🚀 MultiAgent Init

Interactive CLI for generating a clean multi-agent AI project.

Install

pip install multiagent-init

Run

multiagent-init

Wizard

The CLI asks for:

1. Project name
2. Framework
3. Model provider
4. Number of agents
5. Default or custom agents
6. Optional tools
7. Optional tests
8. Optional Docker

Example

🚀 MultiAgent Init

? Project name: research-team

? Select a framework:
❯ Basic
  LangGraph
  CrewAI
  AutoGen

? Select model provider:
❯ OpenAI
  Anthropic
  Google

? Number of agents:
❯ 3
  2
  4
  5
  Custom

? Agent configuration:
❯ Default agents
  Custom agents

? Agent 1 name: Market Researcher
? Agent 2 name: Data Analyst
? Agent 3 name: Report Writer

? Include tools? Yes
? Include tests? Yes
? Include Docker? No

Creating project...

✓ Agents
✓ Workflow
✓ Tools
✓ Configuration
✓ Tests
✓ README

🎉 Done!

Generated project

Custom agent names are converted into safe Python filenames and class names.

Example:

Market Researcher → market_researcher.py → MarketResearcherAgent
Data Analyst      → data_analyst.py      → DataAnalystAgent
Report Writer     → report_writer.py     → ReportWriterAgent

Development

python3 -m venv .venv
source .venv/bin/activate
python -m pip install -e .
python -m unittest discover -s tests -v

Build:

python -m pip install --upgrade build
python -m build

Publish

TestPyPI:

python -m pip install --upgrade twine
python -m twine upload --repository testpypi dist/*

PyPI:

python -m twine upload dist/*

For CI/CD, configure PyPI Trusted Publishing with GitHub Actions.

License

MIT