Multimodal Attachments
Give text-only OpenCode models multimodal attachment analysis through Gemini.
0
82
5 in 7 days
28.7
Multi-signal model
2 months ago
2026-08-19
Install and configure
opencode.jsonWrites to this project's opencode.json — applies to this repository only.
opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["@jsonzx/opencode-multimodal-attachments@0.1.4"]
}Writes to ~/.config/opencode/opencode.json — applies to every project.
~/.config/opencode/opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["@jsonzx/opencode-multimodal-attachments@0.1.4"]
}If you want to modify the plugin locally, install it into the project and reference the local path.
shell
pnpm add -D @jsonzx/opencode-multimodal-attachmentsOpenCode loads npm dependencies through its embedded runtime on startup and caches them locally — no manual global install needed.
No README provided
Missing documentation usually means the project is still early. Check the source repository for details.
Similar plugins
Vision Paste
opencode-vision-paste
OpenCode plugin: intercept pasted images → local VL API analysis → replace with text
Oc Media
oc-media
OpenCode plugin: teaches the native Read tool to ingest audio and video files, gated live by each model's real input modalities from models.dev.
Screenshot Vision
opencode-screenshot-vision
OpenCode plugin: let a text-only LLM read browser screenshots via local Ollama with OpenCode Zen fallback.