⚡ One config to rule them all. Centralized AI assistant configuration management - generate rules for Claude, Cursor, Copilot, Windsurf and more from a single YAML file.
Project description
ai-rulez ⚡
One config to rule them all.
Tired of manually managing rule files, subagents, and custom commands across different AI tools? ai-rulez gives you one ai-rulez.yml file to generate them all. Keep your AI context in sync, and even launch MCP servers for direct integration.
📖 Read the Full Documentation
Feature Highlights
ai-rulez is a progressive tool-box, designed to offer a centralized way to manage AI tooling for a repository.
Centralized Configuration
- Centralized Definitions: Use a single
ai-rulez.ymlas the source of truth to define rules, file structures, and documentation for all your AI tools. - Nested Configs & Monorepo Support: Scale your configurations with
extendsandincludes. Manage complex projects and monorepos with ease by using the--recursiveflag to combine configurations from multiple files.# Generate rules for all projects in a monorepo ai-rulez generate --recursive
Powerful Tooling
- Custom Commands: Define custom commands that your AI assistant can execute, enabling powerful, interactive workflows.
- Specialized AI Agents: Create specialized "sub-agents" with their own system prompts and tools, perfect for complex tasks like code reviews or database queries.
- MCP Integration: Automatically configure MCP servers across CLI tools (Claude, Gemini) and generate config files for others (Cursor, VS Code). One configuration, every tool connected.
- Full-Featured CLI: Manage your entire configuration from the command line. Add rules, update agents, and generate files without ever opening a YAML file.
Flexible Integrations
- Multi-Tool Support: Use presets to instantly generate configurations for popular AI tools like Claude, Cursor, Copilot, Gemini, and more.
- Custom Tool Integration: Don't see your favorite tool on the list? Use the
outputskey to generate a configuration file for any tool, in any format.
How It Works
ai-rulez takes your ai-rulez.yml file and uses it as a single source of truth to generate native configuration files for all your AI tools. Think of it as a build system for AI context—you write the source once, and it compiles to whatever format each tool needs.
Example: ai-rulez.yml
$schema: https://github.com/Goldziher/ai-rulez/schema/ai-rules-v2.schema.json
metadata:
name: "My SaaS Platform"
version: "2.0.0"
# Use presets for common configurations
presets:
- "popular" # Includes Claude, Cursor, Windsurf, and Copilot
rules:
- name: "Go Code Standards"
priority: high
content: "Follow standard Go project layout (cmd/, internal/, pkg/). Use meaningful package names and export only what is necessary."
sections:
- name: "Project Structure"
priority: critical
content: |
- `cmd/`: Main application entry point
- `internal/`: Private application code (business logic, data access)
- `pkg/`: Public-facing libraries
agents:
- name: "go-developer"
description: "Go language expert for core development"
system_prompt: "You are an expert Go developer. Your key responsibilities include writing idiomatic Go, using proper error handling, and creating comprehensive tests."
# MCP servers for direct AI tool integration
mcp_servers:
- name: "ai-rulez"
command: "ai-rulez"
args: ["mcp"]
description: "AI-Rulez MCP server for configuration management"
Run ai-rulez generate → get all your configuration files, perfectly synchronized.
Quick Start
# 1. AI-powered initialization (recommended)
ai-rulez init "My Project" --preset popular --use-agent claude
# 2. Generate all AI instruction files
ai-rulez generate
# 3. Your AI tools now have comprehensive, project-specific context!
That's it! The AI will analyze your codebase and generate tailored rules, documentation, and specialized agents automatically.
Prefer manual setup?
# Basic initialization without AI assistance
ai-rulez init "My Project" --preset popular
# Add your project-specific context
ai-rulez add rule "Tech Stack" --priority critical --content "This project uses Go and PostgreSQL."
# Generate files
ai-rulez generate
MCP Server Integration
ai-rulez provides seamless Model Context Protocol (MCP) integration, automatically configuring both file-based and CLI-based AI tools with your MCP servers.
