PanisHandsome

PanisHandsome / ai-rules-sync

Public

Keep one source of truth for your AI coding-agent rules. Convert and sync between AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Windsurf, Cline, Aider & Gemini — or scaffold a fresh AGENTS.md. Zero dependencies.

panishandsome.github.ioai-rules-sync agents-md ai claude cli codex
27
0
85% credibility
Found Jun 01, 2026 at 27 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
JavaScript
AI Summary

agentsync is a tool that solves a real problem for developers using multiple AI coding assistants. Different AI tools like Claude Code, Cursor, GitHub Copilot, and others each have their own special files where developers write instructions for the AI. Keeping these files consistent across multiple tools is tedious and error-prone. agentsync lets you write your rules once in one format and automatically generates the correct version for each AI tool. It can also generate high-quality rule files from a simple description of your project, check your existing files for outdated commands, and merge multiple rule files into one. The tool runs entirely in your browser or on your computer with zero external dependencies.

How It Works

1
🤖 Meet your AI coding assistants

You start using AI tools like Claude Code, Cursor, and GitHub Copilot to help write code faster.

2
📝 Each assistant needs its own instruction file

You discover that each AI tool reads its own special file where you explain your project's rules and preferences.

3
😰 Keeping them all in sync becomes a nightmare

You find yourself updating the same instructions in five different places, and they slowly drift apart over time.

4
🔄 agentsync brings order to the chaos

You find a tool that can convert between all these different formats or generate a single master file from a simple description.

5
You choose your path
🌐
Browser playground

Paste any existing rule file and see it converted to any other format instantly

💻
Install the tool

Set it up once and let it automatically keep all your files in sync

6
🎯 Create your rules once

You write your project instructions in one place, either by filling out a simple form or by converting an existing file.

🎉 All your AI assistants stay in perfect sync

Every time you commit code, your rules automatically update everywhere. Your AI helpers always know exactly what you want.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 27 to 27 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is ai-rules-sync?

ai-rules-sync is a JavaScript tool that keeps your AI coding agent rules in sync across all the different tools you're using. If you use Claude Code, Cursor, Copilot, or any combination of AI coding assistants, you've probably noticed each one wants its own rules file in its own format. This tool acts as a central hub: write your rules once in AGENTS.md, then convert and sync them to CLAUDE.md, .cursorrules, copilot-instructions.md, and more. It also scaffolds fresh rule files by scanning your project and detecting your language, framework, and build commands. Zero dependencies means it runs anywhere Node does.

Why is it gaining traction?

The pain point is real. Developers juggling multiple AI coding agents deal with the tedious work of manually keeping each rules file current. This tool solves that with a single command (`agentsync sync`) that propagates changes everywhere. The `agentsync setup` command gets you running in seconds by generating a config, creating your first AGENTS.md, and setting up a pre-commit hook so sync happens automatically on every commit. There's also a browser playground where you can test conversions without installing anything.

Who should use this?

Teams running multiple AI coding assistants will find this most useful. If you're using Claude Code alongside Cursor or Copilot, you need to maintain rules in different formats—this eliminates that manual work. Individual developers working with a single agent can use the generate command to quickly create a solid starting point for their AGENTS.md.

Verdict

This is a clever solution to a real problem, but the project is still finding its footing. With only 27 stars, the credibility score sits at 0.85%, suggesting limited adoption and community testing. The code structure is solid and the feature set is complete, but it needs more users and real-world testing to build confidence. The zero-dependency approach and browser playground are smart design choices, though the low star count means you're an early adopter taking on some risk. If you're managing multiple AI agents, the convenience probably justifies that risk—but keep an eye on the project's growth before committing to it long-term.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.