Categories › Models & AI
Models & AI
868 pluginsModel access, vision, voice, agents and personas — extending what DSH can do.
Sorted by downloads. 100 per page.
@liustack/modlenstested
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, lay
↓ 230.8k
@michengai/dsh-puatested
Adds /pua to steer the agent to try another approach and verify results before claiming co
↓ 75.5k
dsh-connect-workbuddytested
Connects locally signed-in WorkBuddy models, CN and international alike, to DSH, reading e
↓ 70.6k
dsh-vision-routertested
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, gro
↓ 47.5k
dsh-codex-subscriptiontested
ChatGPT OAuth provider for Codex models with subscription web search, quota and safe reset
↓ 30.5k
@furongjun1999/dsh-memorytested
White-box AGI architecture exploration: metacognition (self-cognition loop), continual lea
↓ 28.7k
dsh-thinking-levelsfails
Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it
↓ 26.8k
dsh-persona-dafeiyutested
Persona library for DeepSeek Harness: injects the selected persona into the system prompt,
↓ 23.2k
dsh-connect-traetested
Connects locally signed-in Trae CN models to DSH, supports DSH-executed tool calls, accoun
↓ 19.9k
dsh-video-storyboardtested
Turns a video (a local file, or a Bilibili/yt-dlp link) into one addressable storyboard gr
↓ 19.4k
@goodandready/dsh-subscriptionstested
Registers ChatGPT Codex, Claude, Grok and Antigravity subscriptions as DeepSeek Harness LL
↓ 16.7k
@anionex/dsh-vision-toolkitfails
Vision for text-only models: paste an image and the model switches to a Vision Toolkit var
↓ 14.2k
@opencode2dsh/dsh-plugintested
Exposes OpenCode Zen free models to DeepSeek Harness, with no API key.
↓ 13.9k
@mars-sea/dsh-commandcode-providertested
Unofficial Command Code LLM provider: registers a `commandcode` route with a live model ca
↓ 13.0k
dsh-feiyu-moodtested
Gives the companion a mood judged each turn and shown as a short context note, with a pane
↓ 13.0k
@dickpy/dsh-imagegentested
AI image generation for the DSH Web GUI: text-to-image and image-to-image through a config
↓ 12.0k
dsh-plugin-subscriptionstested
Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, wit
↓ 11.7k
dsh-agy-linktested
Google Antigravity (agy CLI) models for DSH — streaming chat with Gemini/Claude/GPT-OSS su
↓ 11.2k
@kenz1117/dsh-engramfails
Cross-session long-term memory as a local SQLite store: dual scopes (user + per-git-origin
↓ 10.4k
dsh-proactivetested
Host-level proactive wake-ups for DeepSeek Harness: the model schedules its own alarms (on
↓ 9.7k
@tnnevol/dsh-codex-authfails
ChatGPT account sign-in for DeepSeek Harness through a Codex browser OAuth flow with no AP
↓ 9.6k
@dmh2002/dsh-connect-qodertested
Connects Qoder (Lingma CN / international) models to DSH through their PATs, with a per-re
↓ 8.9k
dsh-voice-modetested
Full-duplex voice mode for the DeepSeek Harness Web UI: toggle (2s-pause auto-send) or hol
↓ 8.8k
@memef1f1y/dsh-plugin-ttstested
Reads assistant replies aloud via free Edge TTS or your own RVC voice models: read-aloud b
↓ 8.7k
@goodandready/dsh-key-rotationtested
Keeps a pool of API keys per provider with auto-created clone routes, switches to the next
↓ 8.7k
dsh-xiaomi-ttstested
Provides Xiaomi MiMo, Doubao, and browser-local TTS for DSH, with automatic read-aloud, cu
↓ 8.1k
dsh-voicetested
Voice tools: free edge-tts neural speech synthesis, OpenAI-compatible ASR transcription, v
↓ 7.8k
dsh-xdpooltested
Merge every locally signed-in WorkBuddy account into DeepSeek Harness as one auto-failing-
↓ 7.8k
dsh-deepseek-web-logintested
Adds a deepseek-web provider that uses chat.deepseek.com web models in DSH, with browser l
↓ 7.4k
dsh-codex-connectfails
Connect ChatGPT OAuth and OpenAI Codex models to DeepSeek Harness, with opt-in search and
↓ 7.4k
↓ 7.2k
@goodandready/dsh-voicetested
Voice input for the web UI: dictation chunked by pauses and voice messages, each with its
↓ 7.2k
dsh-image-viewertested
