Vision Analyst

Agent

Describes an image, lists objects, reads visible text, or writes alt text.

Agent = does one task.

Ready to UseVersion 1.0.0Published by @Mlaiel0 followers

Staff ran it and it worked. You still need your own provider accounts where listed.

🧪 Try it⬇️ Download

SHA-256: 4f124b071760afd782c7fdffd9cd4dc8a8cc72861b7bc6c689dfea1e43769bf0. Compare this with the file after you download it.

🔌 Integrate🧾 View source🔔 Sign in to get updates

You get an in-app notification when a new version is published. Nothing is installed or updated on your computer automatically.

What it does

Asks a vision model what it can see: a short description, a plain list of objects, the text that is actually visible, or one alt text. It does not identify people, estimate age, draw boxes, or report an accuracy percentage. Face recognition and the named detector weights are not in this package.

🧪 Try it on MLAIEL

Choose the model before you run. “MLAIEL key (OpenAI)” uses the platform key. Your own OpenAI key, Leonardo and Luma are yours: paste them for this request only. MLAIEL does not save them. Pollinations, when it is offered, is free and needs no key. Inputs and results are checked, nothing you send is stored, and you get 8 tries per day across all tools.

Sign in with a verified email to try this tool. Sign in

GitHub activity

mlaiel/iacherie
  • Stars: 2
  • Open issues: 0
  • Open pull requests: 0

Last checked: Nov 16, 2026, 5:15 AM

Public data from GitHub, checked once a day.

Who it's for

Apps that need a caption, a reading, or alt text for an image the user already has.

What it can do

  • Describe, objects, read, alt text
  • Says when text or objects are not visible
  • No face identity and no bounding boxes

What you need

  • Needs your own OpenAI account

    Put your key in a setting named OPENAI_API_KEY on your own computer. Never share it. Where to get a key

MLAIEL does not run these tools for you and never asks for your provider keys. You run them on your own computer or server, with your own accounts.

How to use it

Install

  1. Install Node.js 22.18 or newer.
  2. Download the 1.0.0 package and unzip it, then open the vision-analyst folder.
  3. Run: npm install && npm test (offline tests, no key needed).
  4. Copy .env.example to .env and add your own OpenAI key. Never commit .env.

Use

  1. node --env-file=.env examples/cli.ts describe photo.png
  2. Or use Try it and upload a PNG, JPEG or WebP.

⬇️ Download

Downloads come straight from the source repository. MLAIEL does not host files.

🔌 Integrate

Follow these steps in order. If you get stuck, ask in the improvement project.

Use as a library

import { readFileSync } from "node:fs";
import { analyze } from "./vision-analyst/src/index.ts";

const image = { bytes: readFileSync("photo.png"), mime: "image/png", filename: "photo.png" };
console.log((await analyze({ mode: "alt", image })).text);

Command line

node --env-file=.env examples/cli.ts

Works with

Node.js 22.18+ · Windows, macOS, Linux (tested on Windows 11)

License

License: MIT

MIT, declared by the owner: Fahed Mlaiel, who holds all rights to Mlaiel/iacherie, chose the MIT License for this clean TypeScript rewrite on 2026-10-01. The package ships the LICENSE file. This is not legal advice.

This is not legal advice. Check the license yourself before you use or share this tool.

Security check

  • No secrets found in the checked files.
  • No risky install commands found.
  • Checked on Oct 1, 2026

How it was tested

  • Run test · Passed

    Windows 11, Node.js, package 1.0.0, real OpenAI key, 2026-10-01 · Oct 1, 2026

    Describe mode returned 40 characters for a 1×1 PNG.

    • mode describe on a 1x1 PNG

Versions and changes

  • 1.0.0 · first release

    Oct 1, 2026 · source revision 54911be

    1.0.0 is a clean TypeScript rewrite of the stated iacherie job. BYOK OpenAI. Offline tests included.

    • First TypeScript package
    • Try it on MLAIEL

Updates are never applied silently. You decide if and when to download a new version.

Improvement team

Join the team

Source files: artifacts/configs/ai_agents_specifications.json

← Back to the marketplace