Vision Multimodal
Give opencode native image, PDF and document analysis via any OpenAI-compatible multimodal API. Files are sent as-is; the API decides what it can read. No OCR, no conversion.
0
240
近 7 天 8
33.8
生态多维模型
21 天前
2026-09-13
快速安装与配置
opencode.json写入当前项目的 opencode.json，只对这个仓库生效。
opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["@we64/opencode-vision-multimodal@1.0.0"]
}写入 ~/.config/opencode/opencode.json，对所有项目生效。
~/.config/opencode/opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["@we64/opencode-vision-multimodal@1.0.0"]
}若你要在本地改造这个插件，先装到项目里再从本地路径引用。
shell
pnpm add -D @we64/opencode-vision-multimodalOpenCode 启动时会通过内嵌运行时自动加载 npm 依赖并缓存至本地目录，无需手动在全局环境执行安装。
该插件暂未提供 README 文档
缺少文档通常代表该项目仍在开发初期。建议前往其源码仓库查看详细实现。
同类生态推荐
Vision Paste
opencode-vision-paste
OpenCode plugin: intercept pasted images → local VL API analysis → replace with text
Easy Vision
opencode-easy-vision
OpenCode plugin that restores the paste-and-ask workflow for text-only models by saving pasted images and injecting MCP tool instructions
Minimax Easy Vision Cli
opencode-minimax-easy-vision-cli
OpenCode plugin that adds vision support for text-only models — paste images and the plugin analyzes them via a vision CLI tool (e.g., mmx vision describe)