Skip to content

OSS AI supervisor Agent, for AI lifecycle. πŸ¦Έβ€β™€οΈIntelligent E2E oversight & compliance for trustworthy AI.

License

Notifications You must be signed in to change notification settings

ContrastoAI/cartai

Repository files navigation

🌟 Cartai β€” The AI PM, for AI 🌟

Crafting intelligent E2E supervision & documentation for trustworthy AI

πŸ‘©β€πŸ’Ό Agent-powered project intelligence, from PRD to production

PyPI version Build Status GitHub Repo stars License


cartai is a library that enables end-to-end traceability and lineage of your AI projects. PRDs, data lineage, training experiments, deployments, monitoring, and third-party vibe-coding platforms.

πŸ“‚ Codebase Structure

  πŸ“ cartai/
    β”œβ”€β”€ πŸ“„ __init__.py
    β”œβ”€β”€ πŸ“ adapters/
    β”œβ”€β”€ πŸ“ cli/
    β”‚   β”œβ”€β”€ πŸ“ commands/
    β”‚   β”‚   β”œβ”€β”€ πŸ“„ __init__.py
    β”‚   β”‚   β”œβ”€β”€ πŸ“„ pr_diff.py
    β”‚   β”‚   └── πŸ“„ readme.py
    β”‚   └── πŸ“„ main.py
    β”œβ”€β”€ πŸ“ core/
    β”‚   β”œβ”€β”€ πŸ“„ __init__.py
    β”‚   └── πŸ“„ code_parser.py
    β”œβ”€β”€ πŸ“ lineage/
    β”œβ”€β”€ πŸ“ llm_agents/
    β”‚   β”œβ”€β”€ πŸ“„ __init__.py
    β”‚   β”œβ”€β”€ πŸ“„ documenter.py
    β”‚   β”œβ”€β”€ πŸ“„ graph.py
    β”‚   β”œβ”€β”€ πŸ“„ graph_states.py
    β”‚   β”œβ”€β”€ πŸ“ templates/
    β”‚   β”‚   β”œβ”€β”€ πŸ“„ pr_diff.jinja
    β”‚   β”‚   └── πŸ“„ readme.jinja
    β”‚   └── πŸ“ utils/
    β”‚       β”œβ”€β”€ πŸ“„ __init__.py
    β”‚       β”œβ”€β”€ πŸ“„ model_client_utils.py
    β”‚       └── πŸ“„ yaml_utils.py
    └── πŸ“ langgraph_config/
        β”œβ”€β”€ πŸ“„ dummy_config.yaml
        └── πŸ“„ repo_documenter.yaml

βš™οΈ Installation

To get started with the Cartai project, follow these instructions to set up your environment:

  1. Clone the repository:

    git clone https://www.github.com/ContrastoAI/cartai
    cd cartai
  2. Ensure you have uv and pre-commit installed. You can check their installation with:

    make .uv
    make .pre-commit
  3. Install all dependencies and set up your environment:

    make install-all

πŸ’» Usage

You can run the project using the provided Makefile commands. For example, to generate the README documentation, you can use:

make run_readme

This command will execute the documentation generation process with the description "Crafting intelligent E2E documentation for trustworthy AI." and output it to README_new.md.

Other Makefile Commands

  • Format code:

    make format
  • Lint code:

    make lint
  • Run tests:

    make test
  • Run pre-commit hooks:

    make pre-commit

πŸš€ Deployment

To deploy the project, follow the standard deployment procedures for your environment. Ensure all dependencies are installed, and run the necessary commands as needed.

🀝 Contributing

We welcome contributions! Here's how you can contribute:

  1. Fork the repository 🍴
  2. Create your feature branch:
    git checkout -b feature/YourFeature
  3. Commit your changes:
    git commit -m 'Add YourFeature'
  4. Push to the branch:
    git push origin feature/YourFeature
  5. Open a pull request πŸ“¬

Please follow the coding guidelines and check the Makefile or contributing docs if available.

About

OSS AI supervisor Agent, for AI lifecycle. πŸ¦Έβ€β™€οΈIntelligent E2E oversight & compliance for trustworthy AI.

Topics

Resources

License

Stars

Watchers

Forks

Contributors 2

  •  
  •