in that specific context, read against the conversation it came from; the panel keeps a replayable history and can be promoted into a full session.

412 days agoUI EnhancementsMIT
A

dsh-skills-manager-plus

appthin/dsh-skills-manager-plus

Manage DSH skills and commands from Settings: list, enable/disable, edit, delete and add skills across global and project scopes, and save reusable prompts as slash commands.

412 days agoSkillsMIT
M

dsh-i18n

mimateinn/dsh-i18n

Adds 20 locales (Traditional Chinese HK/TW, Japanese, Korean, French, German, Spanish, Portuguese, Italian, Russian, Ukrainian, Polish, Dutch, Turkish, Arabic, Hindi, Indonesian, Vietnamese, Thai, Swedish) to the DeepSeek Harness Web UI, with hand-polished translations, runtime fallbacks, and automatic translation of market and third-party text.

4last monthUI EnhancementsMIT
S

dsh-im-channel

shrekcg/dsh-im-channel

Unified IM channel for DeepSeek Harness: Feishu, Telegram, DingTalk, Slack, Discord — persistent conversations, true streaming replies, 40 MCP Feishu tools, slash commands, and an IM-bot status tab in the plugin settings.

43 months agoIntegrations & RemoteMIT
M

english-reading-analysis (dsh-plugin)

melanthacode/english-reading-analysis

English article and exam-paper analysis: paragraph-by-paragraph translation, answer keys, and long-sentence syntax breakdown, exportable as a print-ready PDF. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

317 hours agoSkillsMIT
K

dsh-kolmopdf

komoai2026/dsh-kolmopdf

Official KolmoPDF plugin for DeepSeek Harness: six tools for PDF-to-Markdown/OCR with formulas and tables, layout-preserving PDF translation, Markdown export to DOCX/PDF/HTML/LaTeX, cost estimation, and a Settings → KolmoPDF key and live-credits panel. PDFs and Markdown you process are uploaded to the KolmoPDF cloud service (www.kolmopdf.com) with your API key, and conversions use your KolmoPDF credits.

37 days agoTools & CapabilitiesMIT
S

dsh-theme-animal-island-ui

shirolin/dsh-theme-animal-island-ui

Animal Island theme with boarding-pass masthead, cream notebook paper, 118 ThemeRuntime tokens, in-app appearance presets, and starry night mode.

