Plugins

Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.

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

Ambient UI for DeepSeek Harness Web: a glassmorphism balance/token floating widget plus a pixel-art agent-trail animation.

DeepSeek Harness out-of-tree plugin: give a text-only coding model eyes by routing images to a Qwen-VL (DashScope) route through ctx.llm and returning text.

Cost tracking plugin for the DeepSeek Harness Web GUI — snapshot-anchored per-turn pricing, account balance, and live cost estimates.

Custom background (images / GIFs / animated wallpapers) plugin for the DeepSeek Harness (DSH) Web GUI: an enable switch plus a local asset library, with separate display mechanisms for the official theme and skin-center skins.

Adds a produced-files card row to the chat and a resizable split-screen preview panel for workspace artifacts (Markdown, source code, CSV, JSON, images, HTML), plus a localhost port preview.

Aseprite-style pixel art studio: the AI draws sprites stroke by stroke with selections, layers, animation frames, gradients, symmetry and reference layers, each step rendered live as ANSI terminal frames.

Prompt mínimo x capacidades PTC web: persona de una línea, SDK run_code, subagentes, Ralph, búsqueda/obtención web y Git Bash de Windows; la herramienta de flujo general permanece oculta.

Task-to-skill pairing meta-skill with a laziness ladder for minimal loading, a user-editable routing table, and a quarantine, SkillSpector scan, human-approval install flow.

Registers the remove-pdf-background-gray skill for DSH: whitens gray/off-white scan backgrounds in image-based PDFs while preserving resolution, page geometry, and anti-aliased text edges (lossless Flate write-back), via a single Python script (pypdf + Pillow + numpy).

Puente de adjuntos de imágenes en el chat con una herramienta view_image para cualquier VLM compatible con OpenAI (Ollama local o nube): las imágenes pegadas/arrastradas se convierten en marcadores de ruta view_image antes de llegar a los modelos DeepSeek de solo texto.

`describe_image` tool: a vision bridge that sends images to mimo-v2.5 through the opencode Zen API (credential `OPENCODE_GO_API_KEY`, free route first with paid fallback) and returns text descriptions for text-only models, with native passthrough and ImageMagick transcoding of SVG/TIFF/HEIC formats.

Herramienta image_describe (识图) orientada al modelo sobre la API compatible con OpenAI de DashScope (qwen3.7-flash), más un puente de pegado: en sesiones solo texto, las imágenes pegadas se convierten automáticamente en rutas de archivo al enviar y se vuelven a renderizar en la transcripción, para que nunca tropiecen con la admisión de imágenes. Trae tu propia DASHSCOPE_API_KEY; endpoint/modelo/presupuestos configurables, cliente HTTP a prueba de redirecciones y funciona en todos los agent presets.

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.

Auto-discovery vision bridge for text-only DeepSeek Harness agents: automatically finds an image-capable model from your configured providers and returns picture descriptions as plain text via a vision tool.

Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.

On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).

Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, GUI automation, through layered evidence memory and cache.

Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.

Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.

Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

Connects DSH to local Beav for Xiaohongshu (RED/RedNote) and social-media AI operations: topic research, knowledge, copywriting, image, audio, and short-video workflows with approval and artifact tracking.