Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini,…
#vision
MCP servers, skills and plugins tagged “vision” on GitHub.
10 entries · real GitHub data
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
- #3Modlens
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). |…
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
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…
为 Claude Code 赋能多模态视觉能力,适配 纯文本 LLM 底座,用于截图 / UI / 图表分析;搭配 browser-harness 可做前端布局自动化检查。
Vision & image analysis skill for Claude Code & Codex. 帮不能看图的模型看懂图片和视频。
- #8Luma MCP
多模型视觉理解 MCP 服务器,为不支持图片理解的 AI 编码模型提供视觉能力:分析截图、报错、UI 与文档,可接入多家主流视觉大模型。Multi-model vision MCP server that adds image understanding to AI coding models without native vision —…
MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan)…
- #10MCP Vision
Claude Code + DeepSeek 等纯文本模型使用时,无法理解图片内容——截图里的报错、UI 设计稿、手绘架构图、文档扫描件,模型统统"看不见",通过 mcp vision 让模型拥有眼睛。