create-agent
A CLI tool to quickly scaffold LLM agent API projects with an OpenAI-compatible interface.
Features
- Create a new agent project with a single command
- Includes ready-to-use API endpoints compatible with OpenAI's chat completion API
- Built-in RAG (Retrieval Augmented Generation) capabilities using LangGraph
- Support for custom tool definitions
- Complete FastAPI application structure
Installation
pip install create-agent
Usage
Create a new agent project:
create-agent my-agent
This will create a new directory called my-agent with all the necessary files to run an agent API.
Options
--template: Specify a template to use (default: "default")--output-dir: Specify the output directory (default: current directory)
create-agent my-agent --output-dir projects
Project Structure
The generated project follows a well-organized structure:
my-agent/
├── app/
│ ├── api/ # API definitions and models
│ ├── core/ # Core functionality
│ ├── rag/ # RAG implementation with LangGraph
│ ├── services/ # Business logic services
│ ├── utils/ # Utility functions
│ ├── config.py # Application configuration
│ └── main.py # FastAPI application
├── .env.example # Environment variables template
├── .gitignore # Git ignore file
├── README.md # Project documentation
└── requirements.txt # Dependencies
Next Steps After Creating a Project
-
Navigate to your new project directory:
cd my-agent
-
Create and activate a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install dependencies:
pip install -r requirements.txt
-
Set up your environment variables:
cp .env.example .env
-
Edit the
.envfile with your API keys and configuration -
Run the application:
uvicorn app.main:app --reload
License
MIT
Metadata
Release files for create-agent 0.0.3
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 |
|---|---|---|---|---|
| create_agent-0.0.3.tar.gz | 17.2 kB | Without provenance | Details for create_agent-0.0.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| create_agent-0.0.3-py3-none-any.whl | Python 3 | none | any | Details for create_agent-0.0.3-py3-none-any.whl |
Total release size: 39.0 kB
Release files / create_agent-0.0.3.tar.gz
| Download URL | create_agent-0.0.3.tar.gz |
|---|---|
| Size | 17.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5efd85ae28af3ffb835063965dfa7459d2b7eabd54f1c4da601b88bb8aa30fa1
|
|
BLAKE2b-256 checksum How to use checksums |
6584ff6006dfcfdff6b632c6e489aec1c91a643bb1cc9ea44892054779237943
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.11
|
Release files / create_agent-0.0.3-py3-none-any.whl
| Download URL | create_agent-0.0.3-py3-none-any.whl |
|---|---|
| Size | 21.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
33c8db46ebaff492dd4deb987dbe7ad85240db10dd777b4e7f119e2da3d1e163
|
|
BLAKE2b-256 checksum How to use checksums |
f4ebcc3938b236bc68497d3c8088b9216eb561d4fdca584b0f85c8221478e3b1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.11
|
Security for create-agent 0.0.3
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.