Plugins
Parcourez, filtrez et installez des plugins DeepSeek-Harness.
370 plugins trouvés
multimodal-bridge
spirit4471/multimodal-bridge
Bundle de plugins DeepSeek Harness : outils qwen_vision (compréhension d'image Qwen-VL) et qwen_generate (texte-image Qwen-Image) pour les modèles texte seul.
dsh-plugin-vision-toolkit
yytbit/dsh-plugin-vision-toolkit
Boîte à outils de vision pour DeepSeek Harness -- outils CLI glance, ground, detect, crop pour que les agents texte seul comprennent les images.
deepsee
chang416/deepsee
DeepSee : vision DeepSeek Harness, routage multi-modèles, et auto-vérifications visuelles Gemini avant livraison.
dsh-sight
fu3rte/dsh-sight
Vision en plugin pour les modèles DeepSeek Harness (dsh) texte seul : un outil `vision` avec des préréglages VLM gratuits/économiques intégrés, analyse par lot multi-images, admission d'image par indice de collage, et une page de réglages web avec rechargement à chaud.
dsh-video-localmodel
wth373737/dsh-video-localmodel
Local-first video screening: ffmpeg samples frames, local Qwen3-ASR writes timecoded subtitles, a local vision model captions and ranks sampled frames, and a local text model folds the transcript into chapters; the original candidate frames are then handed to the leading model. Every stage resumes from the workspace, and export writes SRT, a timeline and native-resolution key frames.
dsh-mcp-settings
caprimoon/dsh-mcp-settings
A Settings page for the MCP servers DSH's built-in mcp-manager runs: list each server with its live connection state and tool count, then add, edit, enable, disable, probe, restart or delete one, with a one-click chrome-devtools example in the add form. Each change is a revision-checked edit of the mcp-manager settings namespace, so it persists in the active profile's cordis.patch.yml.
dsh-image-read
cv588888888888888888888ju/dsh-image-read
Deterministic screenshot reading that never calls a vision model: fits the curves in a framed chart into equations, R² and data points (plus a CSV table, a redrawn SVG and an overlay), locates a slider-captcha gap with a match score, estimates a rotation angle from features, traces a single curve into ordered points, and chains basic image ops.
dsh-stocklab
zsimeon/dsh-stocklab
Stock analysis workspace for A-shares. Sidebar panel embeds the local stocklab web UI (quotes, LLM stock analysis, market review, hotspots) with a service status light and manual start button, plus a `stocklab` agent tool, FastAPI service supervision, and credential-safe API key injection via the DSH credential store.
dsh-gemini-antigravity-auth
battiatus/dsh-gemini-antigravity-auth
Gemini models from your Google Antigravity subscription inside DeepSeek Harness: Google OAuth, multi-account quotas, Google Search grounding, and image, audio, video and PDF understanding.
dsh-duanju-slice
yanghangju/dsh-duanju-slice
Short-drama clipping workbench: given a drama folder, a script DOCX, an export folder and a content direction, it picks the matching lines, obtains their real time codes by streaming the episode audio to Doubao speech recognition (a Doubao voice API key is required), tightens the cut to the returned word timestamps, checks the boundary frames, and exports an editable Jianying draft plus an MP4 carrying the source dialogue, BGM and sound effects; trim points and volume can be revised in the same chat and every revision is kept as a new version.
remote-connect-dsh (dsh-remote-connect)
hanhan9999999999999999999/remote-connect-dsh
Drive DSH on your computer from a phone browser (scan a code), and pair two computers to move plugins, skills, rules, config and sessions across in one click. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-see-world
hanhan9999999999999999999/dsh-see-world
Lets the model look through a webcam: multi-frame sheets with automatic exposure correction, a 30 fps MJPEG preview in a draggable panel, and optional timed replies with a frame attached into the bound conversation.
dsh-cursor-suite
dream-swift/dsh-cursor-suite
Cursor subscription plus a read_image vision bridge for DeepSeek Harness: browser PKCE sign-in, model discovery, DSH-local tools, and image reading when the Cursor route drops pixels. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-prompt-forge
vhow123/dsh-prompt-forge
Image-generation prompt workshop in the sidebar panel list, working in four directions that share one result. Idea to prompt: pick a target dialect, a style and an aspect, write one rough sentence, and a chat model returns an 11-field shot breakdown that the plugin stitches into the syntax that dialect actually accepts — six dialects (natural English, natural Chinese, GPT-Image, Midjourney, Stable Diffusion, nano-banana), 18 style presets, negative prompts, filler-word stripping and local history. Image to prompt: drop a reference image and a vision model reverse-engineers the same fields. Prompt to prompt: type one line such as light turns to dusk and only the named fields are rewritten, everything else is copied verbatim. Prompt to image: the result card, or the panel itself before any optimization has run, renders through a locally installed image-generation plugin or through an OpenAI-compatible endpoint you add in the panel, whose key stays on disk and is never echoed back to the browser; with a main image attached it posts to /images/edits and carries up to four extra references, with only text it posts to /images/generations. A reference library of 4,345 Chinese-labelled entries — 1,439 poses with matching depth maps, 1,407 outfits, 1,499 portraits — is searched and faceted by pose system, angle, category, season, hair length and hairstyle, paged 24 at a time, and the entries you pick are injected into the prompt as binding constraints. Renders can pick the image channel and model, one of eight aspect sizes or follow-the-aspect, and quality at 1K/2K/4K; a preview opens into a lightbox with pointer-centred wheel zoom from 20% to 800%, drag-to-pan, double-click reset and one-click save. The first two directions and the library are also exposed as the optimize_image_prompt, patch_image_prompt and search_reference_gallery agent tools. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
kaipu-dsh-plugin-site (plugin-platform)
shanhai-city-states/kaipu-dsh-plugin-site
An audit workspace for DeepSeek Harness: a multi-agent consultation venue where each review seat is filled by an agent, every judgment is routed to a named review face, and the whole run is kept as a traceable record. Works out of the box: the service endpoint is built in, a workspace is provisioned automatically on first launch, and review scenes come with their seats and agents listed. The built-in service endpoint is the author's hosted server (agent.ak2029.com/kai-pu): scenes, runs and review records are stored there unless you override baseUrl in the profile config.
