limccn/deepseek-vl-support

Name: limccn/deepseek-vl-support
Author: limccn

Plugin ⭐ 1 MIT visual

Give DeepSeek (text-only) models **vision** in Claude Code and Codex by routing image files to any OpenAI-compatible vision endpoint (OpenRouter, SiliconFlow, DashScope, Ollama, llama.cpp, vLLM, LM Studio, …). Zero runtime dependencies, MIT licensed.

↗ View on GitHub 📄 Read full README

Install

Model (DeepSeek)  Read screenshot.png
  → this tool intercepts the read
  → picture → your vision service → detailed text description comes back
  → the model receives: "[Vision of screenshot.png]: <detailed description>"
  → the model continues from the description

Add limccn/deepseek-vl-support to your DSH config (web profile) to enable.

README

33.1 KB · Cached 2026-08-18 17:11:04 · 33.1 KB

Expand full README Collapse

README is empty.

Rendered from README.md of limccn/deepseek-vl-support. View original on GitHub →

Install

README

Related Plugins