Skip to main content
If you’d rather start from working code than write an agent from scratch, the idun-agent-template repository has nine runnable examples you can clone and adapt. Each template is a self-contained folder with its own config, dependencies, and agent code. Pick the one closest to what you’re building and modify from there.

​
LangGraph templates

TemplateWhat it demonstrates
langgraph-simpleBasic two-step planning pattern. Good starting point
langgraph-tool-nodeTool calling with LangGraph’s built-in ToolNode (recommended pattern)
langgraph-toolManual tool invocation for cases where you need full control
langgraph-tool-localMixing local tools with MCP tools from the platform
langgraph-structuredSeparate input/output schemas with typed state
langgraph-editorial-loopMulti-step researcher/writer/reviewer workflow with conditional routing
langgraph-copy-pasteMinimal file operations example

​
ADK templates

TemplateWhat it demonstrates
adk-toolBasic LlmAgent with tool integration
adk-structuredStructured input/output with typed schemas

​
Get started

1

Clone the template repo

git clone https://github.com/Idun-Group/idun-agent-template.git
cd idun-agent-template
2

Pick a template

cd langgraph-tool-node
3

Install dependencies and configure

pip install -r requirements.txt
cp .env.example .env
# Edit .env with your API keys
4

Run standalone

idun web --port 8010
This runs the agent locally without the Manager. Good for testing your agent logic before connecting to the platform.
5

Connect to the platform

Once your agent works locally, connect it to the Manager for centralized management:
export IDUN_MANAGER_HOST=http://localhost:8000
export IDUN_AGENT_API_KEY=<your-api-key>
idun agent serve --source manager
The agent fetches its config from the platform. Guardrails, observability, memory, and MCP tools configured in the Manager UI are applied automatically.
Get your API key from the API Integration tab on the agent detail page in the Manager UI.

​
Which template should you pick?

  • First time with Idun? Start with langgraph-simple. It’s the shortest path to a running agent.
  • Need tool calling? Use langgraph-tool-node. It follows the recommended LangGraph pattern.
  • Want MCP tools from the platform AND local tools? Use langgraph-tool-local.
  • Building with Google ADK? Start with adk-tool.
  • Need typed input/output schemas? Look at langgraph-structured or adk-structured.
  • Building a multi-step workflow? The langgraph-editorial-loop shows a researcher/writer/reviewer pattern with conditional routing.

​
Templates vs. the quickstart

The quickstart walks you through the minimal steps to run an agent (a few lines of code). Templates give you more structure: proper project layout, config files, environment management, and patterns you’ll need as your agent grows. Both paths end at the same place: an agent connected to the platform.
Last modified on March 22, 2026