Upgrades DSH image viewing with pointer-centered zoom, pan, galleries, downloads, keyboard
↓ 7.0k
dsh-whale-lolitested
↓ 6.9k
@goodandready/dsh-ttstested
Speaks agent replies in the DeepSeek Harness web UI through a provider fallback chain (Ope
↓ 6.8k
@kanadego/dsh-heartbeattested
An agent that wakes up on its own schedule: by default every 60 minutes, ±20% (48–72). It
↓ 6.4k
dsh-plugin-chatgpttested
Signs in to a ChatGPT account over OAuth and serves that plan's models as a DeepSeek Harne
↓ 6.4k
clearai-dshtested
An agent preset for evidence-checked research: every step advances only through system-ver
↓ 6.4k
dsh-see-nowtested
Lets a text-only agent watch a live screen or camera feed: every frame is scored by how mu
↓ 6.4k
dsh-opencode-gotested
OpenCode Go provider with live gateway model discovery, online models.dev capability metad
↓ 6.2k
@ljwei-stak/dsh-model-routerfails
Routes DeepSeek Harness work across configured model APIs and supported vendor CLIs with d
↓ 6.2k
dsh-modeltested
One authenticated OpenAI-compatible endpoint (built on CLIProxyAPI) for dsh and other tool
↓ 6.2k
dsh-comfyuitested
Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object
↓ 6.1k
@q253595422/dsh-imagegen-videotested
AI image and video generation for the DSH Web GUI: text-to-image and image-to-image over p
↓ 6.0k
dsh-maoyingtested
Web-novel writing assistant preset for DeepSeek Harness: the main agent acts as editor-in-
↓ 5.9k
@goodandready/dsh-clinebottested
ClineBot and ClinePass integration for DeepSeek Harness: dedicated settings page, live quo
↓ 5.9k
dsh-model-think-leveltested
Thinking levels, image input and image generation for third-party models in the official M
↓ 5.7k
dsh-agent-personatested
↓ 5.5k
@stardustlc/dsh-dreamtested
Experience memory and reflection for DSH agents: automatically extracts candidate lessons
↓ 5.3k
@hytime/dsh-thinking-efforttested
Configure reasoning-effort levels and sub-agent defaults for custom DSH models.
↓ 5.2k
@istarry/dsh-assistant-profiletested
Agent persona: gives DSH one global persona (name, language, persona prompt) that every ne
↓ 5.2k
dsh-workbuddy-bridgetested
Brings WorkBuddy desktop-app models into DeepSeek Harness: the China and international bui
↓ 5.1k
dsh-gsv-ttstested
Real-time local TTS for DeepSeek Harness: voice presets, auto-read, engine setup assistant
↓ 4.9k
dsh-tts-bridgetested
Reads DSH conversations aloud using the DeepSeek web page's built-in read-aloud, driven by
↓ 4.9k
dsh-qoder-connecttested
Connects Qoder (China and Global) subscriptions to DSH through personal access tokens, kee
↓ 4.8k
dsh-image-pathifytested
Lets text-only models handle pasted chat images, with a native vision experience, batch im
↓ 4.8k
dsh-custom-modetested
Custom modes / assistant manager: give each mode its own system prompt in the settings pag
↓ 4.7k
dsh-oh-my-claudetested
Runs your logged-in Claude Code CLI as a dsh model provider: live model list, session resu
↓ 4.6k
dsh-watch-togethertested
Watch a video together with a text-only agent: with ffmpeg and the bundled browser extensi
↓ 4.4k
@goodandready/dsh-model-synctested
Synchronizes the model catalog of API-key providers from the provider itself instead of ma
↓ 4.4k
dsh-takotested
Adds Tako chat models to the official llm-pi-ai provider list from Tako's public catalog,
↓ 4.4k
@lujianjun19/dsh-llm-github-copilottested
GitHub Copilot LLM adapter: OAuth device-flow sign-in, live model discovery from the Copil
↓ 4.3k
dsh-talktested
Voice I/O for DeepSeek Harness — speech-to-text and text-to-speech over the microphone and
↓ 4.2k
dsh-tool-visiontested
Send local images or HTTP(S) image URLs to a configured OpenAI-compatible vision endpoint
↓ 4.0k
dsh-persona-switchertested
Switches the running session's persona and speaking style in place, via the composer's per
↓ 4.0k
whale-personatested
Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model,
↓ 4.0k
dsh-tool-antigravitytested
