Categories › Models & AI
Models & AI
4323 pluginsModel access, vision, voice, agents and personas.
Sorted by downloads. 100 per page.
@deepseek-ai/dsh-experimental-liveshare-protocolunregistered
Liveshare wire frames and the identity contract shared by the owner bundle and the Relay
↓ 0
@dsh-cc/settings-providerunregistered
Vendored settings-provider contract (harness 0.1.5-rc.1 SettingsProvider seam) decoupled f
↓ 0
@ajia1206/dsh-restart
One-call restart for the running DSH process, with launchd-aware supervision detection, a
↓ 0
dsh-aug-remotetested
一个插件、两种角色：主服务端把 DeepSeek Harness 变成手机能安全访问的 PWA（移动端界面、配对码网关、Web Push），并把选定会话共享给已配对的桌面端；子客户
↓ 0
dsh-plugin-jev-routertested
Per-turn model and reasoning-effort routing for DeepSeek Harness -- one Jev choice questio
↓ 0
icyaaaww/dsh-bili-vision
DSH Bilibili video understanding plugin: timestamped frames, local ASR/OCR, and optional i
↓ 0
dsh-plugin-qwen-imagefails
DeepSeek Harness out-of-tree plugin: give a text-only coding model eyes by routing images
↓ 0
dsh-plugin-packtested
DeepSeek Harness 插件整合包：一键把当前 profile 的第三方插件连依赖和配置导出成 zip（内部每个插件是标准 npm tgz），换机/换 profile 拖
↓ 0
@qiqiangvae/dsh-obsidiantested
Self-organizing AI second brain for Obsidian, as a single DeepSeek Harness plugin. Merged
↓ 0
dsh-harness-jarvistested
A floating desktop assistant for DSH Desktop — a particle orb for quick permission approva
↓ 0
dsh-realtime-audio-wsunregistered
The host end of the client half's transport: a WebSocket upgrade route that bridges microp
↓ 0
dsh-harness-reflextested
DSH Host plugin exposing the harness-reflex System One decision runtime (choice, score, ro
↓ 0
dsh-plugin-shot-annotatefails
Screenshot button for the DeepSeek Harness Web UI 鈥?region capture, annotation (pen/line/b
↓ 0
naili0712/dsh-gsv-localtested
Local GPT-SoVITS voice for DeepSeek Harness: boots the engine with DSH and kills it on exi
↓ 0
Jesse-njx/dsh-voicefails
Voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe),
↓ 0
jryang1997/dsh-hold-to-dictatefails
Hold-to-talk dictation in the composer that ships no recognizer of its own and reuses the
↓ 0
jypjypjypjyp/dsh-music-studiotested
Music composition inside the conversation: the model writes a score against a bundled comp
↓ 0
lihua12345670-jpg/dsh-bili-audiotested
Plays the audio of a Bilibili video from a floating bar in the DSH Web UI, with a queue, s
↓ 0
LIU118117/dsh-voicetested
Adds a voice to the agent: emotional speech synthesis (ChatTTS when available, falling bac
↓ 0
Making-acid/dsh-synthv-studiotested
Connects a local Synthesizer V Studio 2 Pro to the agent through its own Lua script API, w
↓ 0
Nothree-code/voco-input-shtested
Voice input for the Web UI: a mic button that drives local VocoType offline speech recogni
↓ 0
Nuoyi207/dsh-gptsovits-ttstested
Local GPT-SoVITS text-to-speech for DSH: reads replies aloud, switches voices from the rig
↓ 0
OldQin-Aurora001/dsh-breeze-ttstested
Breeze TTS client for DeepSeek Harness: connects to your own Breeze TTS server to read rep
↓ 0
@falsenex/dsh-llm
Provider-neutral LLM service interface for the DeepSeek Harness
↓ 0
QT-Chen/dsh-mic-inputtested
Microphone voice input for the composer: browser Web Speech API live transcription, dedupe
↓ 0
radres/dsh-plugin-call-metested
Rings your phone over CallKit: `call_me` and `text_me` tools, plus optional turn-end and a
↓ 0
red000000/dsh-bili-music-playertested
Bilibili music player for the DSH composer dock: import your Bilibili login cookie and a l
↓ 0
rootryanlau-art/dsh-voice-transcribefails
Transcribe local audio and video files offline with a composer panel, a CLI, and an agent
↓ 0
Schumchanvi/dsh-voice-input-cntested
China-ready voice input for the composer. Requires a local Python bridge (pip install dash
↓ 0
tangzheng202202/dsh-voice-livetested
Real-time duplex voice over Volcengine streaming ASR/TTS: agent reply narration, barge-in,
↓ 0
"https://github.com/scarf1985566475-cloud/dsh-voice/releases/download/v0.2.0/dsh-voice-interpreter-0.2.0.tgz"
Local English-to-Chinese simultaneous interpretation: on-device Qwen3-ASR bilingual captio
↓ 0
↓ 0
toddpan/dsh-xiaozhitested
Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weavin
↓ 0
wzd-cpu/dsh-breeze-ttsfails
BreezeBlue text-to-speech for DSH: three agent tools, a header toggle that reads assistant
↓ 0
yu-wenchao/dsh-tool-lipsynctested
Free lip-sync video generation plugin for DSH with 3000+ voices and 500+ languages.
