AI Project Manager

Markdown-based project management system optimized for AI-assisted development

Stop spending time re-explaining context to AI. This system creates a persistent memory layer that dramatically improves AI coding sessions while reducing token consumption.

I began by using custom markdown files to manage my projects. It was incredibly effective for documenting decisions, sprints, and tasks. Over the last six months, this system has consistently saved me time and provided a persistent record of every project's evolution.

However, I realized I was spending too much time re-explaining context to AI, and manually creating these files became a bottleneck. I built this system to automate that process and streamline project management for myself—and now, for you.

Useful information:

• About Tokens Usage
• Troubleshooting

Quick Start

Installation

# Install to your existing project
npx @rmarsigli/aipm install

Usage

1. First use:

{talk about your project, more details = better AI experience. You can write in any language} - Now, create a .project/ folder with a README.md file following submitted guidelines.

2. Create a task:

{talk about your task, more details = better AI experience} - Now, plan a task for me to start working on it.

Structure

The system relies on a simple file structure in your project root:

.project/
├── current-task.md      # The one active task you are working on
├── context.md           # Persistent session memory and state
├── backlog/             # Future tasks
├── completed/           # Archive of finished tasks
├── decisions/           # Architecture Decision Records (ADRs)
└── scripts/             # Helper scripts (e.g. pre-session checks)

Commands

| Script | description | | :--- | :--- | | .project/scripts/pre-session.sh | Estimates token usage for the current session. | | .project/scripts/validate-dod.sh | validating Definition of Done (tests, lint, etc). |

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for details.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing)
3. Commit your changes (git commit -m 'feat: add amazing feature')
4. Push to the branch (git push origin feature/amazing)
5. Open a Pull Request

License

MIT -- see LICENSE file.