ruler  by intellectronica

Centralize AI coding agent instructions

created 2 months ago
427 stars

Top 70.4% on sourcepulse

GitHubView on GitHub
1 Expert Loves This Project
Project Summary

Ruler centralizes AI coding assistant instructions, providing a single source of truth for teams to manage and distribute consistent guidance across multiple AI agents like GitHub Copilot, Claude, and Aider. This tool simplifies onboarding, reduces configuration duplication, and mitigates context drift by automatically applying rules to agent-specific configuration files.

How It Works

Ruler operates by consolidating Markdown files from a .ruler/ directory (or a global configuration) into a unified set of instructions. These instructions are then automatically distributed to the configuration files of supported AI agents, as defined in a ruler.toml file. It also manages Model Context Protocol (MCP) server settings and automatically updates .gitignore to exclude generated configuration files.

Quick Start & Requirements

  • Installation: npm install -g @intellectronica/ruler or use npx @intellectronica/ruler.
  • Prerequisites: Node.js 18.x or higher.
  • Project Initialization: Run ruler init in your project's root directory.
  • Documentation: https://github.com/intellectronica/ruler

Highlighted Details

  • Supports a wide range of AI agents including GitHub Copilot, Claude, Cursor, Aider, and Gemini CLI.
  • Manages Model Context Protocol (MCP) server configurations for enhanced AI context.
  • Automatically updates .gitignore to keep generated files out of version control.
  • Provides ruler revert command to safely undo changes.

Maintenance & Community

The project is maintained by intellectronica. Contributions are welcome via pull requests. Issues and feature requests can be submitted via the GitHub issues page.

Licensing & Compatibility

  • License: MIT
  • Compatibility: The MIT license permits commercial use and linking with closed-source projects.

Limitations & Caveats

Currently, all agents receive the same concatenated rules; agent-specific instructions must be manually segmented within rule files. The project is described as a "Beta Research Preview," suggesting potential for instability or breaking changes.

Health Check
Last commit

22 hours ago

Responsiveness

Inactive

Pull Requests (30d)
18
Issues (30d)
18
Star History
434 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), Jeff Hammerbacher Jeff Hammerbacher(Cofounder of Cloudera), and
3 more.

AutoPR by irgolic

0.1%
1k
AI-powered workflows for codebase automation
created 2 years ago
updated 1 year ago
Feedback? Help us improve.