Quickstart
Welcome to the Eidolon Quickstart guide. This section covers environment setup, installing Eidolon, creating your first AgentProgram, and running an AgentMachine.
Setup Dev Environment
First let’s fork for Eidolon’s quickstart repository, clone it to your local machine, and start your server.
🚨 No gh
CLI? You can manually fork the quickstart repo and clone it locally.
If this was successful, you should see machine logs in your terminal.
You can also check out your machine’s swagger docs.
Believe it or not, you are already up and running with a simple agent! 🎉
What just happened?
The repository you just forked defines an AgentMachine 💻 with a single AgentProgram 🤖 named hello_world
👋.
The agent 🤖 is defined in a yaml file 📄 located at resources/hello_world_agent.yaml
.
This file describes how to instantiate your agent from its AgentTemplate 🏭 and describes any customization you might want (like a custom LLM. tools, etc).
Try it out
So, if I already have a server running, how do I interact with my agent?
Head over to another terminal where we will install a cli, create a new process, and then converse with our agent on that process.
Did your agent respond to you? If so, congratulations! You have successfully created your first agent machine.
⭐ Eidolon on GitHub if you found this useful. Eidolon is a fully open source project, and we love your support!
Next Steps
Now that you have a running agent machine with a simple agent. Let’s start customizing!
- Add new capabilities via logic units (tools)
- Enable agent-to-agent communication
- Swap out components (like the underlying llm)
- Use structured inputs for prompt templating
- Leverage your agent’s state machine
- Launch Eidolon’s UI