RunhuaHuang/VisionPower

give non-vision models the ability to see images by routing images to a vision capable model

A token-efficient, provider-agnostic vision layer for reasoning models via MCP.

Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a separate vision model through tools: look, OCR, scan, crop, compare. No training, no weights.

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.

给 DeepSeek 装上眼睛 — MCP Server + 通义千问VL, 剪贴板图片→视觉模型→文字描述 / Give DeepSeek the ability to see images via clipboard + Qwen-VL

OpenCode plugin that lets text-only models work with user-provided and tool-returned images by sending each image to a vision-capable model first, then replacing the image with a text description.

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 — analyze screenshots, errors, UI and documents via major vision LLM providers.

Near-native image understanding for DeepSeek Harness