agentinit
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.
Install
pip install agentinit
Usage
agentinit init my-project --framework langgraph --llm openai
Supported Frameworks
| 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 |
Supported LLM Providers
| 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 |
Generated Project Structure
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
Commands
Scaffold a new project
agentinit init <project-name> --framework <framework> --llm <provider>
Add a new agent to an existing project
cd my-project
agentinit add-agent researcher --framework langgraph
List all supported frameworks and providers
agentinit list-frameworks
Examples
# 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 bedrock
Getting Started After Scaffolding
cd my-project
cp .env.example .env # add your API keys
pip install -r requirements.txt
python main.py
License
MIT
Metadata
Release files for agentinit-cli 0.3.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentinit_cli-0.3.4.tar.gz | 9.3 kB | Without provenance | Details for agentinit_cli-0.3.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentinit_cli-0.3.4-py3-none-any.whl | Python 3 | none | any | Details for agentinit_cli-0.3.4-py3-none-any.whl |
Total release size: 27.8 kB
Release files / agentinit_cli-0.3.4.tar.gz
| Download URL | agentinit_cli-0.3.4.tar.gz |
|---|---|
| Size | 9.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e294812681c7f049fb802fec3cf0699c30dca83677efbaa63c9b24dd77991f1e
|
|
BLAKE2b-256 checksum How to use checksums |
78566ca77c72abf2ce2e7593f6c1df07f7c53700f3eb5882bd74ae921bbe0af3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Release files / agentinit_cli-0.3.4-py3-none-any.whl
| Download URL | agentinit_cli-0.3.4-py3-none-any.whl |
|---|---|
| Size | 18.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fbf74be8e82dc94bf8237f08d2a54c301c0f683db7005f66f20a4bd5a974961a
|
|
BLAKE2b-256 checksum How to use checksums |
1cb70e2b9852bd0aa6a7718855c4e2bcfa860ab08bab6f3baf13c6c4287717c7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Security for agentinit-cli 0.3.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.