Connect Google Antigravity OAuth accounts to DeepSeek Harness with smart multi-account quo
↓ 3.9k
dsh-codeartstested
Connects Huawei Cloud CodeArts to DeepSeek Harness with built-in OAuth2 sign-in (PKCE + DP
↓ 3.9k
dsh-better-reasoning-efforttested
Per-model reasoning-effort and input-modality configuration for third-party providers: sug
↓ 3.8k
dsh-qwen-token-plan-cn-responsesfails
Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, w
↓ 3.8k
dsh-voice-chattested
Doubao-style voice chat for DSH: press-and-hold mic in the composer converts speech to tex
↓ 3.8k
dsh-voice-scribetested
Voice input for the DSH web UI: tap or hold Alt to dictate into the composer. Local SenseV
↓ 3.8k
dsh-local-aitested
Ollama provider for DeepSeek Harness with model management, health checks, rule-based loca
↓ 3.8k
dsh-agnes-studiotested
AI image and video studio as a floating DSH panel, so creation runs alongside the conversa
↓ 3.7k
dsh-earstested
Voice input plugin for DeepSeek Harness (dsh): a microphone button in the composer turns s
↓ 3.6k
dsh-drawtested
Multi-engine text-to-image generation (OpenAI Images and Zhipu CogView presets) with per-s
↓ 3.6k
@goodandready/dsh-vision-bridgetested
Routes images to a vision model of your choice - auto-rewrite, explicit tools, or hybrid -
↓ 3.6k
dsh-router-coretested
An AI routing gateway that runs as a DSH plugin. Adds a Routing System sidebar panel for s
↓ 3.6k
@eghrhegpe/dsh-connect-qodertested
Registers Qoder CN and international language models into DSH, fetching each model's rate
↓ 3.6k
@sunshaobei/dsh-codex-authtested
Manage Codex subscription (ChatGPT OAuth) authorization from the DSH settings panel, so Co
↓ 3.6k
↓ 3.5k
@dsh-plugins/dsh-llm-hubtested
Fills in what the official pi-ai adapter leaves out on the Models page: gateway reachabili
↓ 3.5k
dsh-fish-soultested
A single-character agent that lives across QQ (via SnowLuma / OneBot 11), Bilibili and Dou
↓ 3.4k
dsh-auto-model-routingtested
Use Jev to adjust main-chat reasoning effort without switching its model, independently se
↓ 3.4k
dsh-openrouter-providerstested
Route OpenRouter requests through a configured provider list and quantization cap, injecte
↓ 3.4k
dsh-llm-openai-completionsfails
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted
↓ 3.4k
@neptune810/dsh-model-routerfails
Keeps a pool of models and routes every agent step to one of them with its reasoning effor
↓ 3.4k
dsh-prompt-zhtested
Localizes known DSH system instructions and runtime reminders into Simplified Chinese, tri
↓ 3.4k
dsh-model-rotatortested
Ranks the models a DeepSeek Harness install already discovered by measured connectivity an
↓ 3.3k
dsh-connect-agnes-token-planfails
One-tap connect Agnes language, image and video models into DSH (off by default), with ima
↓ 3.3k
dsh-workbuddy2api-hubtested
Registers the models of a local workbuddy2api-hub gateway into DSH as one OpenAI-compatibl
↓ 3.3k
dsh-duettested
Full-duplex Chinese voice interaction for DSH Web: dictate and edit tasks, submit requests
↓ 3.3k
dsh-codebuddy-clitested
Reuses the CodeBuddy CLI sign-in to bring its models into DeepSeek Harness, with a setting
↓ 3.3k
muche-dsh-pluginfails
Chat panel for the MuChe companion with per-user backend settings, plus an outbound bridge
↓ 3.2k
dsh-read-animationfails
Reads animated GIF and WebP as animations: a pasted one keeps playing in the UI while the
↓ 3.2k
dsh-fish-ttstested
Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message re
↓ 3.2k
dsh-webdav-synctested
Syncs DSH model providers and models across computers through any WebDAV server: the backu
↓ 3.1k
dsh-speaktested
Zero-dependency, event-driven voice announcement plugin: no extra model, no token cost. Sp
↓ 3.1k
dsh-connect-sensenova-token-plantested
One-tap connect SenseNova Token Plan language and image models into DSH (off by default),
↓ 3.1k
dsh-magpie-connectortested
Connect a self-hosted Magpie gateway with one provider route per upstream owner, so the st
↓ 3.1k