Automatic CLI Configuration
When you run ai-rulez generate, MCP servers are automatically configured for available CLI tools:
ai-rulez generate
# ✅ Generated 3 file(s) successfully
# ✅ Configured claude MCP server: ai-rulez
# ✅ Configured gemini MCP server: database-tools
Supported CLI tools:
- Claude CLI:
claude mcp addwith full env/transport support - Gemini CLI:
gemini mcp addwith automatic configuration
Hybrid Configuration
ai-rulez supports both CLI and file-based configurations simultaneously:
mcp_servers:
- name: "database-tools"
command: "uvx"
args: ["mcp-server-postgres"]
env:
DATABASE_URL: "postgresql://localhost/mydb"
targets:
- "@claude-cli" # Configure Claude CLI
- "@gemini-cli" # Configure Gemini CLI
- ".cursor/mcp.json" # Generate Cursor config file
This single configuration:
- ✅ Executes
claude mcp addcommands - ✅ Executes
gemini mcp addcommands - ✅ Generates
.cursor/mcp.jsonfile
Control Options
Default behavior (recommended):
ai-rulez generate
# Configures all available CLI tools + generates files
Disable CLI configuration when needed:
ai-rulez generate --no-configure-cli-mcp
# Only generates files, skips CLI tool configuration
Target specific tools:
mcp_servers:
- name: "github-integration"
command: "npx"
args: ["@modelcontextprotocol/server-github"]
targets: ["@claude-cli"] # Only configure Claude CLI
Built-in MCP Server
ai-rulez includes its own MCP server for configuration management:
# Start the ai-rulez MCP server
ai-rulez mcp
# Or configure it automatically via your ai-rulez.yaml
mcp_servers:
- name: "ai-rulez"
command: "ai-rulez"
args: ["mcp"]
description: "Configuration management server"
Installation
Run without installing
For one-off executions, you can run ai-rulez directly without a system-wide installation.
Go
go run github.com/Goldziher/ai-rulez/cmd@latest --help
Node.js (via npx)
# Installs and runs the latest version
npx ai-rulez@latest init
Python (via uvx)
# Runs ai-rulez in a temporary virtual environment
uvx ai-rulez init
Install globally
For frequent use, a global installation is recommended.
Go
go install github.com/Goldziher/ai-rulez/cmd@latest
Homebrew (macOS/Linux)
brew install goldziher/tap/ai-rulez
npm
npm install -g ai-rulez
pip
pip install ai-rulez
Pre-commit Hooks
You can use ai-rulez with pre-commit to automatically validate and generate your AI configuration files.
Add the following to your .pre-commit-config.yaml:
repos:
- repo: https://github.com/Goldziher/ai-rulez
rev: v2.1.0
hooks:
- id: ai-rulez-validate
- id: ai-rulez-generate
Documentation
- Quick Start Guide
- Full CLI Reference
- Configuration Guide
- Migration Guide - Upgrading from v1.x to v2.0
Contributing
Contributions are welcome! Please see the Contributing Guide to get started.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ai_rulez-2.1.0.tar.gz.
File metadata
- Download URL: ai_rulez-2.1.0.tar.gz
- Upload date:
- Size: 12.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ad63d6cb75c4b8c87f6aac8f1126774f9ee4afacae0bc17b540a4362f3761a97
|
|
| MD5 |
00ad99cfb582ad7c7822a1f61139c36b
|
|
| BLAKE2b-256 |
3fc61c5502561584af97209280b2e6f88d9fb70edea339f99c226879b307641d
|
File details
Details for the file ai_rulez-2.1.0-py3-none-any.whl.
File metadata
- Download URL: ai_rulez-2.1.0-py3-none-any.whl
- Upload date:
- Size: 9.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
84edd31778c1fe076df8b192efc662af255b788e65a4ae876dbbabb3f3ac3001
|
|
| MD5 |
3e2111c6b4915bb92cb129df54ca58ca
|
|
| BLAKE2b-256 |
d080490c734346521eb0cbb3b2c43bdf92d0776e843798a8829ca00ce81090ca
|