AgentOp
Sign In Get Started

Getting Started

Learn how to create your first AI agent in minutes

Welcome to AgentOp

AgentOp is a platform for creating browser-executable AI agents using Python. This guide will walk you through creating your first agent, from account setup to deployment.

Prerequisites

Before you begin, you'll need:

  • A modern web browser (Chrome, Firefox, Safari, or Edge)
  • An AgentOp account (free to create)
  • Optional: API keys for OpenAI or Anthropic (if not using local models)

💡 No AI API keys needed to get started!

You can use local WebLLM models that run entirely in your browser without any API costs.

Step 1: Create an Account

Start by signing up for a free AgentOp account:

  1. Visit the signup page
  2. Enter your username, email, and password
  3. Click "Sign Up" to create your account
  4. You'll be automatically logged in

Step 2: Choose a Template

Templates provide starting points for your agents with pre-configured HTML, CSS, and example Python code:

  1. Navigate to Templates
  2. Browse available templates by category or search
  3. Click on a template to preview its interface and functionality
  4. Note the template's name - you'll select it when creating your agent

Popular Templates

  • Basic Chatbot: Simple conversational interface with message history
  • Data Analyst: Ask questions about data and get visualizations
  • Code Assistant: Help with programming tasks and debugging
  • Document Q&A: Upload documents and ask questions about them

Step 3: Create Your Agent

Now you're ready to create your first agent:

  1. Click Create Agent in the navigation menu
  2. Select a template from the grid
  3. The editor will load with the template's default Python code

Configure Your Agent

1. Choose an AI Provider

Select how your agent will generate responses:

  • OpenAI: GPT-3.5/GPT-4 models (requires API key)
  • Anthropic: Claude models (requires API key)
  • Local (WebLLM): Browser-based models (no API key needed, runs locally)

🚀 Recommended for beginners: Local (WebLLM)

Start with local models to test without API costs. You can switch to cloud providers later.

2. Customize the Python Code

The code editor shows your agent's logic. For your first agent, you can use the default code, but here's what you can customize:

  • System Prompt: Instructions that define your agent's personality and capabilities
  • User Prompt Template: How user messages are formatted before sending to the AI
  • Functions/Tools: Python functions your agent can call (e.g., search, calculate, fetch data)

3. Add Python Packages (Optional)

Need extra functionality? Add Python packages:

  • Pyodide Built-ins: Pre-compiled packages like numpy, pandas, matplotlib
  • PyPI Packages: Any package from PyPI (will be installed via micropip)

4. Configure Agent Metadata

  • Name: A descriptive name for your agent
  • Description: What your agent does (supports Markdown)
  • Tags: Categorize your agent for discovery
  • Visibility: Public (listed in marketplace) or Private
  • Allow Forks: Let others create copies of your agent

5. Submit

Click "Create Agent" to save. You'll be redirected to your agent's detail page.

Step 4: Download and Test

Your agent is generated as a standalone HTML file:

  1. On your agent's detail page, click "Download"
  2. If using OpenAI or Anthropic, you'll be prompted to encrypt your API key
  3. Save the HTML file to your computer
  4. Open the file in your browser
  5. Start chatting with your agent!

🔒 Security Note: API Keys

API keys are encrypted client-side before being embedded in the HTML file. For maximum security, use a separate API key with usage limits for each agent.

Testing Your Agent

When you open the HTML file:

  • Local WebLLM: The model will download on first run (may take a few minutes for 4-8GB models)
  • OpenAI/Anthropic: Enter your encryption password if prompted
  • Type a message and press Enter to chat
  • If your agent has functions, try triggering them with relevant requests

Step 5: Share or Deploy

Once your agent works, you have several options:

Share via Marketplace

  1. Edit your agent and set "Visibility" to Public
  2. Your agent will appear in the marketplace
  3. Others can discover, download, and fork your agent

Deploy the HTML File

  • Host on a website: Upload to your web server
  • GitHub Pages: Create a repository and enable Pages
  • Email distribution: Send the HTML file directly to users
  • Embed in applications: Include via iframe or as a component

Share the Agent URL

Each public agent has a detail page you can share: https://agentop.com/agents/your-agent-slug/

Next Steps

Now that you've created your first agent, explore more advanced features:

Agent Creation Guide

Deep dive into agent customization and Python code

Template System

Create your own reusable templates

Provider Configuration

Learn about OpenAI, Anthropic, and WebLLM setup

API Reference

Technical documentation for advanced users

Need Help?

If you run into issues:

  • Check the FAQ for common problems
  • Browse example agents in the marketplace
  • Fork working agents to learn from their code