Plugins

Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Plugin DSH: leva imagens e arquivos diretamente a modelos somente-texto — as imagens mantêm a experiência nativa de anexo, enquanto PDF/Office/compactados/vídeo/áudio aparecem como blocos na barra de anexos; ao enviar, são convertidos automaticamente em caminhos do workspace; combinado com o dsh-vision-toolkit, basta colar para ver a imagem. Um plugin DSH que entrega imagens E arquivos a modelos somente-texto como caminhos de workspace: as imagens mantêm a UI nativa de anexo, os demais arquivos aparecem como chips quadrados na barra, e os caminhos são anexados ao enviar — combina com o dsh-vision-toolkit.

Local OCR for DeepSeek Harness: paste/attach an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline. TUI (cc-tui) and Web. / DeepSeek Harness 本地 OCR 插件：图片转文字，PP-OCRv5 + ONNX Runtime，完全离线，支持 TUI 与 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

MiniMax multimodal bridge: one `mmx_bridge` tool covers image understanding/generation, video, TTS, music, cover, web search and quota; optional `web_search`/`read_image` takeover; inline players/image previews right in the Web GUI (npm: `dsh-mmx-bridge`).

DSH Web background settings: upload a local image or pick a preset ambiance, with live preview and persistent settings.

Skin plugin for the DSH Web UI: 4 built-in skins plus custom image skins with the photo as a full-interface background and the palette following its dominant hue.

Plugin de canal de texto e imagem para bots do QQ, integrado ao DeepSeek Harness

Always-on-top DeepSeek Harness desk pet with a native menu and DIY skins. Shows what your agent is doing: working, waiting, finished, failed. Five skins, or make your own from one image. No dependencies.

DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。

Workspace-safe Office tools for agents: create/read Word, create/read/update Excel, and create/read PowerPoint decks with PNG/JPG/GIF image placement.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floating dock UI), voice mode and mic voice input, plus image/video/music/speech generation and vision inspection tools.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Codex App Server model provider using a local Codex login, with session reuse, Harness tool bridging, native action traces, and durable generated-image projection.

Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.

Ponte de texto e imagem entre o WeCom AI Bot e o DeepSeek Harness

Plugin de visão DeepEye para o DeepSeek Harness (DSH): descrição de imagens, OCR, VQA, layout de UI e análise da área de transferência.

Envie imagens e arquivos locais para seu host de imagens usando a configuração já existente do PicGo (PicGo Cloud, GitHub, S3, COS, Qiniu ou qualquer plugin de upload instalado), por meio de uma ferramenta `picgo_upload` e do comando `/picgo`.

Bancada arrastável de mini-cards (saldo de API, uso de tokens, estatísticas de sessão, meta, custo) nas áreas em branco ao lado da conversa, com níveis de tamanho e preços oficiais da DeepSeek.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.

Gives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.