Plugin

Vision gratuita per agenti solo testuali: catena di vision integrata senza chiave, più strumenti pixel (Q&A, grounding, ritaglio, confronto pixel, colori, OCR, tracciamento SVG, ritaglio silhouette, screenshot); incolla un'immagine per usarla.

Attività visive per modelli solo testuali: Q&A su immagini consapevole dell'intento, OCR su screenshot lunghi, riproduzione UI, grounding e confronto pixel.

Plugin di vision esterno per DeepSeek Harness: pannello di configurazione con pulsante balena, riconoscimento immagini con risposta automatica e strumenti agente per screenshot/riconoscimento.

Ponte verso dispositivi HarmonyOS: ciclo di automazione hdc per screenshot/installazione/log/crash/UI con read_image, conoscenza dell'API versionata con priorità alle fonti ufficiali (SDK .d.ts + documentazione offline in bundle) e una pipeline DevEco CLI per build/firma/lint.

Ponte runtime DSH↔motore Godot: avvia e controlla un gioco Godot 4.x in esecuzione tramite il suo server di interazione TCP in-game — 8 strumenti (ispezione scena/UI, valutazione GDScript, simulazione input, screenshot, operazioni statiche headless, validazione degli script), sostituisce godot-mcp.

Funzionalità di browser reale condiviso per DeepSeek Harness: un browser visibile che l'utente umano osserva e può controllare, guidato dall'agente tramite CDP (snapshot/esecuzione/contenuto/gestione delle tab); interfaccia lato host, provider e strumenti browser_*

Agente GUI per Android con screenshot via ADB, grounding compatto della gerarchia UI, azioni iterative verificate, approvazioni e una vista 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.

Automazione del browser per DeepSeek Harness: strumenti open/click/type/screenshot/eval basati su Playwright, così l'agente può guidare pagine web reali

Plugin per DeepSeek Harness: strumenti di navigazione web (markdown / screenshot / pdf) basati su Cloudflare Browser Run — vero Chrome headless con rendering JS, sessioni di login e supporto 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.