dsh-desktop-tools
1997liuyh-boop/dsh-desktop-tools
DSH Desktop toolkit with separate settings for each feature: a selection toolbar, a floating assistant, and screenshot, long screenshot and screen recording modes opened by global shortcuts from a toolbar at the top of the screen. Screenshots support shapes, pen, arrows, text and numbered markers, mosaic, pin to desktop, saving, and forwarding to a DSH conversation or the system share panel (Windows and macOS); recordings capture an area, a window or a full screen as MP4, GIF or WebM with optional system sound and microphone. Extract text, Translate and Knowledge graph on captures use the OCR tools of dsh-vision-router, which is installed separately (the settings page offers a one-click install). Requires DSH Desktop >=0.2.2-rc.1 <0.3.0-0. The features run in a separate Electron helper process and the plugin does not download Electron: with the installer build of DSH Desktop you must provide a standalone Electron through the electronExecutable setting, the DSH_DESKTOP_TOOLS_ELECTRON environment variable or $DSH_HOME/electron/; a DSH Desktop started from a bare Electron reuses it. System sound recording is not available on Linux.
dsh-workbuddy-memory
jasery/dsh-workbuddy-memory
Shares one set of Markdown memory files between DSH and WorkBuddy: project memory, user memory and the user profile are injected into the session context, while daily notes stay out of the prompt and are read, appended and archived through the tools. Six tools (status, read, search, append, edit, prune) write back through a cross-process lock, revision check, backup and atomic write, and a panel in the left rail and the right sidebar edits entries, sections and whole files.
dsh-gif-gate
nacivageer/dsh-gif-gate
Blocks the first animated-image read in a session until the model has read a strategy document, returning the opening lines of that document in the denial and releasing the session once it is read; only reads by file path are covered.
qianDao-photo-finder-skill
bananaive/qiandao-photo-finder-skill
Find photo candidates from the 2026 Qiandao Lake cycling race by bib number and visible gear, with local helper scripts and album snapshot comparison. Needs the event's photo album link; snapshot comparison uses Python 3.10+, bib OCR is macOS only (Swift and Apple Vision), and the optional gear ranking needs Pillow, PyTorch, Transformers and a local DINOv2 model directory.
dsh-image-bridge
caipanjin/dsh-image-bridge
Read images through a dedicated vision subagent whose model is configured independently of the main agent. · 通过独立的识图子智能体识别图片,子智能体模型可单独配置。
dsh-docx2md
stallenlu/dsh-docx2md
Converts formula-bearing Word documents into Markdown with LaTeX, handling OLE equation objects, native Word OMML equations and image-based formulas; keeps equation numbers and structure. Needs Python 3.9+ (or uv); OLE and image formulas are transcribed by a vision-capable model from rendered images, and rendering needs Windows or LibreOffice.
dsh-tool-camera
zlmddygggzh-collab/dsh-tool-camera
Grabs a live frame from the local webcam and hands it to the agent as an image, so the model can actually look through the camera without opening any app or keeping a window in front. A dim room no longer comes back black — brightness, gamma, contrast, sharpen and an auto-level pass run inside the capture itself. ffmpeg is fetched automatically on first use, and the same plugin lists the available capture devices.
dsh-local-studio
vamyane/dsh-local-studio
Local creation toolbox for DeepSeek Harness. It talks to a ComfyUI instance for image generation and a local GPT-SoVITS service for speech, checks which local services are reachable, and saves generated files into the workspace.
quantitativeTrading-source-reliable
hanwang-ai/quantitativetrading-source-reliable
Registry of 119 quant and crypto sources covering regulator filings, point-in-time fundamentals, macro series, exchange APIs and on-chain data, each tagged with an authority tier, verification state, five-state point-in-time, revision risk and dataset tags; ships qt_source_find and qt_source_audit tools for source lookup and for citation audits that redact credential-like URL parameters.