Plugins

88API Image Studio for DSH: four Image2 and Nano Banana models for text-to-image, multi-reference editing, 2K/4K output, and sequential batches.

GLM 视觉模型插件：注册 glm-vision 供应商路由（glm-4.6v 系列，image+text 输入声明）并提供 glm_vision 工具，让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。

Lightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.

vision_analyze tool: analyze a local image or URL with an OpenAI-compatible vision model.

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.

Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.

明眸 VisionBridge - Selbstentwickelte visuelle Brücke: Wenn ein blindes Modell Bilder empfängt, wird automatisch ein visuelles Modell zur Erkennung aufgerufen und der erkannte Text an das Hauptmodell zurückgegeben; nahtlos, konfigurierbar, verlustfrei bei Upgrades.

Deterministic aggregate media budgets and safe request projections for DeepSeek Harness (DSH)

Dynamic multimodal-to-text projection and cross-model vision bridge for DeepSeek Harness (dsh), allowing seamless hot-switching between vision models (Gemini/Claude) and text-only models (DeepSeek).

Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes

DeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.

DSH-native video understanding with configurable multimodal providers

Connects DeepSeek Harness to AsimovBox for creating, updating, rendering, and finishing videos through API-key-authenticated tools.

Plugin für visuelle UI/UX-Reviews im Unterhaltungsstil für DeepSeek Harness: Tools vision_review / vision_ask, gestützt auf jeden OpenAI-kompatiblen multimodalen Endpunkt (z. B. agnes-2.5-flash)