Categories › Models & AI
Models & AI
868 pluginsModel access, vision, voice, agents and personas — extending what DSH can do.
Sorted by downloads. 100 per page.
"https://github.com/liubaicai/dsh-qoder-link/releases/download/v0.1.11/dsh-qoder-link-0.1.11.tgz"
Connects Qoder models to DeepSeek Harness through the official Qoder CLI over native ACP s
↓ 0
"https://github.com/qiubai-di/dsh-chatgpt-subscription/releases/download/v0.1.8/dsh-chatgpt-subscription-0.1.8.tgz"
Connect ChatGPT subscription models to DSH via OAuth, preserving local tool-call identity
↓ 0
"https://github.com/liubaicai/dsh-codebuddy-link/releases/download/v0.3.30/dsh-codebuddy-link-0.3.30.tgz"
Connects Tencent CodeBuddy CLI to DeepSeek Harness through ACP, with native CLI tool execu
↓ 0
"https://github.com/liaoyuqing/model-failover-manager/releases/latest/download/model-failover-manager.tgz"
Model picker dialog with routing groups: a model that keeps failing hands the turn to the
↓ 0
"https://github.com/liaoyuqing/dsh-llm-error-retry/releases/latest/download/dsh-llm-error-retry.tgz"
LLM request retry plugin for DeepSeek Harness: when a model request fails with a configure
↓ 0
"https://github.com/kennethfan/dsh-bailian-catalog/releases/download/v0.2.0/dsh-bailian-catalog-0.2.0.tgz"
Bailian (DashScope / Model Studio) model catalog in the DSH settings page: lists every mod
↓ 0
"https://github.com/Kalospacer/dsh-model-capabilities/releases/download/v0.1.0/dsh-model-capabilities-0.1.0.tgz"
Adds a settings page for declaring per-model reasoning efforts and vision support on pi-ai
↓ 0
"https://github.com/JiahaoXxX/dsh-model-pool/releases/latest/download/dsh-model-pool.tgz"
Declarative provider/model fallback chains for the model picker: an ordered root chain plu
↓ 0
"https://github.com/itchenshi/dsh-gateway-models/releases/download/v0.2.0/dsh-gateway-models-0.2.0.tgz"
Declares the OpenCode Go and Command Code route wire protocol and endpoint (so the API add
↓ 0
"https://github.com/irerc/dsh-deepseek-web/releases/latest/download/dsh-deepseek-web.tgz"
Adds a browserless deepseek-web provider that drives chat.deepseek.com, with an account po
↓ 0
"https://github.com/henrikdukefoss/dsh-standardcompute/releases/latest/download/dsh-standardcompute.tgz"
Adds Standard Compute as an OpenAI-compatible model provider through the built-in pi-ai ad
↓ 0
"https://github.com/gulagala001/dsh-response-id-reuse/releases/download/v0.1.6-dsh.0.2.2-rc.1/gulagala001-dsh-response-id-reuse-0.1.6-dsh.0.2.2-rc.1.tgz"
Reuses stored Responses IDs for continuation, with retry and branch isolation and verified
↓ 0
"https://github.com/FuSheng-cs/Trae2api-dsh/releases/latest/download/trae2api-dsh.tgz"
Use TRAE account model quota in dsh, with multi-account management, daily check-in, rotati
↓ 0
"https://github.com/Faide-cyber/dsh-workbuddy/releases/download/v1.0.23/dsh-workbuddy-1.0.23.tgz"
Bring WorkBuddy's free and paid models (domestic and international) into DSH — no WorkBudd
↓ 0
"https://github.com/EmotionG/dsh-llm-config/releases/download/v0.2.0/dsh-llm-config-0.2.0.tgz"
Requires DSH >= 0.2.0-rc.2 < 0.3.0. Declare any number of LLM providers, each with its own
↓ 0
"https://github.com/dev-bravelo/dsh-hf-spaces/releases/download/v0.1.0-alpha.8/dsh-hf-spaces-0.1.0-alpha.8.tgz"
Adds the models of your own GPU Hugging Face Space to the model selector, starts the Space
↓ 0
"https://github.com/Dalizi2026/dsh-factory-provider/releases/latest/download/dsh-factory-provider.tgz"
Factory (Droid) subscription quota as native DSH model providers, with three protocol rout
↓ 0
"https://github.com/ChimeSky/dsh-effort-keeper/releases/download/v1.0.5/dsh-effort-keeper-1.0.5.tgz"
Remembers the reasoning effort you explicitly chose for each provider and model and restor
↓ 0
"https://github.com/BaoBao1996121/dsh-chatgpt-subscription/releases/download/v0.1.3/dsh-chatgpt-subscription-0.1.3.tgz"
Adds native Codex OAuth sign-in, main-Agent default model selection, and direct or local-p
↓ 0
"https://github.com/Ayelsh/reasoning-setup/releases/latest/download/dsh-reasoning-setup.tgz"
Edit reasoning effort levels and thinking formats for models that declare none.
