Show HN：CodeSyncer – 將 AI 編碼上下文儲存在程式碼註解中

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

To see all available qualifiers, see our documentation.

Uh oh!

There was an error while loading. Please reload this page.

AI-powered multi-repository collaboration system

License

Uh oh!

There was an error while loading. Please reload this page.

bitjaru/codesyncer

Folders and files

Latest commit

History

Repository files navigation

CodeSyncer CLI

Is your AI coding dumb? Make it smarter - Persistent project context, controlled inference, and live architecture sync for Claude Code

한국어 문서 | English

🎬 Demo

🤔 The Problem

Working with AI on real projects? You face these issues:

1. Context is lost every session 😫

2. Multi-repo chaos 🤯

3. AI makes dangerous assumptions ⚠️

Result: You spend more time explaining and fixing than actual coding.

✨ The Solution

CodeSyncer gives AI the full picture through:

Result: AI codes with high accuracy even in complex multi-repo projects. 🎯

🎯 What is CodeSyncer?

CodeSyncer provides the framework and rules for AI coding assistants (like Claude Code) to set up an intelligent collaboration system across your multi-repository workspace.

How it works:

CodeSyncer defines WHERE and HOW documentation should be created. Your AI assistant fills in the WHAT by analyzing your actual code.

Key Features

⚠️ Prerequisites

CodeSyncer requires an AI coding assistant to be active.

Currently supported:

Important: Make sure your AI coding assistant is running and active before using CodeSyncer. The AI will analyze your projects and help generate accurate documentation.

📦 Installation

🔄 Updating CodeSyncer

Check your current version

Check latest version

Update to latest

After updating, validate and sync your project

When you update CodeSyncer to a new version, first validate your setup, then sync:

The validate command checks your CodeSyncer setup and reports issues:

What it checks:

Example output:

Sync your project with the latest templates and features:

What happens:

Example output:

After running codesyncer update:

Choose one of these options to apply changes:

Option 1: Start a new AI session (Recommended)

Option 2: Apply in current session

🚀 Quick Start

Step 1: Install CodeSyncer

Step 2: Launch your AI assistant

Open your AI coding assistant:

Make sure it's active and running.

Step 3: Navigate to your project

CodeSyncer works with single repositories, multi-repo workspaces, and monorepos:

Single Repository (auto-detected):

Multi-Repository Workspace:

Monorepo (auto-detected via Turborepo, pnpm, Nx, Lerna, npm/yarn workspaces):

Step 4: Initialize CodeSyncer

You'll be asked:

What happens:

That's all CodeSyncer does! It provides the framework and rules. Now your AI takes over.

⚠️ IMPORTANT: Step 5 - Let AI Set Everything Up

🎯 Don't skip this step! This is where the magic happens.

Launch Claude Code (or your preferred AI assistant) and say:

For Single Repository:

For Multi-Repository Workspace:

What happens next (automatically):

1️⃣ AI Analyzes Your Code

2️⃣ AI Asks Critical Questions (Never assumes!)

3️⃣ AI Generates Complete Documentation

💡 Why this works: AI analyzes YOUR actual code and asks YOU questions. The generated docs are tailored to your specific project, not generic templates.

Step 6: Start Coding!

Once setup is complete, just tell your AI:

Your AI assistant will then:

📚 Usage

Initialize collaboration system

Update project structure

Watch Mode (NEW in v2.6.0)

What it does:

Example output:

Add new repository to workspace

🏷️ Comment Tag System

CodeSyncer uses a structured comment tag system to permanently record all AI inferences and decisions in your code.

Available Tags

Legacy Compatibility

Existing @claude-* tags are fully compatible:

🤝 Auto-Discussion System

CodeSyncer automatically pauses AI work when critical keywords are detected, preventing costly mistakes.

Critical Keywords (Auto-Enabled)

How It Works

🌍 Multi-Language Support

CodeSyncer fully supports both Korean and English:

Switch language anytime during setup or use language-specific commands.

🔧 Tech Stack Auto-Detection

CodeSyncer automatically detects your project type and tech stack:

Supported:

Detection happens automatically by scanning:

📖 Example Workflow

Scenario: Adding Payment Feature

🎯 Why CodeSyncer?

Before CodeSyncer ❌

After CodeSyncer ✅

🤖 Supported AI Tools

✅ Currently Supported

🚧 Coming Soon (Community Contributions Welcome!)

Want to add support for your favorite AI tool? Contribute here!

📁 Project Structure

After running codesyncer init, your project will look like:

Single Repository Mode

Multi-Repository Mode

Monorepo Mode (NEW in v2.4.0)

Supported Monorepo Tools:

🛠️ Advanced Usage

Custom Keywords

In Expert setup mode, you can add custom keywords:

Then select "Add custom keywords" and specify:

Updating Existing Projects

Run codesyncer update to:

🔍 Searching Tags

Find all tagged comments in your codebase:

🤝 Contributing

We welcome contributions! CodeSyncer is open source and community-driven.

🚀 Quick Start for Contributors

🎯 Priority Areas for Contribution

📖 Guidelines

See CONTRIBUTING.md for detailed contribution guidelines.

💬 Questions?

📝 License

Commons Clause License + MIT

See LICENSE file for full details.

Why Commons Clause?
We want CodeSyncer to remain free and accessible to all developers while preventing commercial exploitation. If you need a commercial license, please contact us.

🙋 FAQ

Q: Does this only work with Claude Code?
A: Currently, yes. But we're building support for Cursor, GitHub Copilot, and other tools. Contributions welcome!

Q: Can I use this on a single repository?
A: Yes! CodeSyncer automatically detects if you're in a single repo (has package.json, .git, etc.) and creates .claude/SETUP_GUIDE.md instead of the multi-repo structure.

Q: Does this work with monorepos (Turborepo, pnpm, Nx, Lerna)?
A: Yes! As of v2.4.0, CodeSyncer automatically detects monorepo configurations (turbo.json, pnpm-workspace.yaml, nx.json, lerna.json, or package.json with workspaces) and scans all packages in your workspace patterns.

Q: Will this slow down AI responses?
A: No. CodeSyncer only adds documentation files that AI reads once per session. It actually makes AI more efficient by providing context upfront.

Q: Can I customize the keyword detection?
A: Yes, use Expert setup mode to fully customize which keywords trigger discussions.

Q: Is my code/data sent anywhere?
A: No. CodeSyncer is a purely local CLI tool that generates documentation files in your repos. Nothing is sent to external servers.

🌟 Show Your Support

If CodeSyncer helps your team, please:

💰 Support Development

If you'd like to support the development of CodeSyncer, you can donate via cryptocurrency:

Ethereum (ETH) / ERC-20 Tokens:

Your support helps maintain and improve CodeSyncer! 🙏

📮 Contact

Built with ❤️ by the CodeSyncer community

Making AI collaboration seamless, one repo at a time.

About

AI-powered multi-repository collaboration system

Topics

Resources

License

Code of conduct

Contributing

Uh oh!

There was an error while loading. Please reload this page.

Stars

Watchers

Forks

Releases

  22

Sponsor this project

Uh oh!

There was an error while loading. Please reload this page.

Packages

  0

Contributors

  3

Languages

Footer

Footer navigation