Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

252 plugins found

Z

dsh-agnes-media

zzsszz1122/dsh-agnes-media

Sidebar panel for Agnes image and video generation that also ships a node canvas and a short-drama mode. Canvas nodes are chained by extracting the previous shot's tail frame with ffmpeg and submitting it as the next shot's first frame; short-drama mode turns an imported script into storyboard shots. Generation and polling run in the Host process, so tasks survive a page reload or a closed panel, and results plus an 80-entry history are stored on disk.

46 days agoVision, Voice & MultimodalMIT
A

dsh-bili-interactor

acttk/dsh-bili-interactor

Browses Bilibili on your behalf and actually takes part: search videos, like, coin, send danmaku, post comments, reply to other people, and keep replying when someone answers back. Reads the video's Bilibili AI subtitle (or transcribes the audio locally when there is none) so its comments talk about what the video really says, and it reads that same content before choosing whom to reply to. Instead of copying other people's sentences, it distills rules about how to sound like a person and gets less AI-ish the more it runs. Skips videos it already browsed, de-duplicates replies per thread, and after too many rounds with the same person in one comment section it reviews whether the exchange has any substance -- if it looks like two bots complimenting each other, it says one last line and stops replying to that person there. Checks whether each comment is genuinely public or only visible to your own account, can scan any time window (last hour / day / 3 days / all) and lists the ones others cannot see, warning you on the overview when replies got folded. Six-tab settings panel where every change takes effect immediately with no restart, a manual run that queues behind the background listener instead of being refused, and an environment self-check that tells you exactly what to install. Requires Python 3 for the Bilibili actions; the built-in check lists any missing packages.

426 days agoTools & CapabilitiesMIT
H

dsh-icon-console

h1kariiiiiii/dsh-icon-console

Icon console for the DSH desktop app: import one icon and apply it to the desktop and Start Menu shortcuts (immediately), the application window image and the system tray image (after a restart), with automatic backup, one-click restore, a named icon library, and restart/exit controls.

42 months agoUI EnhancementsApache-2.0
W

dsh-inline-media-viewer-plugin

wisdoverse/dsh-inline-media-viewer-plugin

Renders image, video, and audio paths and URLs from DSH conversations inline, with workspace-confined local reads and an optional ComfyUI proxy.

45 days agoSessions & MessagesMIT
F

dsh-wechat-mp-studio

funcwei/dsh-wechat-mp-studio

WeChat Official Account content studio: anti-homogenization rotation writing, low-creativity remediation playbook, blessing-image visual baseline, gpt-image pipeline with OCR acceptance, and the measured xiaolvshu draft web API.

43 months agoSkillsMIT
T

dsh-media-preview

tsonglew/dsh-media-preview

Audio/video FileViewer for dsh-better-sidebar: native inline playback for mp4/webm/mkv/mov and mp3/flac/wav, served by a Range-capable streaming media route.

43 months agoUI EnhancementsMIT
O

pocketagents

oscarka/pocketagents

PocketAgents (formerly deepseekharness-remotecontrol): self-hosted mobile Web PWA and Feishu remote control hub for DeepSeek Harness plus local adapters for Antigravity IDE, Codex, Claude Code, WorkBuddy and Doubao, with swipe-triage approvals, multiple-choice popup replies, hold-to-talk voice steering, TTS reply playback, HLS/WebRTC media preview, multi-host pinning, Web Push notifications, and 5-second terminal QR pairing.

3yesterdayIntegrations & RemoteMIT
O

deepseekharness-remotecontrol

oscarka/deepseekharness-remotecontrol

Mobile Web PWA and Feishu remote control hub for DeepSeek Harness (plus optional local adapters for Antigravity, Codex, Claude Code, WorkBuddy and Doubao): starts an embedded HTTP hub on 0.0.0.0:8788 gated by a bearer token and 6-character pairing code, with session switching, file browsing, media preview, tool approvals, Web Push notifications, and optional outbound relay to a self-hosted Cloud Hub or Feishu bot.

33 days agoIntegrations & RemoteMIT
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.

35 days agoModels & ProvidersMIT
W

dsh-wechat-media

wjh-ux/dsh-wechat-media

Personal WeChat and WeCom (企业微信) bridge: QR pairing, one DSH conversation per chat, two-way text/image/video/document/archive transfer, chat commands (/help, /status, /new, /stop, /friends) answered by the bridge itself without spending a model turn, a switch that restricts the bot to 1:1 chats (group messages are dropped silently and counted), remote approval by replying 1 or 2 in the chat, and a two-way WeCom intelligent robot over its long connection (no public URL needed) that also receives and sends images, files and videos.

322 days agoIntegrations & RemoteMIT
U

dsh-notify-say

unifilitence/dsh-notify-say

Windows desktop notifications for DSH that speak the turn result by default: Windows TTS needs no download, and 13 VOICEVOX voice packs can be installed from the settings page. A completed alert waits until running subagents and background jobs finish; approval, question and error alerts fire immediately. Voice packs are downloaded from GitHub after a terms confirmation.

