Arcade Ai Agent

Arcade AI Agent with LangGraph

A comprehensive tutorial project demonstrating how to build production-ready AI agents using [Arcade AI](https://arcade.dev) for tool management and [LangGraph](https://langchain-ai.github.io/langgraph/) for agent orchestration and long term memory. This repository progressively builds from basic tool usage to a full-featured agent with memory, authentication, and a Streamlit interface.

🚀 Overview

This project showcases the integration of Arcade AI's powerful tool ecosystem with LangGraph's advanced agent framework. The agent has access to:

• Gmail Integration: Read, search, and manage emails
• Asana Integration: Access and manage tasks, projects, and team collaboration
• Long-term Memory: Persistent conversation memory using PostgreSQL
• Production Features: Authentication, session management, and robust error handling

The codebase follows a progressive learning approach, evolving from simple tool usage to enterprise-ready deployment patterns.

📋 Prerequisites

• Python 3.11+
• PostgreSQL database (for memory and checkpointing)
• OpenAI API key
• Arcade API key
• Gmail Account
• Asana Account

🛠️ Installation & Setup

1. Clone the Repository

git clone https://github.com/coleam00/arcade-ai-agent.git
cd arcade-ai-agent

2. Create Virtual Environment

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install Dependencies

pip install -r requirements.txt

4. Environment Configuration

Copy the example environment file and configure your API keys:

cp .env.example .env

Edit `.env` with your credentials:

# Get your Arcade API key: https://docs.arcade.dev/home/api-keys
ARCADE_API_KEY=your_arcade_api_key

# OpenAI API key from https://platform.openai.com/api-keys
OPENAI_API_KEY=your_openai_api_key

# Model selection
MODEL_CHOICE=gpt-4.1-mini

# Your email for tool authorization
EMAIL=your.email@example.