npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

opencode-minimax-easy-vision-cli

v1.0.1

Published

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)

Readme

OpenCode Easy Vision

An OpenCode plugin that adds vision support to models that lack it — paste images directly into the chat and ask questions, just like you would with Claude or GPT.

Table of Contents

The Problem

Many models — open-weight ones especially — have no vision capability. They are text-only and simply cannot process image input. Pasting an image to them is useless — the model silently ignores it.

This plugin solves that. It intercepts pasted images, saves them to disk, runs a vision CLI tool (e.g., mmx vision describe) to analyze them, and injects the analysis results directly into the message. The model receives the image content as plain text — no extra tool calls needed.

Setup

For Humans

1. Install and authenticate the vision CLI

This plugin runs a local CLI command to analyze images. The default command is mmx vision describe --image from the mmx-cli package:

npm install -g mmx-cli
mmx auth login --api-key sk-xxxxx

You can also configure any CLI tool that reads an image path and outputs analysis to stdout.

2. Install the plugin

With the OpenCode CLI (v1.3.4+):

Global (all projects):

opencode plugin opencode-minimax-easy-vision-cli --global

Project-level (current directory only):

opencode plugin opencode-minimax-easy-vision-cli

Or manually, add it to the plugin array in your opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["opencode-minimax-easy-vision-cli"]
}

For LLM Agents

Paste this into OpenCode and let your agent handle the rest:

Set up opencode-minimax-easy-vision-cli by following https://raw.githubusercontent.com/devadathanmb/opencode-minimax-easy-vision/main/AGENT_SETUP.md

The agent follows the instructions in AGENT_SETUP.md. It will:

  1. Pre-fetch your existing config and the full configuration reference before asking anything
  2. Ask which models the plugin should activate for
  3. Ask which models the plugin should activate for
  4. Apply all changes — updating existing files in place rather than replacing them
  5. Walk you through verifying the setup after a restart

Usage

  1. Select a configured model in OpenCode.
  2. Paste an image (Cmd+V / Ctrl+V).
  3. Ask your question — just like you would with Claude or GPT.

Configuration

[!IMPORTANT] By default, this plugin only activates for MiniMax provider models — i.e. models where MiniMax is the direct provider in OpenCode (IDs matching minimax/*, minimax-cn/*, etc.). If you're using a different model, the plugin won't activate until you add that model's pattern to the models config — see CONFIGURATION.md.

Config files are loaded in priority order:

  1. Project level: .opencode/opencode-minimax-easy-vision-cli.json (or .jsonc)
  2. User level: ~/.config/opencode/opencode-minimax-easy-vision-cli.json (or .jsonc)

On first load, an example config is created at ~/.config/opencode/opencode-minimax-easy-vision-cli.jsonc with all options and inline comments. See CONFIGURATION.md for the full reference.

Supported Image Formats

PNG, JPEG, WebP — exact formats depend on the vision CLI tool you've configured.

Troubleshooting

Plugin not updating after a new release?

OpenCode caches plugins under ~/.cache/opencode/packages/. If it's still running an old version after a release, clear the cache entry and restart:

rm -rf ~/.cache/opencode/packages/opencode-minimax-easy-vision-cli@latest

Plugin not activating?

By default the plugin only fires for MiniMax provider models (IDs matching minimax/*, minimax-cn/*, etc.). To use the plugin with a different model or provider, add the model's ID pattern to models in your config — see CONFIGURATION.md.

Uninstallation

  1. Remove opencode-minimax-easy-vision-cli from the plugin array in your opencode.json file.

  2. Delete the config files the plugin created:

rm -f ~/.config/opencode/opencode-minimax-easy-vision-cli.{json,jsonc}

Contributing

See CONTRIBUTING.md for local development setup.

License

AGPL-3.0. See LICENSE.

References