Skip to content

Artifact-Virtual/AGENTfoundry

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Agent Foundry

Python 3.10+ License: MIT Python 3.10+ Code style: black Type checking: mypy Testing: pytest Aider Ollama

An AI-powered code generation tool that converts natural language prompts into working codebases using multi-agent workflows and iterative refinement. In other words, this is a prompt-to-product, fully hands-off automation, from prototype working code. It is designed as a compliment to the newly introduced in-house production pipeline to help automate the iteration process to develop robust systems.

Features

  • Multi-agent optimization system (MAOS) for prompt engineering
  • Integration with Aider for AI-assisted code generation
  • Complete project structure generation with documentation
  • Support for multiple programming languages and frameworks
  • Automated testing and deployment preparation

Installation

git clone https://github.com/artifact-virtual/agent-foundry.git
cd agent-foundry
python3 -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate
pip install -r requirements.txt

Prerequisites

  • Python 3.10+
  • aider-chat
  • ollama (or compatible LLM service)

Quick Start

python cli.py --user demo --input "Create a REST API for task management"

Configuration

Set up your environment:

export OLLAMA_HOST="localhost:11434"  # If using Ollama locally

python cli.py --user [username] --input [file location] --enhanced

Project Structure

Generated projects include:

  • Source code with proper structure
  • Test files and configuration
  • Documentation and setup instructions
  • Deployment scripts when applicable

Contributing

See CONTRIBUTING.md for development guidelines.

License

MIT License - see LICENSE for details.

About

Agent Foundry is an AI-powered, prompt-to-product, code generation tool that converts natural language prompts into functional codebases using multi-agent workflows and iterative refinement.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages