Quick Start

This guide shows how to create and run your first AI agent with BindAI in just a few minutes. By the end of this guide, you will have:

Created an AI agent
Connected it to a language model
Sent your first prompt
Received a response

Before You Begin

Make sure you have completed the Installation guide. You will also need an API key for your chosen model provider. For OpenAI:

OPENAI_API_KEY=your_api_key_here

Create an Agent

Create a new file named main.py.

from bindai_agent import Agent


agent = Agent(
    provider="openai",
    model="gpt-4.1-mini",
    instructions="You are a helpful assistant.",
)

result = agent.chat(
    "What is BindAI?"
)

print(result.output)

Run the file.

python main.py

Example output:

BindAI is a modular Python framework for building AI agents, workflows, tools, memory, and production-ready AI applications.

What Happened?

The example performs four simple steps.

1. Create an Agent

agent = Agent(
    provider="openai",
    model="gpt-4.1-mini",
    instructions="You are a helpful assistant.",
)

This creates a new AI agent configured to use the OpenAI provider and the selected model. The instructions become the agent’s system prompt.

2. Send a Message

result = agent.chat(
    "What is BindAI?"
)

The chat() method sends your prompt to the configured language model.

3. Receive the Result

print(result.output)

The response returned by the model is available through result.output.

Loading an Agent from YAML

Instead of configuring agents in Python, BindAI also supports YAML configuration. Example:

name: assistant

provider: openai

model: gpt-4.1-mini

instructions: |
  You are a helpful assistant.

Load the agent.

from pathlib import Path

from bindai_agent import Agent


agent = Agent.from_yaml(
    Path("agent.yaml"),
)

result = agent.chat(
    "Hello!"
)

print(result.output)

YAML configuration makes it easier to manage agents without modifying application code.

Using Templates

BindAI includes ready-to-run templates demonstrating common patterns. Examples include:

Agent Basics
Workflow Basics
Conditions
Loops
Parallel Execution
Retry Policies
Scheduling

You can execute a template directly.

python templates/workflow-basic/main.py

Templates are the recommended way to learn the framework because every example is fully runnable.

Getting Started

Core

Tools

Memory

Knowledge

Workflows

Projects

Templates

API Reference

01.3 quick start

Quick Start

Before You Begin

Create an Agent

What Happened?

1. Create an Agent

2. Send a Message

3. Receive the Result

Loading an Agent from YAML

Using Templates

​Quick Start

​Before You Begin

​Create an Agent

​What Happened?

​1. Create an Agent

​2. Send a Message

​3. Receive the Result

​Loading an Agent from YAML

​Using Templates

Quick Start

Before You Begin

Create an Agent

What Happened?

1. Create an Agent

2. Send a Message

3. Receive the Result

Loading an Agent from YAML

Using Templates