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.

[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

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

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

Near-native image understanding for DeepSeek Harness

DeepSeek Harness 外置视觉模型插件：inspect_image 把本地图片或 http(s) 图片 URL 发给任意 OpenAI 兼容端点，视觉模型看图的文字回答直接带回对话；附 Web UI 设置栏。

给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。

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）。

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

dsh 插件：给纯文本 DeepSeek 加视觉——view_image 工具桥接任意 OpenAI 兼容 VLM（默认智谱免费档，实测 4 厂商 10 模型）

Plug-in vision for text-only LLMs, powered by the free Antigravity CLI

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

MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness

Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。

Vision analysis CLI + MCP server backed by Seed 2.0 via Volcano Ark or any OpenAI-compatible endpoint

Context-as-image compression proxy for LLMs: renders bulky context (system prompt, tool docs, history) as dense PNG pages with exact per-provider billing math (Anthropic/OpenAI/Gemini). Node and Cloudflare Workers. Part of the OmniRoute family.

Recreate any web animation from a screen recording. A motion-design plugin: analyzes motion (timing, easing, stagger, loops) and rebuilds it as GSAP / CSS / Framer Motion / Lottie code.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

Agent Skills for end-to-end story writing in markdown, packaged as Codex and Claude Code plugins.

DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.

Workflow-continuity bridge for AI coding agents. Wrap Claude Code or Codex in a PTY and supervise, approve, and redirect the session from any device — async. The terminal companion for CodeAgent Mobile.