328 days agoIntegrations & RemoteMIT
D

dsh-media-lens

drscrewdriver/dsh-media-lens

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

34 days agoVision, Voice & Multimodal
T

dsh-zcode-plan-bridge

tangyixiao/dsh-zcode-plan-bridge

Requires the ZCode CLI installed and signed in. Relays the ZCode CLI agent into DeepSeek Harness as a model provider. A resident app-server session streams each turn, and the model catalogue is read from the CLI at runtime, so context windows, image support and provider routes follow the installed CLI and account. Stable 0.6.6 supports DSH 0.2.2-rc.1 and 0.2.2-rc.3, adds a bilingual toolkit, optional Z·SWITCH saved-account controls with independent DSH or shared login, next-request quota switching without failed-task replay, and canonical context-overflow handling. Session titles are generated in disposable native sessions. Quota rotation recognizes attributed Start Plan code 1005 with the exact exceed quota limit message. Tool permission requests are denied by default; unknown approval or permission methods are always denied, and full-auto requires an explicit opt-in. DSH approval UI does not mediate this separately spawned app-server process, and the policy is not an OS sandbox. Derived from kyle123740/dsh-zcode-cli-proxy (AGPL-3.0); it registers the same `zcode-cli` provider id, so it cannot be installed alongside the original. Its HTTP routes first require the synchronous connection.requestRejection Host/Origin policy, then connection.admit owner admission; missing, throwing, malformed or asynchronous checks fail closed. Independent rotation continues the current task by default after confirmed quota exhaustion and native tool drain.

320 hours agoModels & ProvidersAGPL-3.0
O

dsh-video-preview

orderg-x/dsh-video-preview

Plays local video and audio inside the conversation. Media files the model writes during a turn - screen recordings, transcodes, voiceovers - get a player under its final reply automatically when their paths appear in its commands, the command output or the reply; the play_video tool plays any other file. Video shows as compact cards with a hover preview, audio as a slim seek bar, streamed over HTTP Range so long files seek instead of loading into memory. Also registers a sidebar media preview renderer, since the built-in previewer treats mp4 as unviewable. The look_video tool lets the model see a video itself: a hidden local Chrome or Edge grabs frames into a time-labelled contact sheet (or big frames at given times, or a short range frame by frame), checks the audio (silence, too quiet, clipping, one channel only) and the picture (black or frozen frames), and reads MP4 / MOV headers for phone compatibility (codec, HDR, faststart and more), with ffmpeg fixes.

310 days agoUI EnhancementsMIT
L

dsh-plugin-genshin-launch

link258qaq/dsh-plugin-genshin-launch

Windows only. On every DSH start it checks, with no configuration, whether Genshin Impact is already installed — if it is, the game is launched (falling back to the miHoYo launcher when the game exits immediately, e.g. while an update is pending); if it is not, the launcher installer is downloaded to the desktop behind a size gate that rejects any link whose payload is more than 15 MiB away from the expected ~224 MiB, and a failed download falls back to opening the official download page.

3last monthJust for FunMIT
C

dsh-terse-mode

cspyz/dsh-terse-mode

Four terse levels in the conversation header — less thinking, no web search, shorter answers — plus independent switches for reasoning effort, web search and subagents, mirrored in Settings. Changes apply immediately. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

37 days agoUsage & BillingMIT
J

linkdigest-mcp

jcaiagent7143-ui/linkdigest-mcp

Turns a Xiaohongshu, Douyin, TikTok, YouTube or X link into text: transcript with timecodes, on-screen text, a description and OCR of every image, caption and metadata. Mounts the hosted MCP server over streamable HTTP.

32 days agoTools & CapabilitiesMIT
X

dsh-session-theme

xliecc/dsh-session-theme

Shows every session theme in the DSH Web left sidebar immediately on page load by warming the session projection cache at startup; no need to click into a conversation first.

33 months agoUI EnhancementsMIT
W

wavespeed-dsh-skill

wavespeedai/wavespeed-dsh-skill

Generate and edit AI media (image, video, audio, 3D) with WaveSpeed models via the open-source wavespeed CLI: live catalog search, per-model input-schema introspection, local-file upload with @path markers, and price checks before running.

317 days agoSkillsMIT
G

dsh-mobile-remote

good-boy4069/dsh-mobile-remote

Drive your dsh agent from WeChat over the iLink gateway: two-way encrypted media transfer (auto-decrypt inbox + /send), proactive weixin_send tool, completion notifications, multi-session switching, and a health panel with file logging.

33 months agoIntegrations & RemoteMIT
L

dsh-plugin-grok2api-media-tool

lsjspl/dsh-plugin-grok2api-media-tool

Gives dsh the ability to generate images and videos through the grok2api API.

33 months agoVision, Voice & Multimodal
S

dsh-plugin-muapi

samuraigpt/dsh-plugin-muapi

MuApi media-generation tool: a muapi_generate tool that submits and polls jobs against any of MuApi's 100+ image, video, audio, and 3D models through one x-api-key.

33 months agoTools & CapabilitiesMIT
R

dsh-wallpaper-engine

ruijiaang-lab/dsh-wallpaper-engine

Wallpaper backgrounds for the DSH web GUI. Windows: reads your Wallpaper Engine (Steam) library and plays video/web wallpapers behind the chat. macOS: scans the WaifuX download folder and loose media folders automatically — anything saved in WaifuX becomes a DSH background with zero setup. Liquid-glass blur, dim and border sliders.

32 months agoThemes & Appearance
H

dsh-plugin-aigc-canvas

huanlinoto/dsh-plugin-aigc-canvas

provider-agnostic AIGC HTTP 桥 + 无限画布 + ffmpeg 后处理,13 个工具含画布连边/reroll/媒体编辑 | Provider-agnostic AIGC HTTP bridge + infinite canvas + ffmpeg post-processing; 13 tools incl. canvas linking/reroll/media-edit

33 months agoVision, Voice & Multimodal