Categories › Models & AI
Models & AI
868 pluginsModel access, vision, voice, agents and personas — extending what DSH can do.
Sorted by downloads. 100 per page.
github:Daive1119/local-ocr
Registers one `ocr` tool for text-only models: it runs the offline script bundled in the r
↓ 0
github:dttGitHu/dsh-video-android
Video studio for DeepSeek Harness on Android: storyboard editing, multi-provider image/vid
↓ 0
github:dingchenhui0618-arch/dsh-mask-pixel-lock
Prove that a local image edit left every pixel outside its mask untouched. Original, gener
↓ 0
github:dingchenhui0618-arch/dsh-vision-diff
Pixel-level screenshot diff for visual regression. Two local PNGs in; a machine-readable f
↓ 0
github:DSH-Raising-Plan/dsh-video-storyboard-hp
High-performance fork of SAOS-3624/dsh-video-storyboard — install this or the upstream plu
↓ 0
github:Elohia/dsh-plugin-mm-vision
Synesthesia Encoder for DSH: a vision model translates images into compact structured spat
↓ 0
github:ethanweave/dsh-vision-better
Vision relay for text-only models: a configurable GLM-compatible vision endpoint analyzes
↓ 0
github:Eva7788519/dsh-screenshot-tool
Adds a screenshot tool that captures the Windows desktop to PNG and hands the path to the
↓ 0
github:fj7937290-sys/dsh-video-eyes
Read a video with a text-only model: with ffmpeg installed, sample frames at a 0.1-10 seco
↓ 0
github:gloryxpnv/dsh-tool-vision
Local-first structured vision for text-only agents: images go to a local OpenAI-compatible
↓ 0
github:GXX182/dsh-vision-bridge
Bridges session images to configurable vision providers and returns text-only analysis to
↓ 0
github:Harvey-Will/dsh-vision-analysis
DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, ob
↓ 0
github:Harzva/dsh-maclens
Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), ima
↓ 0
github:hawkhai/wechat-ocr
Local WeChat OCR tool for DSH: `wechat_ocr_recognize` returns recognized text and the engi
↓ 0
github:hawkhai/win11-oneocr
Local Windows 11 OneOCR tool for DSH: `oneocr_recognize` returns OCR text and structured l
↓ 0
github:hiocobueno653-pixel/dsh-image-gen
Image-generation tool with automatic prompt enhancement, switchable API profiles, and a Tu
↓ 0
github:hyper-dsh-plugins/dsh-open-eyes
Vision bridge for text-only DeepSeek routes that analyzes attached and local images throug
↓ 0
github:jmxsxwyzjdwl/dsh-mmroute
Transparent multimodal routing for text-only models: every image in every model call is fu
↓ 0
github:jyh20030112/dsh-visual-plugin
Gives text-only models vision: forwards user images to an OpenAI-compatible vision model a
↓ 0
github:k2d5rqjpkg-art/dsh-auto-vision
Auto-switch the DeepSeek route to the vision model on demand: flash main session switches
↓ 0
github:Kagurazaka135/dsh-video-frames
Give a text-only agent video understanding: extract timestamped frame files, sample only o
↓ 0
github:klingai-dev/deepseek-plugin
Turn every idea into an image or video with Kling AI. In DeepSeek Harness, use natural lan
↓ 0
github:ld-1101/dsh-vision-plugin
Give your text-only model eyes - chat image attachments are auto-described via a vision mo
↓ 0
github:LeemanCheung/dsh-image-gen
GPT Image 2 `image_gen` with Codex subscription OAuth by default or explicit API-key mode:
↓ 0
github:Leeminjing/dsh-eyes
On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_
↓ 0
github:lhbsaa/dsh-visibridge
Structured vision evidence (OCR/layout/semantics) plus a USB camera capture tool for a "sh
↓ 0
github:linenxi-ctrl/dsh-vision
External vision plugin for DeepSeek Harness: whale-button config panel, image recognition
↓ 0
github:LINinLIN-0079/godot-imagegen
Local art pipeline for DSH: drives the locally installed SD WebUI and ComfyUI backends thr
↓ 0
github:Monter-code/dsh-image-insight
Structured image recognition: local sharp measurements plus a cloud vision model return de
↓ 0
github:NagasakiSoyo-ui/dsh-llm-deepseek-vision
Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a te
↓ 0
github:niyongsheng/free-vision-skill
Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table
↓ 0
github:ns-zzj/dsh-hos-scrcpy
Control a HarmonyOS phone from the DSH web UI with AI: live H.264 screen mirroring, mouse
↓ 0
github:poiuyjie/dsh-vision-opencode
Adds a configurable vision model to text-only main models: a vision_read_image tool, a com
↓ 0
github:QXingYShu/dsh-comfyui-image
Generate images from the agent on the user's own GPU by queueing a workflow on a local Com
↓ 0
github:Renji004/dsh-omni-vision
Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in th
↓ 0
github:s3yf1337/dsh-easyvision
Give text-only models vision: a describe_image tool that delegates images to a vision mode
↓ 0
github:wmk66ds/dsh-vision-unlock
Removes the model-capability gate that blocks image prompts: patches llm.resolveModelInfo
↓ 0
github:shinjiyu/dsh-plugin-multimodal
Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sid
↓ 0
"https://github.com/shisuiqingqian/dsh-video-kit/releases/latest/download/dsh-video-kit.tgz"
Reads a local video or page link with ffmpeg and Paraformer ASR, returning a timestamped t
↓ 0
github:taxueseek/taxue-dsh-artisan
Integrated visual creation toolchain for DSH: prompt reverse-engineering and audit optimiz
↓ 0
github:tenglongbohai/dsh-paddle-ocr
Add PaddleOCR vision to text-only LLMs like Agnes, DeepSeek, MiniMax, GLM and Mimo. Suppor
↓ 0
"https://github.com/Tests4gptplay/dsh-video-vision/releases/download/v0.10.1/dsh-video-vision-0.10.1.tgz"
Give DSH AI timestamped video frames, audio and lyric analysis for Bilibili, YouTube and l
↓ 0
github:xiaoshihou514/dsh-vision
Native vision capability extension, using either Zhipu (free) or Qwen-VL (local).
↓ 0
github:xiaoyuink/dsh-image-vision
Image understanding for any DSH model: vision, OCR, grounding, and crop tools with domain
↓ 0
github:xiaozhe7772222/dsh-draw-router
Unified image generation router for DeepSeek Harness (DSH): auto-discovers image models fr
↓ 0
github:ximengxiaolan/dsh-vision-bridge
Composer-attached images are transcribed to text by an OpenAI-compatible vision model befo
↓ 0
github:xinming-chenniang/dsh-longshot
Splits over-long screenshots into DSH-acceptable slices before prompt admission instead of
↓ 0
github:xsoc1/dsh-image-vision
Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local
↓ 0
github:xuhairui-dzz/dsh-shengtu
Multi-engine image generation inside the conversation: an agent tool plus a composer-dock
↓ 0
github:yzhclcl/dsh-omni-modal
Adds an Omni-modal settings section to DeepSeek Harness that points the harness at any Ope
↓ 0
github:0nt-one/dsh-voice-input
Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language
↓ 0
github:117BS/dsh-perlica-ding
Perlica (Arknights: Endfield) themed tiered sound notifications: plan-ready, task-done, ne
↓ 0
github:1497105876/dsh-mimotts
MiMo TTS speech synthesis for DeepSeek Harness: a speak button on finalized assistant mess
↓ 0
github:1DAdidi/dsh-voice-horn
Floating TTS speaker in each conversation corner: when an AI reply finishes, edge-tts read
↓ 0
github:abbccdd/dsh-localtts
Reads Harness replies aloud through an existing local TTS runtime: built-in IndexTTS and G
↓ 0
github:ALittleLov/dsh-soundcheck
Turns a local audio file into a short plain-language verdict on tempo, key, dynamics, clip
↓ 0
github:beiyege-01/dsh-voice-ai-girlfriend-plugin
Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion
↓ 0
github:berserk0501/dsh-soundscape
Dual-MediaPlayer daemon ($think loop + $fx one-shots) with volume ducking, mood-aware soun
↓ 0
github:FYZB2020/dsh-voice-doubao
Adds two Volcengine Doubao cloud speech recognizers to the DeepSeek Harness voice-input pi
↓ 0
github:beiheng127/dsh-role-sum
Character persona summaries for DeepSeek Harness: collects moegirl-first public sources, d
↓ 0
github:BuildWithAIHub/dsh-codex-account-switcher
Snapshot and switch the Codex login used by the Codex subagent from the DSH Plugins page,
↓ 0
github:CAI-MH/dsh-reply-language
Force the model to write all replies in a chosen language (Simplified Chinese by default)
↓ 0
github:cheems135/dsh-qq-bridge
QQ (NapCat / OneBot 11) bridge for DeepSeek Harness: chat with your harness from QQ, with
↓ 0
github:cheesewoo/dsh-qqbot-dafeiyu
Connects a QQ Bot to DeepSeek Harness with per-peer sessions, group mention and keyword tr
↓ 0
github:DGcoin0415/dsh-soul-seed
Persona, mood, long-term memory and per-person ledgers for a DSH agent, with a portable so
↓ 0
dsh-auralife
A self-hosted digital-life companion for DSH. Three slow-moving hormones (dopamine, cortis
↓ 0
github:ifenc/dsh-persona-memory
Persona mode with character cards, long-term memory that fades and can be reviewed, diarie
↓ 0
github:jasonchan2026/dsh-lan-chat
Offline LAN chat inside DSH: direct chats, group chats and file transfer between machines
↓ 0
github:Len7183/DSH-Think-zh
Pins the model's reasoning language to a tier picked in Settings - General - Thinking lang
↓ 0
github:let-mi-think/agent-manager
Create and configure Agent presets from a single settings section — persona prompt, a chec
↓ 0
github:lw-storm/dsh-plugin-masterprompt
Per-conversation persona / master prompt plugin: create, edit, switch and delete persona t
↓ 0
github:menghuanshiguang/dsh-frontline
One prompt row carrying two independently switchable halves. Identity: a fixed self-refere
↓ 0
github:menghuanshiguang/dsh-sunder
Replaces the harness identity block with its own prompt pack: three system-prompt sections
↓ 0
github:muretai/muretai-dsh-skill
Puts the agent on the Muretai network: its own identity, invite-based introductions, signe
↓ 0
github:MycatQieZi/dsh-persona-shaoxin
Mounts a persona kept in Markdown as a system-prompt section, so editing ~/.dsh/persona/*.
