Agent with Vision

Agent with Vision

Create agents capable of processing and analyzing images.

Quick Start

Clone the Complete Example

The easiest way to get started is to clone the complete example repository:

git clone https://github.com/astreus-ai/agent-with-vision
cd agent-with-vision
npm install

Or Install Package Only

If you prefer to build from scratch:

npm install @astreus-ai/astreus

Environment Setup

# .env
# Vision-capable model API key
OPENAI_API_KEY=sk-your-openai-api-key-here

# Database for agent persistence
DB_URL=sqlite://./astreus.db

Vision Agent

import { Agent } from '@astreus-ai/astreus';

const agent = await Agent.create({
  name: 'VisionBot',
  model: 'gpt-4o',
  visionModel: 'gpt-4o',
  vision: true,
  systemPrompt: 'You can analyze and describe images in detail.'
});

// Analyze an image
const result = await agent.ask("Analyze this image and describe what you see", {
  attachments: [{
    type: 'image',
    path: './screenshot.png'
  }]
});

console.log(result); // Detailed image analysis

Running the Example

If you cloned the repository:

npm run dev

Repository

The complete example is available on GitHub: astreus-ai/agent-with-vision

Last updated: September 10, 2025