Documentation Index
Fetch the complete documentation index at: https://docs.run-agent.ai/llms.txt
Use this file to discover all available pages before exploring further.
Synopsis
runagent init [PROJECT_NAME] [OPTIONS]
Description
The init command creates a new RunAgent project with a pre-configured structure and optional template.
Options
| Option | Description | Default |
|---|
--framework, -f | AI framework to use | langgraph |
--template, -t | Project template | Based on framework |
--path, -p | Directory to create project in | Current directory |
--no-git | Skip git initialization | false |
Examples
Basic Usage
# Create a new project
runagent init my-agent
# Create with specific framework
runagent init my-agent --framework crewai
# Use a specific template
runagent init my-agent --template chatbot
Advanced Usage
# Create in specific directory
runagent init my-agent --path ~/projects
# Skip git initialization
runagent init my-agent --no-git
# Interactive mode
runagent init
Project Structure
The command creates:
my-agent/
├── agent.py # Main agent code
├── runagent.config.json # Configuration
├── requirements.txt # Dependencies
├── .env.example # Environment template
├── .gitignore # Git ignore rules
└── README.md # Project documentation
Templates
Available templates by framework:
problem-solver - Multi-step reasoningchatbot - Conversational agentresearcher - Web research agent
crew-basic - Simple crew setupresearch-crew - Research teamdev-crew - Development team
minimal - Bare minimum setupapi-agent - REST API integrationtool-agent - Multi-tool agent
Interactive Mode
When run without arguments, enters interactive mode:
$ runagent init
? Project name: my-awesome-agent
? Select framework:
❯ langgraph
crewai
agno
letta
custom
? Choose a template:
❯ problem-solver
chatbot
minimal
? Initialize git repository? (Y/n)
Post-Initialization
After creating a project:
cd my-agent
pip install -r requirements.txt
cp .env.example .env
# Edit .env with your API keys
runagent serve .
See Also