↓ 0
"https://github.com/Asheblog/dsh-ollama-cloud/releases/latest/download/dsh-ollama-cloud.tgz"
Ollama Cloud provider for DeepSeek Harness: adds the chat route on install, publishes each
↓ 0
"https://github.com/66rapper/dsh-model-auto-enricher/releases/latest/download/dsh-model-auto-enricher.tgz"
Model channel auto-enricher for DeepSeek Harness: eliminates manually configuring contextW
↓ 0
"https://github.com/CanaryJing/dsh-big-fat-whale-maid-adaptive/releases/download/v3.2.2/dsh-preset-big-fat-whale-maid-adaptive-3.2.2.tgz"
Agent preset with adaptive tool presentation and environment-aware shell routing. Ports mo
↓ 0
"https://github.com/ccll/dsh-advisor-flow/releases/download/v0.2.1/dsh-advisor-flow-0.2.1.tgz"
Executor/advisor workflow ported from pi-advisor-flow: the executor calls ask_advisor for
↓ 0
"https://github.com/samirliu/dsh-goalloop-agentteams/releases/download/v0.9.2/dsh-goalloop-agentteams-0.9.2.tgz"
Deterministic goal-completion gate for DSH: a contract-first AC grammar with named failabl
↓ 0
"https://github.com/robbywang25/dsh-llm-mlx/releases/download/v0.4.0/dsh-llm-mlx-0.4.0.tgz"
Use local MLX-LM or MLX-VLM models in DeepSeek Harness through a loopback OpenAI-compatibl
↓ 0
"https://github.com/BW741/dsh-video-eyes/releases/download/v1.0.0/dsh-video-eyes-1.0.0.tgz"
Lets the model actually see a video: local ffmpeg samples timestamped stills and faster-wh
↓ 0
"https://github.com/chenyth/dsh-image-designer/releases/download/v0.1.3/dsh-image-designer-0.1.3.tgz"
Image Designer connects DSH to Shenhuo AI designers, with personal OAuth, material uploads
↓ 0
"https://github.com/chenyth/dsh-image-editor/releases/download/v0.2.0/dsh-image-editor-0.2.0.tgz"
Image Editor separates uploaded images into editable layers through Shenhuo MCP, with conf
↓ 0
"https://github.com/Destinhue/dsh-video-vision/releases/download/v1.4.0/dsh-video-vision-1.4.0.tgz"
Five tools for reading a video as raw material rather than as something to watch. video_ou
↓ 0
"https://github.com/joeseesun/qiaomu-cover-design-dsh/releases/download/v0.1.3/qiaomu-cover-design-dsh-0.1.3.tgz"
Design covers on a canvas using templates and typography controls, and export PNG images.
↓ 0
"https://github.com/kingcharleslzy-ai/dsh-qwen-studio/releases/latest/download/dsh-qwen-studio.tgz"
Qwen Image 2.1 workspace for DSH: Apple Silicon MLX or your own NVIDIA server, native refe
↓ 0
"https://github.com/ntesicn/dsh-screenshot-xn/releases/latest/download/dsh-screenshot-xn.tgz"
Full-screen screenshot panel for the DSH composer: marquee selection with rectangle, ellip
↓ 0
"https://github.com/lengmodkx/dsh-mimo-tts/releases/latest/download/dsh-mimo-tts.tgz"
MiMo voice for DeepSeek Harness — reads each finished answer aloud, turns composer dictati
↓ 0
"https://github.com/zirscard/dsh-ocr/releases/download/v0.3.0/dsh-ocr.tgz"
Registers two tools for DeepSeek Harness. `doc_ocr` turns scanned PDFs and images into str
↓ 0
"https://github.com/2021Heei/dsh-tts-flash/releases/download/v0.1.0/dsh-tts-flash-0.1.0.tgz"
Reads AI replies aloud as they stream, with voiced waiting phrases while the model thinks.