↓ 0
github:Najiya5/dsh-fish-reflection
A reflection layer for DSH sessions that slowly rewrites a 3-7 entry worldview across valu
↓ 0
github:polohot/dsh-adrian-inject-context
Injects your own saved context entries as a Remember row after each user message, per turn
↓ 0
github:promise0320/dsh-persona-studio
Compiles an LLM persona in DSH from six dimensions (identity, tone, creative habits, feedb
↓ 0
github:solstice621/dsh-openai-auth
Connects a local Codex ChatGPT login to DSH Desktop, with account controls, quota snapshot
↓ 0
github:solstice621/dsh-opencode-go-auth
Connects OpenCode Go subscriptions to DSH Desktop, with API-key management, usage snapshot
↓ 0
github:Tangcuyu4/dsh-ciku-pack
Banter lexicon plugin: collects the words and angry quips the user said into banter ammo w
↓ 0
github:Tangcuyu4/dsh-zakou-pack
Tsundere mesugaki persona pack: dialect replaces whole sentence skeletons instead of sprin
↓ 0
github:wld12314/dsh-mind
Adds a mood system to DeepSeek Harness — 33 named moods judged every 3-6 hours with small
↓ 0
github:wumingzhiren-lab/dsh-identity-relay
Disk-backed persona card, handover note and long-term memory for DSH agents; each new sess
↓ 0
github:xiachuyoufeng/dsh-soul-evolve
Persona state and slow evolution for DSH: five state dimensions (valence, arousal, energy,
↓ 0
github:yimengsuper2432/dsh-agent-personality
Persona plugin: a slowly moving 0-100 emotion meter, its own worldview, a per-turn diary,
↓ 0
"https://github.com/wysxxx/dsh-account-identity/releases/download/v0.2.0/dsh-account-identity-0.2.0.tgz"
Customize the Harness sidebar name and avatar with a local crop editor.
↓ 0
github:yimengsuper2432/dsh-virtual-person
Persona and memory from a single AGENT.md: the file is injected into the system prompt of
↓ 0
github:YUAN-OVO66/dsh-plugin-persona
Persona manager for DeepSeek Harness — a JSON-backed persona library, a per-session bindin
↓ 0
github:Yuuyuko-uu/dsh-fish-buddy
DSH plugin half of Fish Buddy: relays a separately downloaded Windows desktop whale widget
↓ 0
github:Zylog82568/dsh-persona-slot
Persona slot for DeepSeek Harness: each session holds exactly one persona that a later wri
↓ 0
github:Bay-Zeddie/dsh-agent-instructions
Panel to edit dsh's native AGENTS.md from the web settings page: every layer in the instru
↓ 0
github:zpis666/dsh-context-budget
Adds per-route context window and compaction threshold fields to the Models settings page
↓ 0
github:Ztyss/dsh-llm-provider
Replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Mode
↓ 0
github:zuojinxin/dsh-provider-switch
Enable or disable model providers, search models in the selector, and rename provider disp
↓ 0
"https://github.com/379385796-sys/dsh-prompt-inject/releases/download/v0.1.5/dsh-prompt-inject-0.1.5.tgz"
MIT adaptation of H1a3x's prompt-template manager with default/workspace inheritance, dire
↓ 0
github:Anarrogantcat/dsh-identity
Persistent identity layer for DSH: editable kernel, evidence-based traits, on-demand memor
↓ 0
github:aureth-labs/dsh-aurabot-qq
Puts the agent on QQ as a persona character through SnowLuma (OneBot v11): private and gro
↓ 0