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

agent-vision

v0.0.1

Published

Analyze images using AI vision (powered by Puter + Kimi K2.5)

Readme

Agent Vision CLI

A CLI tool for image analysis using AI vision, powered by Puter and Kimi K2.5.

Note: Kimi K2.5 is currently FREE on Puter for a limited time!

Installation

npm install -g agent-vision

Quick Start

# First, authenticate
agent-vision login

# Analyze an image
agent-vision analyze screenshot.png
agent-vision analyze photo.jpg "What objects are in this image?"

Commands

agent-vision login

Opens your browser to authenticate with Puter. Your token is stored securely in your config directory.

agent-vision logout

Removes your stored authentication token.

agent-vision analyze <image> [prompt]

Analyzes an image using AI vision.

Arguments:

  • image - Path to image file (png, jpg, jpeg, gif, webp)
  • prompt - Optional custom prompt (default: "Describe what you see in this image.")

Options:

  • -d, --debug - Enable debug output
  • -m, --model <model> - AI model to use (default: kimi-k2.5)

Environment Variables

  • PUTER_TOKEN - Set token directly for CI/CD or automation (skips stored token)

Examples

# Basic usage
agent-vision analyze screenshot.png

# Custom prompt
agent-vision analyze diagram.png "Explain this technical diagram"
agent-vision analyze photo.jpg "What objects are visible?"

# Debug mode
agent-vision analyze --debug photo.jpg

# CI/CD usage (no stored token needed)
PUTER_TOKEN=xxx agent-vision analyze image.png "Describe this"

For Agents & Automation

This tool outputs clean text responses suitable for programmatic consumption.

Error handling for automation:

When no token is configured, the CLI fails with a clear error message:

Error: No authentication token found.

To authenticate, run:
  agent-vision login

For CI/CD or automation, set the PUTER_TOKEN environment variable:
  PUTER_TOKEN=xxx agent-vision analyze image.png

Get your token from: https://puter.com

Token Storage

Tokens are stored in platform-appropriate config directories:

  • Linux: ~/.config/agent-vision/token (respects $XDG_CONFIG_HOME)
  • macOS: ~/Library/Application Support/agent-vision/token
  • Windows: %APPDATA%/agent-vision/token

Backend

Powered by:

  • Puter (https://puter.com) - Cloud platform providing the API
  • Kimi K2.5 - 1T parameter multimodal AI with MoonViT vision encoder

License

MIT