↓ 0
zeshuochen/dsh-watch-videofails
Subtitle-first video transcription with SRT export, cancellable job controls, and a faster
↓ 0
dsh-plugin-repotested
Self-hosted plugin repository for DeepSeek Harness (DSH). Each device serves its own repo
↓ 0
1122438/we-plugin
DeepSeek Harness 的会话级角色扮演插件
↓ 0
dsh-plugin-auto-videotested
Turn a script into a finished video locally: AI voiceover, perfectly timed subtitles, back
↓ 0
@tmim/dsh-plugin-tmimtested
DeepSeek Harness plugin that connects to the TM IM network (Agent Takeover webhook + REST)
↓ 0
@eduwork/dsh-oidctested
Standards-based OIDC identity, token-authorized model access, declarative branding, and Op
↓ 0
dsh-plugin-claude-bridgetested
Bridge Claude Code's memory, skills, and configuration into DeepSeek Harness — zero migrat
↓ 0
dsh-pi-agent-providersfails
The pi agent's provider catalog (~/.pi/agent/models.json) as DeepSeek Harness LLM routes —
↓ 0
hangdingding/breezetts-dshtested
Breeze TTS for DeepSeek Harness: read replies aloud in full or as a short summary, one-cli
↓ 0
FYZB2020/dsh-voice-doubaotested
Adds two Volcengine Doubao cloud speech recognizers to the DeepSeek Harness voice-input pi
↓ 0
@showin2333/dsh-plugin-share-imagetested
DeepSeek Harness plugin that shares selected conversation messages as a PNG card.
↓ 0
berserk0501/dsh-soundscapefails
Dual-MediaPlayer daemon ($think loop + $fx one-shots) with volume ducking, mood-aware soun
↓ 0
beiyege-01/dsh-voice-ai-girlfriend-pluginunregistered
Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion
↓ 0
ALittleLov/dsh-soundchecktested
Turns a local audio file into a short plain-language verdict on tempo, key, dynamics, clip
↓ 0
abbccdd/dsh-localttsunregistered
Reads Harness replies aloud through an existing local TTS runtime: built-in IndexTTS and G
↓ 0
1DAdidi/dsh-voice-horntested
Floating TTS speaker in each conversation corner: when an AI reply finishes, edge-tts read
↓ 0
1497105876/dsh-mimottstested
MiMo TTS speech synthesis for DeepSeek Harness: a speak button on finalized assistant mess
↓ 0
117BS/dsh-perlica-dingtested
Perlica (Arknights: Endfield) themed tiered sound notifications: plan-ready, task-done, ne
↓ 0
0nt-one/dsh-voice-inputtested
Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language
↓ 0
dsh-visual-card
可视化回答：AI 生成一段 HTML，在对话中以沙箱卡片渲染，支持交互按钮；配色自动跟随当前主题。
↓ 0
yzhclcl/dsh-omni-modaltested
Adds an Omni-modal settings section to DeepSeek Harness that points the harness at any Ope
↓ 0
xuhairui-dzz/dsh-shengtutested
Multi-engine image generation inside the conversation: an agent tool plus a composer-dock
↓ 0
CAI-MH/dsh-gpt-imagetested
Generate images through a logged-in web ChatGPT session and download them to a local direc
↓ 0
Cheng-cheng9669/dsh-deepseek-visiontested
Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool
↓ 0
ChordXD/dsh-image-comparetested
Adds a right-column panel that compares a set of images the user picks from the workspace
↓ 0
ck99998888/dsh-video-readertested
Reads a video or audio file into metadata, sampled stills, subtitles and a multilingual sp
↓ 0
NewDaNew/dsh-voice-inputunregistered
Voice input for the web UI: a mic button in the composer that transcribes speech into the
↓ 0
Daive1119/local-ocrtested
Registers one `ocr` tool for text-only models: it runs the offline script bundled in the r
↓ 0
dttGitHu/dsh-video-androidtested
Video studio for DeepSeek Harness on Android: storyboard editing, multi-provider image/vid
↓ 0
dsh-llms-forgefails
Generate llms.txt for DeepSeek Harness (dsh) plugin repositories from package.json + READM
↓ 0
dingchenhui0618-arch/dsh-mask-pixel-locktested
Prove that a local image edit left every pixel outside its mask untouched. Original, gener
↓ 0
dingchenhui0618-arch/dsh-vision-difftested
Pixel-level screenshot diff for visual regression. Two local PNGs in; a machine-readable f
↓ 0
DSH-Raising-Plan/dsh-video-storyboard-hpunregistered
High-performance fork of SAOS-3624/dsh-video-storyboard — install this or the upstream plu