33 days agoThemes & AppearanceMIT
L

dsh-local-trim

leonlee114514/dsh-local-trim

One-step local model onboarding plus a light harness for DSH. On load it probes loopback and private-network inference endpoints (llama.cpp, Ollama, vLLM, LM Studio), reads each model's context window and output budget from the backend, and registers the provider through settings, so a local model becomes selectable without hand-writing config. It then trims only that provider: masks the tool list through tools.restrict, drops named system-prompt sections and memory contexts, swaps the injected instruction block for a short one while preserving its first 80 and last 96 characters, and truncates tool-schema descriptions without touching structure or required fields. Cloud providers are returned as the same assembly object, untouched. The injected block is re-read from disk on every assembly, so editing the file takes effect on the next request with no reload. The panel in the plugin detail page is a live operations view: it shows whether the takeover is active and by which hook, how many characters the last assembly was trimmed from and to, and which providers are online (probed concurrently, with a real one-shot completion reporting latency and reply text per provider). If a local backend is not running, the panel offers a one-click launch: it probes the port first (never starting a duplicate), then starts the matching server (ollama serve, or a custom command you supply) detached and polls until the endpoint answers, clamping the wait to 3-600 seconds, reaping the child it just spawned if it never answers, and naming the paths it searched when it cannot find the binary. A stop button kills backends this plugin started (SIGTERM, then SIGKILL) and refuses to touch a server somebody else launched. When a model has just been downloaded and no backend exists yet, the panel can also scan the machine for .gguf files with hard caps (300 models, 20000 directory entries, Downloads only one level deep), start llama-server on the chosen one (skipping the .mmproj. vision projection and reusing a server that already answers), register the provider under the model id the backend reports, and run one real completion to prove it works. Before spawning anything it does a fit check that counts only the part of the file the GPU cannot hold: hostBytes = fileSize - VRAM, compared against max(total RAM - 2GB, free RAM). A file far larger than RAM is refused outright; a heavy host-side remainder is refused unless you confirm; the same remainder under mmap is only a warning, because the weights land in reclaimable page cache. A load-mode selector (auto / mmap / none / mlock / mmap+mlock) maps to llama.cpp --load-mode, and the default is whatever the engine picks. From 0.4.2 everything above is derived from the platform instead of assumed: home and data directories come from os.homedir() and the OS conventions (LOCALAPPDATA on Windows, ~/Library/Application Support on macOS, XDG_DATA_HOME elsewhere); backend binaries are looked up in the official install locations of each OS and can be pinned with OLLAMA_BIN, LLAMA_SERVER_BIN, VLLM_BIN or LMSTUDIO_BIN; model discovery walks DSH_LOCAL_MODELS_DIR, ~/models, ~/llama.cpp/models, ~/.cache/llama.cpp and the LM Studio data directory, with the WorkBuddy layout demoted to one candidate among them. VRAM is asked from nvidia-smi, then rocm-smi, then sysctl hw.memsize on Apple Silicon (flagged unified, so the same bytes are not charged twice), and any flip to a unified-memory budget is handled explicitly. Before building a command line the plugin runs llama-server --help once and keeps only the flags that build actually has, so older engines get --n-gpu-layers 99 and no KV quantization while newer ones get auto plus q8_0; anything it cannot probe is passed through rather than dropped. LM Studio is started with lms server start --port N rather than being lumped in with the engines that need a model argument, and vLLM gets its own --model example instead of llama.cpp syntax. Windows, macOS and Linux are all exercised in CI, including a windows-latest and a macos-latest job, because a cross-platform claim that has only ever run on one OS is not a claim. Two of those suites exist specifically to catch this machine's blind spots: one replays the whole suite with process.platform rewritten to each OS, and one deletes every advantage this development box has — no nvidia-smi, no rocm-smi, no sysctl, an empty PATH, a home directory with no models — and requires graceful degradation rather than a crash. That last one caught a real class of bug: several assertions hardcoded 'lms.exe', which cannot pass where the executable has no suffix. Measured on the reference machine: a 16.9GB 27.2B MoE with 14.5GB of VRAM holds a 285-691MB working set and sustains 76 tok/s after a 1000-2000 token warm-up, so file size alone is not a fit signal. From 0.4.3 the scanned models are shown as a table rather than a dropdown (one row per gguf, with its size and any fit warning), so you can see what is on disk before choosing. From 0.4.4 the delete button on the provider table removes the provider entry, not the weights file on disk. That distinction matters: what people actually want to clear out is the dead entry - one pointing at a port that never answered, one registered twice for the same port, one whose model file was deleted long ago - not a 15.8GB gguf. Deleting a config is undone by importing again; deleting a gguf is not. The removal goes through settings.mutate with an unset op on \['providers', id], because update merges layers: writing null there leaves a null provider key that the loader reads as a broken config rather than an absent entry, and only mutate/unset is implemented as Reflect.deleteProperty. The result is read back afterwards, because unset on a key that comes from a lower layer (the profile cordis.patch.yml or a home patch) does not delete it - it restores the inherited value, so the call succeeds while the entry stays. When the entry is still there the panel says so and points at the file to edit instead of reporting success, and a DSH whose settings service predates mutate() is told plainly rather than silently ignored. Deleting takes two clicks and clearing the confirmation is as easy as clicking another row; on success the online and baseURL caches are cleared and the tool surface is recomputed, since the provider list changed. The gguf itself is never touched by this plugin - the scanned-model table is display and selection only.VRAM reporting is driver-dependent. From 0.4.5 model discovery also reads Ollama's own storage: its blobs are named sha256-… with no extension, so extension matching could never list them. Weights are now accepted by extension OR