Plugins
Browse, filter, and install DeepSeek-Harness plugins.
967 plugins found
dsh-mindseye
kanchengw/dsh-mindseye
Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, GUI automation, through layered evidence memory and cache.
dsh-tool-vision
gloryxpnv/dsh-tool-vision
Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.
dsh-plugin-mm-vision
elohia/dsh-plugin-mm-vision
Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.
dsh-vision-fallback
1helloman1/dsh-vision-fallback
Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.
beav-deepseek-harness
jamailar/beav-deepseek-harness
Connects DSH to local Beav for Xiaohongshu (RED/RedNote) and social-media AI operations: topic research, knowledge, copywriting, image, audio, and short-video workflows with approval and artifact tracking.
dsh-model-reasoning
tikaflow/dsh-model-reasoning
Auto-fills reasoning-effort levels, context windows, output limits and image modality for models from unofficial (custom) providers, with data from models.dev.
dsh-wallpaper-skin
ddbj-hub/dsh-wallpaper-skin
Persistent wallpaper skin for the dsh web profile: static image or muted looping video as the app background, with translucent panels and a floating picker panel.
multimodal-bridge
spirit4471/multimodal-bridge
DeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image) tools for text-only models
dsh-plugin-vision-toolkit
yytbit/dsh-plugin-vision-toolkit
Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images
dsh-yali-image-generator
pptt121212/dsh-yali-image-generator
DeepSeek-Harness 图像生成插件。申请 Yali AI API Key:https://api.yaliai.com/
dsh-skin
sakka6868/dsh-skin
DSH skin plugin: Alphacoders popular wallpapers as the DeepSeek Harness Web GUI background (gallery, search, local image upload, light/dark mask)
dsh-sight
fu3rte/dsh-sight
Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.
ez-dsh-memo
liudiw/ez-dsh-memo
A sticky-note wall for DeepSeek Harness: markdown notes, categories, reminders, wiki links, images, and fast-note-sync mirroring.
DSH_VCG
zymjason/dsh_vcg
Node-based image and video generation canvas for DeepSeek Harness: 16 built-in nodes and 5 example workflows, chat and project canvases, AI workflow building, cloud Model Studio image/video models, optional local ComfyUI, local safetensors weight inspection, trusted-source model downloads, and per-run token usage.
dsh-image-studio
shamanjin/dsh-image-studio
Image workbench for DSH: keep several OpenAI-compatible image services side by side, click a tile to make one active, fetch the model list from that service, and generate or edit images from chat. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-api-free-image
apfsds-dog/dsh-api-free-image
A DSH plugin that provides API-free image generation capabilities. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
novaflow-dsh-plugin
azheyc/novaflow-dsh-plugin
NovaFlow browser sign-in, native model configuration, personal and company balances, and image and video generation through a built-in MCP service.
dsh-skin-nier-automata
sunrayan/dsh-skin-nier-automata
A NieR-inspired theme with a graphite palette, ice-white type and a pure-CSS ruined skyline; it ships no artwork, and both wallpaper slots take images you upload yourself.
dsh-sidebar-shelves
yl404/dsh-sidebar-shelves
Two-line session cards for the sidebar: per-workspace project tiles (monogram, emoji, color or image), pinning, hand or timed archiving with a collapsible archived shelf, running and waiting status markers, per-session background-job and subagent counts, and newest-input-first sorting. Web GUI; requires DSH 0.2.1-rc.5 or later.
dsh-asset-library
isdou/dsh-asset-library
Local reference image library for DSH, allowing fast @keyword image search and attachment directly from the conversation input.
dsh-ask-aside
az-666316/dsh-ask-aside
Highlight text in an answer and ask about it in a right-sidebar session that inherits the conversation context, with streaming answers and image/file attachments. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-scheduled-message
intelfabs/dsh-scheduled-message
Schedule a message you are writing in the DSH composer — text, images and files — to be sent later; the Host delivers it after the tab closes, and a message that came due while DSH was closed is sent at the next start and marked late. Tick Repeat to create a DSH Automation task instead. A peak-price hint appears when a DeepSeek model is selected and the chosen time falls in its weekday peak window.
dsh-guofeng-studio
vamyane/dsh-guofeng-studio
Chinese-style songwriting studio for DeepSeek Harness: three bundled skills — a composer (mode and scale decisions, number-notation melody, pentatonic chords, arrangement table, three lint gates, multi-track MIDI), a lyricist (rhyme scheme, imagery, allusion control, structure, 14 lint rules, fill-in lyric slots), and a suite entry that connects both through .jp / .lyr / .slots.json files. The Python scripts use only the standard library and run fully locally.
dsh-dafeiyu-voice-chat
dennisyang1986/dsh-dafeiyu-voice-chat
Voice chat inside DeepSeek Harness: a draggable fish launcher records from the microphone, transcribes with DeepSeek speech recognition, answers with deepseek-flash (images included), and speaks each sentence through DeepSeek speech synthesis as the answer streams. Two voices, a continuous-conversation switch, and the API key stays on the Host.