Rulebook AI

- For bug report, use issues or use rulebook-ai command rulebook-ai bug-report
- For real-time chat, community support, and to share your ideas, Join our Discord
- Have specific feedback or want a personal demo? Book a Chat on my Calendar

Rulebook-AI: The AI Environment Manager

rulebook-ai is a command-line tool for packaging and deploying consistent, expert environments—rules, context, and tools—to your favorite AI coding assistants.

Stop wasting time re-explaining your project's architecture or manually copy-pasting instructions between different AIs. With rulebook-ai, you define your AI's environment once, and deploy it anywhere.

The Problem: AI Assistants are Generic and Isolated

AI coding assistants are powerful, but they operate in a vacuum.
1.  They are forgetful: They have no long-term memory of your project's specific architecture, libraries, or goals.
2.  They are inconsistent: Instructions you give to Cursor don't work in Gemini, and your Copilot context is siloed.
3.  They are unspecialized: An AI's general knowledge is not enough for expert-level tasks. A great "React developer" AI needs different rules, context, and tools than a great "DevOps engineer" AI.

The Solution: Portable and Composable AI Environments

rulebook-ai solves this by treating an AI's entire operational context as a portable Environment that you can manage like code. An Environment consists of three parts:
*   Rules: The AI's operating instructions and workflows.
*   Context: A persistent knowledge base (your project's "memory").
*   Tools: Helper scripts the AI can use to perform tasks.

These environments are packaged into versionable, shareable Packs.

Why rulebook-ai is the Answer

Quick Start with uvx

This will create a .rulebook-ai directory to manage state, and populate…