Getting Started

This guide will walk you through setting up the Idun Agent Platform and deploying your first agent.

Time to complete: ~10–15 minutes.

Prerequisites

Before you begin, make sure you have the following installed:

• Python 3.12 - Required for running the agent platform Install Python
• Docker and Docker Compose - Required for running the platform containers. Steps to install Docker.
• Git - For cloning the repository
• uv - For Python package management. Steps to install uv

1. Clone the Repository

git clone https://github.com/Idun-Group/idun-agent-platform.git
cd idun-agent-platform

2. Copy env file

cp .env.example .env

3. Start the Platform

Tip

Make sure you start the Docker daemon before running the container

Launch the Docker containers:

docker compose -f docker-compose.dev.yml up --build

4. Access the platform

The manager UI will be available at http://localhost:3000

Login. If you didn't set up any login method yet, just press Login.

Congratulations

The Idun Agent Platform is ready to use! You can now start to plug in your agents and configure Observability, Memory, MCP, Guardrails, and production-grade APIs.

Next → Use an ADK agent

Next → Use a LangGraph agent

Next Steps

• Observability - Monitor your agent's performance and add checkpointing
• Memory - Add memory to your agents
• MCP - Give MCP tools to your agents
• Guardrails - Protect your agents with Guardrails
• A2A - Enable A2A (Agent-to-Agent) capabilities to your agents