Plugins

Visão gratuita para agentes somente-texto: cadeia de visão integrada sem chave, além de ferramentas de pixel (perguntas e respostas, grounding, recorte, diff de pixels, cores, OCR, rastreamento SVG, recorte de objetos, capturas de tela); cole uma imagem para usar.

Tarefas de visão para modelos somente-texto: perguntas e respostas sobre imagens com reconhecimento de intenção, OCR de capturas de tela longas, reprodução de UI, grounding e diff de pixels.

Plugin de visão externa para o DeepSeek Harness: painel de configuração via botão da baleia, reconhecimento de imagens com resposta automática e ferramentas de captura de tela/reconhecimento para o agente.

Ponte para dispositivos HarmonyOS: loop de automação de captura de tela/instalação/log/crash/UI via hdc com read_image, conhecimento de API versionado priorizando fontes oficiais (SDK .d.ts + documentação offline embutida) e uma trilha de build/assinatura/lint via CLI do DevEco.

Ponte de runtime DSH↔Godot: inicie e controle um jogo Godot 4.x em execução por meio do seu servidor de interação TCP interno — 8 ferramentas (inspeção de cena/UI, avaliação de GDScript, simulação de entrada, capturas de tela, operações estáticas headless, validação de scripts), substitui o godot-mcp.

Capacidade de navegador real compartilhado para o DeepSeek Harness: um navegador visível que o humano observa e pode assumir, controlado pelo agente via CDP (snapshot/execute/content/gerenciamento de abas); interface do lado do host, provedor e ferramentas browser_*

Agent de GUI para Android com capturas de tela via ADB, grounding compacto da hierarquia de UI, ações iterativas verificadas, aprovações e uma visão Mobile Web.

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

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.

DeepSeek Harness plugin that turns UI screenshots into implementation-grade web specs using OCR, deterministic geometry, scene graphs, assets, and render comparison.

CloakBrowser-powered native browser tools with per-agent isolated sessions, bounded snapshots, ref-based interaction, screenshots, and safe routing.

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.

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.

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.

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).

Paper Design MCP bridge as a DeepSeek Harness bundle: paper_* tools, image screenshot support, design skills, OAuth auth, and Cursor-parity design guidance.

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.

Automação de navegador para o DeepSeek Harness: ferramentas open/click/type/screenshot/eval baseadas em Playwright, para que o agente possa controlar páginas web reais

Plugin do DeepSeek Harness: ferramentas de navegação web (markdown / captura de tela / pdf) baseadas no Cloudflare Browser Run — Chrome headless real com renderização JS, sessões de login e suporte a WebMCP

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.

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 plugin: launch the dsh-desktop Windows shell (region screenshot, tray, session manager) from the DSH conversation via a desktop_launch tool.

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.

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.