convez.ai
AgenteAutomaçãoAvançado
peterzervas

CodeSynthAI

peterzervas/CodeSynthAI

Geração automatizada de código Python com sistema multi-agente

Ver no GitHub
InicialPluginScore · de 0 a 100

Agent de geração de código assistida por IA que utiliza um sistema multi-agente com LLMs para automatizar a criação de scripts Python. Combina modelos de linguagem com agentes colaborativos para explorar o potencial do desenvolvimento assistido por inteligência artificial.

Instalação

$npx convez-ai peterzervas/CodeSynthAI

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
3
Forks
0
Acompanhando
1
Saúde
42%
Último commit
há 2 anos
Versão
—
Issues abertas
0
Contribuidores
2

Casos de uso

  • Automatizar criação de scripts Python através de prompts em linguagem natural
  • Explorar arquiteturas multi-agente para resolução de problemas de codificação
  • Acelerar prototipagem e desenvolvimento de soluções programáticas

Veredito

Projeto experimental em fase inicial (WIP) que explora geração de código via multi-agent systems. Útil para pesquisa e prototipagem, mas requer revisão crítica antes de uso em produção — a qualidade do código gerado ainda é inconsistente.

README

A tradução para o português deste README ainda está na fila.

:notebook_with_decorative_cover: Table of Contents

:star2: About the Project

CodeSynthAI is an experimental proof-of-concept (POC) project that explores the potential of AI-assisted code generation using a multi-agent system. It aims to streamline the process of creating Python scripts by leveraging the power of Large Language Models (LLMs) and collaborative AI agents.

Project Status

Please note that CodeSynthAI is currently a work in progress (WIP) and is in its early stages of development. The project serves as an initial exploration of the concept and is not yet a fully-fledged solution. The code generated by CodeSynthAI may vary in quality and reliability, and it should be thoroughly reviewed and tested before being used in any production environment.

:camera: Screenshot(s)

:space_invader: Tech Stack

:dart: Features

  • AI-assisted Python script generation
  • Multi-agent collaboration for code refinement
  • Integration with OpenAI embeddings and Pinecone vector store
  • User-friendly Streamlit interface
  • Iterative development process

:key: Environment Variables

TBA

:toolbox: Getting Started

:bangbang: Prerequisites

  • Python 3.7+
  • OpenAI API key
  • Anthropic API key
  • Pinecone API key

:gear: Installation

  1. Clone the repository:
    git clone https://github.com/peterzervas/CodeSynthAI.git
    cd CodeSynthAI
    
  2. Clone the repository:
    pip install -r requirements.txt
    
  3. Set up the necessary API keys:
    OpenAI: Set the OPENAI_API_KEY environment variable.
    Anthropic: Set the ANTHROPIC_API_KEY environment variable.
    Pinecone: Set the PINECONE_API_KEY and PINECONE_ENVIRONMENT environment variables.
    

:running: Run Locally

  1. Start the Streamlit app
    streamlit run app.py
    or
    python -m streamlit run app.py
    

:eyes: Usage

Enter your script requirements in the text area provided in the Streamlit app. Click on "Generate Code" to initiate the code generation process. Review and confirm the refined requirements. Click on "Start Scripting" to begin the iterative scripting process. Provide feedback on the generated code by selecting "👍 Thumbs Up" or "👎 Thumbs Down" and click "Submit Feedback and Add to Vector Store" to store the code snippet and feedback.

:compass: Roadmap

  • Initial proof-of-concept release
  • Requirements
  • Expand support to other programming languages
  • Improve code quality and reliability
  • Integrate with version control systems
  • Explore more advanced AI techniques and models

:wave: Contributing

Made with contrib.rocks.

Contributions are always welcome!

See contributing.md for ways to get started.

:globe_with_meridians: License

Distributed under the MIT License. See LICENSE for more information.

:gem: Acknowledgements

Ver o original no GitHub

Bom para

Relacionados