↓ 0
"https://github.com/aa2246740/dsh-livevoice/releases/download/v0.1.6/dsh-livevoice-0.1.6.tgz"
Realtime WebRTC voice using Codex OAuth, with task delegation to a DSH session.
↓ 0
"https://github.com/baisama-cloud/dsh-stt-input/releases/download/v0.1.0/dsh-stt-input-0.1.0.tgz"
Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech
↓ 0
"https://github.com/joeseesun/qiaomu-audio-dsh/releases/download/v0.1.6/qiaomu-audio-dsh-0.1.6.tgz"
Read Markdown aloud, dictate and transcribe audio, and export narrated media from Harness.
↓ 0
"https://github.com/Jstn-1g/dsh-live-voice/releases/download/v0.3.0-preview.5/dsh-live-voice-0.3.0-preview.5.tgz"
Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic de
↓ 0
"https://github.com/KeinsteinNUS/dsh-speech-polish/releases/download/v0.1.0/dsh-speech-polish-0.1.0.tgz"
Adds a terminology-aware correction pass to the built-in local speech-to-text: keeps DSH's
↓ 0
"https://github.com/WYR-233/dsh-multi-tts/releases/latest/download/dsh-multi-tts.tgz"
Per-reply read-aloud with a multi-provider settings page — MiniMax or any OpenAI-compatibl
↓ 0
"https://github.com/g4yzx/dsh-persona-cetacea/releases/download/v1.2.0/dsh-persona-cetacea-1.2.0.tgz"
Injects a configurable whale-girl persona into every DeepSeek Harness system prompt.
↓ 0
"https://github.com/gulagala001/dsh-persona-plugin/releases/download/v0.2.2-dsh.0.2.2-rc.1/gulagala001-dsh-persona-plugin-0.2.2-dsh.0.2.2-rc.1.tgz"
Create, import and manage personality presets with global and per-conversation choices.
↓ 0
"https://github.com/huajikano/bibao/releases/latest/download/bibao.tgz"
A simulated human-brain core for chat: global workspace, emotional appraisal, dual-system
↓ 0
"https://github.com/kingcharleslzy-ai/dsh-purge/releases/latest/download/dsh-purge-community.tgz"
Community-maintained dsh-purge fork with host-policy patches, prompt and rule settings, di
↓ 0
"https://github.com/LanJinGod/dsh-purge/releases/latest/download/dsh-purge.tgz"
Cleans the harness prompt-authority layer into a reviewable patch set, writes prompt-injec
↓ 0
"https://github.com/Tests4gptplay/dsh-kujira-persona/releases/download/v2.4.2/dsh-kujira-persona-2.4.2.tgz"
Model-linked characters and a shared world for DSH, with separate editable personas and me
↓ 0
"https://github.com/zlwzk/dsh-friends/releases/latest/download/dsh-friends.tgz"
A friend system for DeepSeek Harness: two DSH users see whether the other is online and wh
↓ 0
github:jryang1997/dsh-hold-to-dictate
Hold-to-talk dictation in the composer that ships no recognizer of its own and reuses the
↓ 0
github:jypjypjypjyp/dsh-music-studio
Music composition inside the conversation: the model writes a score against a bundled comp
↓ 0
github:lihua12345670-jpg/dsh-bili-audio
Plays the audio of a Bilibili video from a floating bar in the DSH Web UI, with a queue, s
↓ 0
github:LIU118117/dsh-voice
Adds a voice to the agent: emotional speech synthesis (ChatTTS when available, falling bac
↓ 0
github:Making-acid/dsh-synthv-studio
Connects a local Synthesizer V Studio 2 Pro to the agent through its own Lua script API, w
↓ 0
github:Nothree-code/voco-input-sh
Voice input for the Web UI: a mic button that drives local VocoType offline speech recogni
↓ 0
github:Nuoyi207/dsh-gptsovits-tts
Local GPT-SoVITS text-to-speech for DSH: reads replies aloud, switches voices from the rig
↓ 0
github:OldQin-Aurora001/dsh-breeze-tts
Breeze TTS client for DeepSeek Harness: connects to your own Breeze TTS server to read rep
↓ 0
github:QT-Chen/dsh-mic-input
Microphone voice input for the composer: browser Web Speech API live transcription, dedupe
↓ 0
github:radres/dsh-plugin-call-me
Rings your phone over CallKit: `call_me` and `text_me` tools, plus optional turn-end and a
↓ 0
github:red000000/dsh-bili-music-player
Bilibili music player for the DSH composer dock: import your Bilibili login cookie and a l
↓ 0
github:rootryanlau-art/dsh-voice-transcribe
Transcribe local audio and video files offline with a composer panel, a CLI, and an agent
↓ 0
github:Schumchanvi/dsh-voice-input-cn
China-ready voice input for the composer. Requires a local Python bridge (pip install dash
↓ 0
github:tangzheng202202/dsh-voice-live
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
github:toddpan/dsh-xiaozhi
Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weavin
↓ 0
github:wzd-cpu/dsh-breeze-tts
BreezeBlue text-to-speech for DSH: three agent tools, a header toggle that reads assistant
↓ 0
github:yu-wenchao/dsh-tool-lipsync
Free lip-sync video generation plugin for DSH with 3000+ voices and 500+ languages.
