Plugins
Explora, filtra e instala plugins de DeepSeek-Harness.
27 plugins encontrados
dsh-vision-router
ysr666/dsh-vision-router
Visión gratuita para agentes de solo texto: cadena de visión integrada sin clave más herramientas de píxeles (preguntas y respuestas, grounding, recorte, diff de píxeles, colores, OCR, trazado SVG, recorte de figuras, capturas de pantalla); pega una imagen para usarla.
dsh-vision-toolkit
anionex/dsh-vision-toolkit
Tareas de visión para modelos de solo texto: preguntas y respuestas sobre imágenes con detección de intención, OCR de capturas largas, reproducción de UI, grounding y diff de píxeles.
dsh-vision
linenxi-ctrl/dsh-vision
Plugin de visión externo para DeepSeek Harness: panel de configuración con botón de ballena, reconocimiento de imágenes con respuesta automática, y herramientas de captura y reconocimiento para el agente.
dsh-hdc-bridge
1na-ko/dsh-hdc-bridge
Puente de dispositivos HarmonyOS: bucle de automatización de UI con hdc (capturas, instalación, logs, fallos) con read_image, conocimiento de API versionado priorizando lo oficial (SDK .d.ts + documentación sin conexión), y un carril de build/firma/lint con la CLI de DevEco.
godot-bridge
smalldy/godot-bridge
Puente de runtime entre DSH y Godot: controla un juego de Godot 4.x en ejecución vía su servidor TCP interno; 8 herramientas (inspección de escena/UI, evaluación de GDScript, simulación de entradas, capturas, operaciones headless, validación de scripts); sustituye a godot-mcp.
dsh-browser
wqty123/dsh-browser
Capacidad de navegador real compartido para DeepSeek Harness: un navegador visible que el humano observa y puede retomar, controlado por el agente vía CDP (snapshot/execute/content/gestión de pestañas); interfaz del lado del host, proveedor y herramientas browser_*
dsh-mobile-gui-agent
kunjinkao-os/dsh-mobile-gui-agent
Agente de GUI para Android con capturas de pantalla vía ADB, grounding compacto de la jerarquía de UI, acciones iterativas verificadas, aprobaciones y una vista Mobile Web.
dsh-vision-bridge
sfyyy/dsh-vision-bridge
On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model
dsh-pilot
guo6x/dsh-pilot
Zero-dependency browser control: drive a real headless Edge/Chrome over CDP with 8 `pilot_*` tools (navigate/click/type/keys/eval/screenshot) plus a live draggable cockpit panel in the Web GUI - text-first snapshots for text-only models, no Playwright, no API key.
dsh-ui-spec
yumimanji/dsh-ui-spec
DeepSeek Harness plugin that turns UI screenshots into implementation-grade web specs using OCR, deterministic geometry, scene graphs, assets, and render comparison.
dsh-cloak-browser
maxiaovivi/dsh-cloak-browser
CloakBrowser-powered native browser tools with per-agent isolated sessions, bounded snapshots, ref-based interaction, screenshots, and safe routing.
dsh-vision-mix
haiziyao/dsh-vision-mix
Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.
dsh-Kimi-WebBridge
microherox/dsh-kimi-webbridge
Drive the user's real browser through the local Kimi WebBridge daemon: navigate, find-tab, snapshot, click, fill, evaluate, CDP, screenshot, network, upload, PDF export and tab-management tools that reuse existing login sessions.
dsh-browser-control
kyo615/dsh-browser-control
Playwright MCP browser control for AI agents: drive a real, visible Chrome (navigate/click/type/snapshot + ~80 browser_* tools), with a live screenshot panel embedded in the GUI that refreshes after every action.
dsh-computer-use-win
yu-tao-li/dsh-computer-use-win
Windows computer use for DeepSeek Harness: an MCP stdio server over a PowerShell UIA backend exposing 22 desktop tools (UIA tree, screenshots, typed input, OCR, window management, failsafe).
dsh-paper-design
try-works/dsh-paper-design
Paper Design MCP bridge as a DeepSeek Harness bundle: paper_* tools, image screenshot support, design skills, OAuth auth, and Cursor-parity design guidance.
dsh-screenshot
paicat1/dsh-screenshot
Standalone screen capture for DeepSeek Harness (dsh). Browser hotkeys for instant capture plus an agent-facing capture and read tool that lets the agent see and analyze any screen region.
dsh-browser
ben7am1n/dsh-browser
Automatización de navegador para DeepSeek Harness: herramientas open/click/type/screenshot/eval impulsadas por Playwright para que el agente pueda manejar páginas web reales.
dsh-cloudflare-browser-run
realalexandreai/dsh-cloudflare-browser-run
Plugin de DeepSeek Harness: herramientas de navegación web (markdown / captura de pantalla / pdf) impulsadas por Cloudflare Browser Run, un Chrome headless real con renderizado de JS, sesiones de inicio de sesión y soporte de WebMCP.
gewu-tools
nyantused-cpun/gewu-tools
Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.
dsh-wechatmpdev
vincentjiang06/dsh-wechatmpdev
WeChat Mini Program automated testing for DeepSeek Harness (dsh): selector-addressed actions, build-freshness gates, geometry-first assertions that work on text-only models, and screenshot image blocks on vision routes. 微信小程序自动化测试 dsh 插件:选择器寻址、构建新鲜度门、面向纯文
dsh-desktop
reachga0/dsh-desktop
dsh plugin: launch the dsh-desktop Windows shell (region screenshot, tray, session manager) from the DSH conversation via a desktop_launch tool.
dsh-cdp-browser
zaiwenj/dsh-cdp-browser
CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.
dsh-preview
viger1/dsh-preview
Headless-browser verification tools so the agent opens the page it just built, reads the rendered DOM and computed styles, checks the console, and screenshots the result; ships a frontend-verify skill.