by GGUF magic header (only dot-free files of at least 8MB, capped at 600 header reads per scan; obviously-not-weights extensions like .json/.md/.safetensors/.part are never opened). Ollama models are resolved from their manifests: the model layer is picked by mediaType application/vnd.ollama.image.model (never adapter/mmproj layers), the human-readable name is restored from the manifest path (…/qwen3/8b becomes qwen3:8b, …/latest stays bare), tags sharing one blob merge into a single row, and the metadata kv supplies name, quantization and context length. Adopting an Ollama model does not start a duplicate llama-server over the same weights: it confirms ollama serve answers on 11434 (launching it if not) and registers the provider under the tag the endpoint itself reports — the blob's sha256 name would never match anything, since 11434 lists qwen3:14b, not sha256-a8cc…. Two real-machine-only traps fixed on the way: existsSync('<file>/') returns true on Windows, so manifest-vs-directory branching now goes by parseable content instead of trailing-slash semantics; and the quantization label table had been copied from a stale ggml enum generation, labelling ggml_type 15 as Q5_K_S while ollama show reports Q4_K_M. Same-blob dedup is by (dev,ino), keeping whichever entry has a name. Verified on the reference machine: the scan goes from 1 row to 4 — qwen3:14b (8.64G) and qwen3:8b (4.87G) now appear with Q4_K_M badges — in 4ms; npm run verify exits 0 (launcher 57, portable 35, panel-host green including the linux/darwin simulated-platform runs); the new panel-host suite builds a real miniature Ollama store in tmpdir and points OLLAMA_MODELS at it, so results no longer depend on whether the test machine happens to have Ollama installed. From 0.4.6 the panel shows each model its real name instead of its file name, because some download tooling stores every weight under one generic file name, leaving the real name only inside the GGUF header. The scan now reads each file GGUF KV section - not a fixed-size head buffer, because tokenizer.ggml.tokens (hundreds of thousands of strings on a large MoE model) and the chat template push general.file_type past any window; and GGUF string arrays are interleaved (u64 length plus payload per element), so treating them as a length table walks the cursor off the rails and produces astronomically large reads. Reading and skipping are accounted separately: key names and types are always read, string values over 256KB and string arrays are only walked past without copying, non-string arrays over 64 elements are skipped outright, and a cursor past the file size stops the read, because an out-of-range position means the cursor is wrong rather than that a limit should be raised. The displayed name goes Ollama tag, then general.basename plus size_label, then general.name, then the file name, with the full string kept for the hover text since it usually carries internal build numbers; mmproj files are now identified by general.type as well as by name. A short read (truncated file) no longer feeds half a value into the parser. On the reference machine, reading one file header parses 44 keys in about 16ms, and a whole scan takes about 31ms. From 0.4.7 the smoke test no longer fails the first time and passes the second. The old code gave both request attempts one shared AbortController and one shared 30-second timer, so the total budget covered both rounds: a cold load of a large model burned it in round one, the abort left the signal permanently aborted, and the second round (the Ollama-style reasoning_effort: none retry) could not even be sent - which is exactly why the first click returned This operation was aborted and the second succeeded. Now each attempt gets its own controller and timer, a timeout retries once automatically (retryOnTimeout, on by default) because a first-request timeout almost always means the weights are still being read from disk, and non-timeout errors (refused connection, HTTP error) are not retried at all. Timeouts report themselves: the message says the wait exceeded smokeTimeout, whether a retry already happened, and points at the new smokeTimeout setting (seconds, default 60, clamped to 5-600) - port responding is not the same as tokens coming out, so it is a separate knob from launchTimeout. Unrelated: an example naming one specific model was dropped from the panel copy, since not every machine has that model downloaded, and the explanation now describes the mechanism instead. From 0.4.8 adopting a plain .gguf no longer registers an unrelated Ollama model. The port field used to follow the last click rather than the file: selecting an Ollama entry moved it to 11434, selecting a plain .gguf did not move it back, so a 11434 left over from an earlier click stayed. The server accepted it as given, probed the port, found Ollama answering and borrowed it (the skipped-launch log line about the port already answering is this path), and then the model id - derived from the file name - could not be matched against Ollama's /v1/models, where the fallback was to grab the first entry in the list. Embedding models tend to sort first, so the adopt registered a model the user never selected. Now the port follows the file: a plain .gguf landing on another engine's port (ollama 11434, vLLM 8000, LM Studio 1234) is moved to 8090 and the panel says so. Only ports belonging to a known engine are overridden - a hand-typed 9999 aimed at your own llama-server is left alone. The model-id fallback no longer guesses either: it takes the only entry when there is exactly one (a single-model backend may legitimately report a different id than the file name) and otherwise reports an error listing the ids it did see, rather than registering a wrong provider. From 0.4.9 the panel can no longer vanish. It used to be possible for the whole section to disappear from the plugin detail page while the host stayed up, the HTTP bridge kept answering, and no crash log appeared. The cause was a scope error: a helper was declared inside one component and referenced from another, which is valid JavaScript and passes a syntax check, so it only threw at render time - when the user pressed the scan button and React ran the state updater. The host wraps every slot entry in an error boundary whose fallback is an empty anchor, so the throw was contained silently: the panel was not uninstalled or crashed, it was replaced by an empty div. The helpers now live in the module scope both components share. The client half also gained its own test - a minimal React stand-in loads the real panel module, really calls the components, really runs the state updater at render time, and presses the scan button, so this class of error can no longer reach a release.