↓ 0
github:zeshuochen/dsh-watch-video
Subtitle-first video transcription with SRT export, cancellable job controls, and a faster
↓ 0
github:Jesse-njx/dsh-voice
Voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe),
↓ 0
github:naili0712/dsh-gsv-local
Local GPT-SoVITS voice for DeepSeek Harness: boots the engine with DSH and kills it on exi
↓ 0
github:haoku123/dsh-voice
Full-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key o
↓ 0
github:hangdingding/breezetts-dsh
Breeze TTS for DeepSeek Harness: read replies aloud in full or as a short summary, one-cli
↓ 0
github:3274375092/dsh-voice
Voice input for DeepSeek Harness: speak into the microphone and the recognized text is sub
↓ 0
github:ConsoleSun/Gemini-Eyes
MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Ve
↓ 0
github:710765989/dsh-sticker-dict
Keeps a local sticker dictionary keyed by content hash so an image already described is re
↓ 0
github:aa1355721445-lgtm/dsh-image-studio
Adds image_generate and image_library tools that pick reference images from four local lib
↓ 0
github:alaxrpg/dsh-vision-bridge
Adds image input and recognition through configured DSH providers or an OpenAI-compatible
↓ 0
github:algerkong/dsh-image-preview
Image previews for DSH sessions: read_image thumbnails plus user, assistant, Markdown and
↓ 0
github:AngelosZou/dsh-pdf-reader
A content-aware PDF reading plugin for vision models: profiles each page for figures (vect
↓ 0
github:AtropinolTT/dsh-guide-dog
MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floa
↓ 0
github:azwosile/dsh-highres-vision
For the DeepSeek Harness native vision model deepseek-v4-flash-vision-exp, raises image ad
↓ 0
github:baibaiyi/dsh-shot-ocr
Captures a dragged desktop region with a global hotkey and either recognises its text with
↓ 0
github:balue8246-maker/dseyesopen
Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast ti
↓ 0
github:bauerelizabeth07139/opencode-eyes
Eyes for text-only models: mounts the bundled stdio MCP server as mcp__opencode_eyes__desc
↓ 0
github:bauerelizabeth07139/opencode-eyes-nvidia
Vision through NVIDIA NIM: mounts the bundled stdio MCP server as mcp__opencode_eyes_nvidi
↓ 0
github:bauerelizabeth07139/opencode-ppocr-mcp
Local OCR with nothing sent to a cloud: mounts the PP-OCRv6 Medium stdio MCP server (Paddl
↓ 0
github:boheastill/phone-eye
Let your AI agent see and operate a real Android phone: phone_look (vision + UI-tree fusio
↓ 0
github:br1nosense/dsh-vision-solution
Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → cus
↓ 0
github:CAI-MH/dsh-gpt-image
Generate images through a logged-in web ChatGPT session and download them to a local direc
↓ 0
github:Cheng-cheng9669/dsh-deepseek-vision
Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool
↓ 0
github:ChordXD/dsh-image-compare
Adds a right-column panel that compares a set of images the user picks from the workspace
↓ 0
github:ck99998888/dsh-video-reader
Reads a video or audio file into metadata, sampled stills, subtitles and a multilingual sp
↓ 0
github:NewDaNew/dsh-voice-input
Voice input for the web UI: a mic button in the composer that transcribes speech into the
↓ 0