The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deployed endpoint in a single command, no API glue code.

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

把本机 Wallpaper Engine 的壁纸变成 DSH 网页界面的背景：Video 动态播放、Web 以 iframe 加载、Scene 壁纸提取主纹理作为静态帧；iOS 液态玻璃设置窗口（配色 / 玻璃颜色 / 透明度）、内容分级与类型过滤、自定义壁纸上传、紧凑 CD 架布局、黑胶唱片展示、隐藏 / 恢复、倍速 / 翻转与自动轮播。感谢 Jerry 维护 macOS 版。

DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text before delegating to the text-only DeepSeek adapter. Official deepseek-v4-flash-vision-exp by default (a pure-te

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Wallpaper Engine library as the DSH web GUI background — video/web/still wallpapers, rotation lists, search, resource monitor, bilingual UI.

Turn one sentence into finished ads: video ads, UGC, product photos, voiceover, brand kits, A/B.

Create and track AI music videos and audio-reactive visuals from songs.

Provides a local stdio MCP server for controlling YouTube Music through the CLI, enabling playback, search, queue management, and library access via MCP-compatible clients.

Enables searching the Whitney Museum's public API for artworks, artists, exhibitions, events, and audio guides from any MCP client.

Text-to-speech plugin for Claude Code — multi-provider support (ElevenLabs, OpenAI, Google, Amazon Polly, Azure, Kitten, local system TTS) on macOS, Linux, and Windows

A collection of open-source Agent Skills for content creation — images, audio, and video.

Turn footage into finished video: content-aware reframing, captions behind the subject, graphics.

Filtrix MCP for image/video generation. Portal: https://agent.filtrix.ai/

Node-based AI design workflows on the Gemus canvas: generate images, video, 3D, and PPT.

Personalized hypnosis audio sessions for sleep, focus, confidence, and mental rehearsal.