VibeChecks

Table of Contents

• Introduction
• Features
• Technologies
• Team
• Contributing
• Others

Introduction

VibeChecks is a lightweight python package that allows users to use natural language (LLMs) as part of their code logic. For example, VibeChecks can be used to check if/loop statements as well as provide responses for functions that are described but not implemented. It supports OpenAI and Google Gemini client currently and a simple example illustrating how it can be used can be seen below:

from google import genai
from vibechecks import VibeCheck

# initialize client
client = genai.Client(api_key=GEMINI_API_KEY)

# wrap it in VibeCheck
vc = VibeCheck(client, model="gemini-2.0-flash-lite")

# the example below asks user for a dog breed and checks if it is valid
user_input = input("Enter a dog breed:")
if vc(f"{user_input} is a valid dog breed"):
    print(f"{user_input} is a valid dog breed!")
else:
    print(f"{user_input} is not a valid dog breed!")

VibeChecks is published on pypi and can be easily installed with:

python3 -m pip install vibechecks

Details on the usage of the package and available APIs can be found on the wiki page.

Features

• Natural Language Conditions: Use natural language to check for conditions, making your code more readable and intuitive.
• Multi-provider Support: Seamlessly switch between different LLM providers. VibeChecks currently supports OpenAI and Google Gemini.
• Extensible: The modular design allows for easy extension to other LLM providers in the future.
• Custom Exceptions: Provides custom exceptions for better error handling and debugging.

Technologies

Technologies used by VibeChecks are as below:

Done with:

Python

Project Repository

https://github.com/vibe-engineers/vibechecks

Team

• Kong Le-Yi
• Tan Jin

Contributing

If you are looking to contribute to the project, you may find the Developer Guide useful.

In general, the forking workflow is encouraged and you may open a pull request with clear descriptions on the changes and what they are intended to do (enhancement, bug fixes etc). Alternatively, you may simply raise bugs or suggestions by opening an issue or raising it up on discord.

Note: Templates have been created for pull requests and issues to guide you in the process.

Others

For any questions regarding the implementation of the project, you may also reach out on discord.