↓ 0
Elohia/dsh-plugin-mm-visiontested
Synesthesia Encoder for DSH: a vision model translates images into compact structured spat
↓ 0
ethanweave/dsh-vision-bettertested
Vision relay for text-only models: a configurable GLM-compatible vision endpoint analyzes
↓ 0
Eva7788519/dsh-screenshot-tooltested
Adds a screenshot tool that captures the Windows desktop to PNG and hands the path to the
↓ 0
fj7937290-sys/dsh-video-eyestested
Read a video with a text-only model: with ffmpeg installed, sample frames at a 0.1-10 seco
↓ 0
gloryxpnv/dsh-tool-visionunregistered
Local-first structured vision for text-only agents: images go to a local OpenAI-compatible
↓ 0
GXX182/dsh-vision-bridgefails
Bridges session images to configurable vision providers and returns text-only analysis to
↓ 0
Harvey-Will/dsh-vision-analysistested
DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, ob
↓ 0
Harzva/dsh-maclenstested
Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), ima
↓ 0
hawkhai/wechat-ocrfails
Local WeChat OCR tool for DSH: `wechat_ocr_recognize` returns recognized text and the engi
↓ 0
hawkhai/win11-oneocrfails
Local Windows 11 OneOCR tool for DSH: `oneocr_recognize` returns OCR text and structured l
↓ 0
hiocobueno653-pixel/dsh-image-gentested
Image-generation tool with automatic prompt enhancement, switchable API profiles, and a Tu
↓ 0
hyper-dsh-plugins/dsh-open-eyesfails
Vision bridge for text-only DeepSeek routes that analyzes attached and local images throug
↓ 0
jmxsxwyzjdwl/dsh-mmroutetested
Transparent multimodal routing for text-only models: every image in every model call is fu
↓ 0
jyh20030112/dsh-visual-plugintested
Gives text-only models vision: forwards user images to an OpenAI-compatible vision model a
↓ 0
k2d5rqjpkg-art/dsh-auto-visiontested
Auto-switch the DeepSeek route to the vision model on demand: flash main session switches
↓ 0
Kagurazaka135/dsh-video-framestested
Give a text-only agent video understanding: extract timestamped frame files, sample only o
↓ 0
klingai-dev/deepseek-pluginunregistered
Turn every idea into an image or video with Kling AI. In DeepSeek Harness, use natural lan
↓ 0
ld-1101/dsh-vision-pluginfails
Give your text-only model eyes - chat image attachments are auto-described via a vision mo
↓ 0
LeemanCheung/dsh-image-genfails
GPT Image 2 `image_gen` with Codex subscription OAuth by default or explicit API-key mode:
↓ 0
Leeminjing/dsh-eyestested
On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_
↓ 0
lhbsaa/dsh-visibridgefails
Structured vision evidence (OCR/layout/semantics) plus a USB camera capture tool for a "sh
↓ 0
linenxi-ctrl/dsh-visionfails
External vision plugin for DeepSeek Harness: whale-button config panel, image recognition
↓ 0
LINinLIN-0079/godot-imagegentested
Local art pipeline for DSH: drives the locally installed SD WebUI and ComfyUI backends thr
↓ 0
xhznai/media-sense
Audio and video understanding for DeepSeek Harness, with configurable models and FFmpeg se
↓ 0
Monter-code/dsh-image-insighttested
Structured image recognition: local sharp measurements plus a cloud vision model return de
↓ 0
NagasakiSoyo-ui/dsh-llm-deepseek-visiontested
Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a te
↓ 0
niyongsheng/free-vision-skilltested
Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table
↓ 0
ns-zzj/dsh-hos-scrcpytested
Control a HarmonyOS phone from the DSH web UI with AI: live H.264 screen mirroring, mouse
↓ 0
poiuyjie/dsh-vision-opencodefails
Adds a configurable vision model to text-only main models: a vision_read_image tool, a com
↓ 0
QXingYShu/dsh-comfyui-imagetested
Generate images from the agent on the user's own GPU by queueing a workflow on a local Com
↓ 0
Renji004/dsh-omni-visiontested
Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in th
↓ 0
s3yf1337/dsh-easyvisionfails
Give text-only models vision: a describe_image tool that delegates images to a vision mode
↓ 0