Design, Media & Vision

OCR、版面与语义结构化视觉证据

为纯文本 DSH Agent 提供 10 个结构化视觉工具：意图感知图片问答、长截图 OCR、原始像素 grounding、UI 还原、像素 diff 等

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

The DeepSeek Harness plugin for OpenPencil — preview, inspect, and edit real .op documents inside a conversation.

Near-native image understanding for DeepSeek Harness

Registers a view_image tool that bridges text-only DeepSeek to any OpenAI-compatible VLM endpoint for OCR, counting, chart reading and UI-layout questions.

为 DeepSeek Harness 增加外挂识图模型：圆形鲸鱼按钮配置面板、发送图片识图自动回传当前会话、为 agent 注入 screenshot/recognize_image 工具、多协议自动适配（可配地址/密钥/模型/提示词/代理）。

给 DSH 接入 DeepSeek 网页版原生多模态视觉：deepseek_vision/status/login/logout 4 个宿主级原生工具，宿主进程内 spawn visionary-server（Rust 单二进制：PoW→上传→fork→HIF 签名→SSE 流式），支持 CDP 浏览器自动登录；另有 vision CLI 与内嵌 skill。

DeepSeek brain + automatic image transcription — proxies attached images to a VLM (DashScope qwen by default) and feeds the transcribed text back to DeepSeek.

Provider-agnostic AIGC HTTP bridge + infinite canvas + ffmpeg post-processing (aigc_http_request, aigc_canvas_place, aigc_media_edit).

Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel

视觉插件/技能：让纯文本模型调 OpenAI 兼容识图 API 看图（描述/问答/OCR/多图对比），DSH 提供 vision_query 工具 + /image-vision 斜杠命令

Gives dsh image reading & generation: free GLM-based vision model route, paste-image reading, and vision-review / image-gen skills; keys read from env → ~/.dsh/secrets/media-tools.env → DSH credential store, never hardcoded.

MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Veo video generation, and conversation management using the logged-in browser session with no API key.

Collection of DSH plugins: image vision analysis (7 tools) and cross-session long-term memory, plus general skills.

Hosted free vision sidecar for DeepSeek Harness with durable session evidence

Adds eyes+paintbrush to DeepSeek: paste screenshots/images in-session, GLM vision model transcribes verbatim (errors/code/UI), DeepSeek continues; automatic text-to-image generation displayed in conversation; config under ~/.dsh/settings.yaml dsh-multimodal:.

Vision for DeepSeek Harness: Doubao Web by default (zero-cost, no API key), Antigravity IDE quota (flash/pro), any IDE CLI, Gemini — auto detail escalation, evidence memory

DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.

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.

让 AI 自动调用 VLM 分析图片：analyze_image 工具（主/备 OpenAI 兼容视觉端点，自动故障转移），设置页 Vision 管理，配置存 vlm-vision.json

Config-only DeepSeek Harness bundle for OpenAI-compatible vision models.

Qwen-MM 能力作为运行时拉取的 Agent Skills 与严格 MCP 工具服务器（core/video-memory/video-edit/blender/freecad/edu-agent）。

为 Agent 注册 `inspect_image`，调用兼容 OpenAI 的视觉模型

Vision-language gateway plugin for DeepSeek Harness - paste an image, DeepSeek sees text

Paste images into DeepSeek Harness with a four-model vision race, OCR, and an automatic text bridge.

Automatically generates and displays images in the DSH chat via API channels or local CLIs (supports mmx / codex / agy).

DeepSeek vision bridge for dsh: route image attachments to a vision model (Qwen3-VL via pi-ai/llama.cpp) and continue on a text-only LLM (DeepSeek)

本地化识图/OCR 技能插件：基于 macOS Vision Framework 的图片文字识别、表格结构提取与无文字图片描述，全本地无网络（中英文）；双形态：DSH Cordis 插件 + skill（SKILL.md，allowed-tools Bash）。

百度 ERNIE-Image-Turbo 文生图：宿主工具生成图片落盘并注册为会话附件，浏览器配置卡与生成画廊面板