Replacement of bash "column".

Fully-local OCR CLI for text-only LLMs: PaddleOCR-VL first-tier engine with tesseract fallback, dsh plugin included

Local MCP bridge for fixed Qwen3-VL-Plus visual image analysis

Multi-model vision understanding MCP server. Supports GLM-4.6V (Zhipu), DeepSeek-OCR (SiliconFlow - Free), Qwen3-VL-Flash (Aliyun), and Doubao-Seed-1.6 (Volcengine)

Optimized version of OpenAI Codex for side-by-side installs, loop-driven workflows, and Vivling companions

Airship bridge to other libs (CARTO VL, CARTO.js)

Multi-model vision MCP server (GLM-4.6V, Kimi, Qwen-VL, GPT-4o) that lets text-only coding models in Claude Code see and understand images.

Official Baidu Cloud and self-hosted PaddleOCR-VL document converter plugin for XpertAI.

Reranker nodes for n8n - Custom rerank API (recommended), VL Classifier, Ollama Generate (experimental). Vector Store provider + workflow node.

DeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image and image editing) tools for text-only models

A React binding of CARTO VL

Pi Agent extension that adds a describe_image tool, letting non-multimodal models delegate image analysis to a vision-capable model (like Qwen VL)

Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.

Multi-provider vision MCP server for image recognition (OCR, scene description, chart extraction). Supports Qwen-VL, OpenAI, Gemini, Claude, OpenRouter, Ollama and any OpenAI-compatible endpoint.

Out-of-tree dsh provider plugin: a DeepSeek gateway route that claims image input and transparently describes pasted images through a configured vision-language model (e.g. Qwen-VL) before the text-only DeepSeek wire sees them.

OCR 工具:RapidOCR + PaddleOCR-VL,为 dsh-image-text-fallback 提供图片识别能力

vue-layer修复版vl-layer，一款好用的vue弹窗组件，layui-layer弹窗风格

DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.

vl-mongo

Local MLX vision for text-only models on Apple Silicon Macs: a describe_image tool backed by LiquidAI LFM2.5-VL-3B-MLX-8bit, so non-vision models (DeepSeek, etc.) can see images.