A CLI tool to scaffold production-ready LLM agent projects in seconds.
Stop copy-pasting boilerplate. Run one command and get a fully structured, framework-specific agent project ready to run.
pip install agentinitagentinit init my-project --framework langgraph --llm openai| Framework | Description |
|---|---|
langgraph |
LangChain's graph-based agent framework |
crewai |
Multi-agent role-based framework |
autogen |
Microsoft's conversational agent framework |
google_adk |
Google's Agent Development Kit |
openai_agents |
OpenAI's official agents SDK |
smolagents |
HuggingFace's lightweight agent framework |
| Provider | Env Variable |
|---|---|
openai |
OPENAI_API_KEY |
anthropic |
ANTHROPIC_API_KEY |
groq |
GROQ_API_KEY |
azure |
AZURE_OPENAI_API_KEY + AZURE_OPENAI_ENDPOINT |
bedrock |
AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY |
gemini |
GOOGLE_API_KEY |
my-project/
├── agents/
│ └── base_agent.py # framework-specific agent logic
├── tools/
│ └── sample_tool.py # sample tool stub
├── config/
│ └── config.yaml # llm and project config
├── Dockerfile # ready to containerize
├── main.py # entry point
├── .env.example # environment variable template
└── requirements.txt # dependencies for chosen framework
agentinit init <project-name> --framework <framework> --llm <provider>cd my-project
agentinit add-agent researcher --framework langgraphagentinit list-frameworks# LangGraph with OpenAI
agentinit init my-agent --framework langgraph --llm openai
# CrewAI with Anthropic
agentinit init my-crew --framework crewai --llm anthropic
# AutoGen with Groq
agentinit init my-autogen --framework autogen --llm groq
# Google ADK with Gemini
agentinit init my-adk --framework google_adk --llm gemini
# OpenAI Agents SDK with Azure
agentinit init my-openai-agent --framework openai_agents --llm azure
# Smolagents with Bedrock
agentinit init my-smol --framework smolagents --llm bedrockcd my-project
cp .env.example .env # add your API keys
pip install -r requirements.txt
python main.pyMIT