33 days agoModels & ProvidersMIT
D

dsh-im-union

drscrewdriver/dsh-im-union

Union IM bridge for DSH — an independent implementation uniting the capability sets of community peer plugins (xmanrui/dsh-im, MichengAI/dsh-im-connect). Drive your agent session from 15 channel adapters across 12 platforms (including email; WeCom/DingTalk/QQ each contribute two: bot + self-built app or notify tier) — WeChat (official iLink QR bind), Feishu/Lark (long-connection + streaming cards; the voice tier requires system ffmpeg), Telegram, Discord, WeCom intelligent bot & self-built app (signed callback), DingTalk (stream + AI Card and custom-robot notify), QQ official bot (plus notify tier), Slack (Socket Mode), WhatsApp (Baileys QR pairing; the dependency ships as an optionalDependency of the plugin package), Matrix, iMessage (macOS only), Email (IMAP/SMTP thread routing). The cross-version narrow waist auto-adapts settings gen1/gen2/gen3 across hosts 0.1.2-rc.1→0.2.1-rc.2 (12-tag enum; rc.2 verified by a real desktop-profile install with double read-back) using capability probing only, never version branches. In chat: a 25-command panel, tool-approval and question loops answered in the originating chat (deny-by-default, initiator-only, 5-min expiry), image/file input gated on host model metadata, deliverable file return, a delivery log with bounded retry (uncertain is never re-sent), proactive delivery and fragment composition. It also splits the native sidebar into self-owned Tasks / Channels tabs (standing down entirely when another plugin already owns the slot), registers an `im-concise` agent preset plus reply sanitisation that keeps GenUI fences and raw HTML out of text-only chats, renders `svg` fences to PNG images, guards model choice with an allowlist, and mirrors each turn's final answer to notify channels via `/relay` (addressed by account ID or alias, never guessed on ambiguity). Secrets are one-way into the vault and never echoed back. npm: `dsh-im-union`.

36 days agoIntegrations & Remote
H

dsh-jev-thinkout

han-1413141/dsh-jev-thinkout

Shows JeV-selected task plans, progress updates and stage summaries in DSH chat, with native translation or lightweight summaries. Requires a JeV key; the Jev service is called externally and may bill. and hierarchical serial/parallel task flows.

328 days agoUI EnhancementsMIT
S

dsh-select-translate

shan5246992zhui/dsh-select-translate

Select text in any Windows app and read the translation in an always-on-top card next to the cursor: streaming text follows the newest line, up to 15000 characters per request. Windows only.

327 days agoUI Enhancements
J

dsh-prompt-enhancer (dsh-prompt-enhancer)

jianyiag/dsh-prompt-enhancer

Composer prompt enhancement for DeepSeek Harness: a button beside the model selector rewrites the draft through one auxiliary LLM call and writes the result back in place, with composer undo left intact; a /prompt-enhance slash command returns the rewritten prompt as a command result line without touching the draft; the enhancement call can be pinned to its own fast provider and model in the profile patch; the rewrite policy is faithful - original intent, language and information are kept, code, commands and paths are preserved verbatim, and nothing is invented or padded with placeholder text.

3yesterdayUI EnhancementsMIT
W

dsh-word-vault

wangzhanchao883/dsh-word-vault

English word bank for one or more children, built for DSH 0.2 and newer (0.2.0-rc.1 and 0.2.0-rc.2 verified, including the desktop shell; 0.1.7 through 0.2.x all work). 1.10 added pronunciation: in the memory cards and in the online quiz every word and every example sentence has a speaker button that reads it aloud with the built-in Windows voice - offline, with no network call and no model call - and the whole batch of audio is pre-rendered in the background whenever cards or an exam are generated, so a click starts instantly. 1.11 adds: pick words in bulk straight from the library (10 at a time, top-down, up to 50 selected, with a live counter); turn the words a child got wrong in a quiz into a one-click review set - an online card page that speaks plus a printable PDF; and every card example sentence now carries its Chinese translation underneath. Words marked on textbook or workbook photos (highlighter, red pen) are found by their marks, then translated and stored in a local SQLite bank with an occurrence count; the clipboard picker, the photo route and dictation all land in the same bank. High-frequency words surface by count, three correct answers in a row flag a word as learned, and any selection prints as a memory card set (a word split into chunks, real IPA per chunk, a grade-7 example sentence, a mnemonic hook, an A4 sheet of eight) in HTML, PDF or Word, with a print-and-answer exam page whose four options are set against each other for meaning. On 0.1.5 the settings panel does not appear - install dsh-word-vault@1.0.2 instead.

3last monthTools & CapabilitiesMIT