🚧 Work in Progress - Production Ready for Next.js
While this project is actively evolving, it's already proven valuable for AI-assisted development. The installer is safe and non-destructive - it never modifies existing files or adds dependencies. It simply creates helpful scaffolding files that make AI tools smarter.
A zero-dependency lightweight scaffolding tool for adding AI-assisted development structure to Next.js projects (Python support coming soon).
🔥 Pro Tip: Try it first on a sample project like
npx create-next-app@latestwith the--addflag to see how it works. The tool will:
- Create a
rules.yamlfile (symlinked as.windsurfrules,.cursorrules, and.clinerules)- Set up a
memory-bankdirectory with default files based on your rules
AI Init helps you quickly set up the foundation for AI-assisted development by creating a standardized structure of files and directories. This structure helps AI tools like GitHub Copilot, Cursor, and WindSurf better understand your project context and maintain knowledge across sessions.
Designed specifically for Next.js projects (with Python support in development), AI Init creates the necessary directory structure and files that enable AI assistants to better understand and help with your development.
As a developer working primarily with Next.js and Python, I found myself spending too much valuable time on repetitive scaffolding tasks when using AI-powered IDEs like Cursor, Windsurf, and Cline. Each new project required the same manual setup to properly direct the AI and help it understand my codebase.
I created AI Init because I believe our time is better spent solving real problems, not configuring environments. The tool allows you to immediately take advantage of AI using standardized rules and persistent memories across sessions, without wasting hours on setup and troubleshooting.
What makes AI Init special is its unopinionated approach. Since I regularly use all three major AI-powered IDEs and recognize that each has its place in a developer's toolbox, I designed this template to work seamlessly with any of them.
By using the --add flag, you can quickly outfit existing projects with AI-friendly structure, or create new directories that follow current best practices. My roadmap includes extending this to other platforms, with Python support currently in development.
I sincerely believe this tool will help others, and I'm sharing it because I believe a rising tide floats all boats. Let's all spend less time configuring and more time building amazing things.
AI Init is a one-time scaffolding tool - it sets up the structure and gets out of your way. There's no ongoing dependency or library to maintain. The created files provide context to AI assistants, helping them:
The easiest way to use AI Init is with npx, which comes with npm 5.2+ and higher:
# Create a new directory with AI scaffolding
npx ai-init my-directory
# Add scaffolding to an existing project (run in the project directory)
npx ai-init --add
If you prefer, you can install AI Init globally:
# Install globally
npm install -g ai-init
# Then use without npx
ai-init my-directory
The current version is 1.6.8. You can use AI Init with either the latest or a specific version:
# Always use the most recent version from npm
npx ai-init@latest my-directory
# Use a specific version for consistency or compatibility
npx ai-init@1.6.8 my-directory
npx ai-init [directory-name] [options]
Options:
--add - Add scaffolding to existing project--verbose - Show detailed logs--skip-symlink - Skip creating symlinks--help or -h - Show help message--version or -v - Show version numberRun without arguments for interactive prompts:
npx ai-init
After initialization, your project will have the following structure:
project-root/
├── .cursor/ # Cursor-specific configurations
│ └── rules/ # Individual rule files
├── doc-files/ # Project documentation
│ └── adr/ # Architecture Decision Records
├── memory-bank/ # AI assistant persistent memory
│ ├── projectbrief.md # High-level project goals
│ ├── techContext.md # Technical stack information
│ ├── systemPatterns.md # Common patterns and conventions
│ ├── activeContext.md # Current work in progress
│ ├── progress.md # Project status tracking
│ └── roadmap.md # Future development plans
├── mem-scripts/ # Helper scripts
├── .windsurfrules # Symlink to rules.yaml for WindSurf IDE
├── .cursorrules # Symlink to rules.yaml for Cursor IDE
├── .clinerules # Symlink to rules.yaml for command-line tools
└── rules.yaml # Main configuration file
After installing AI Init, you'll need to set up your project's rules and memory bank using AI prompts.
AI Init automatically creates symlinks from rules.yaml to .windsurfrules, .cursorrules, and .clinerules in your project root. These ensure that AI assistants and command-line tools can detect and apply your project rules.
Use your AI assistant to intelligently populate the placeholders in rules.yaml with this prompt:
## Prompt: Analyze and Populate `@rules.yaml`
### Objective
Deeply analyze the `@rules.yaml` file to understand its **intent and purpose** within the context of the project.
### Your Role
You are tasked with the following responsibilities:
1. **Analyze the Project Structure**
- Review the project's directory and codebase in detail.
- Identify core features, modules, and functionalities.
- Infer the application's primary purpose and architectural qualities.
2. **Interpret and Populate `@rules.yaml`**
- Understand the placeholders and schema definitions in the `@rules.yaml` file.
- Replace all placeholder content with accurate, context-specific information derived from the codebase.
- Maintain the structure and syntax of the YAML file.
### Output Requirements
- Use **clear, concise, and informative** language.
- Think in terms of **dense technical documentation**: descriptive but not overly verbose.
- Ensure every populated section in the `@rules.yaml` reflects the **real capabilities and structure** of the application.
- When uncertain, make educated inferences based on patterns in the codebase—but flag assumptions as such.
- Fill all placeholders or remove the placeholder if it is not relevant.
After setting up the rules.yaml file, populate your memory bank files with this prompt:
## Prompt: Initialize Memory Bank Files
### Objective
Create a comprehensive knowledge foundation across the memory bank files to enable effective AI assistance for this project.
### Your Role
You are tasked with analyzing the project and populating the memory bank files:
1. **Analyze Project Structure and Purpose**
- Review the project's codebase, structure, and documentation
- Identify core technologies, architecture, and patterns
- Determine project goals and target audience
- Map out feature areas and development priorities
2. **Populate Each Memory Bank File**
- **projectbrief.md**: Summarize purpose, goals, audience, stakeholders, and success criteria
- **techContext.md**: Document technology stack, architecture, APIs, and environment setup
- **systemPatterns.md**: Identify coding patterns, naming conventions, and architectural approaches
- **activeContext.md**: Outline current development status, active features, and immediate challenges
- **progress.md**: Record completed features, milestones, and upcoming development phases
### Content Guidelines
- Be specific and factual based on actual project code and structure
- Organize information with clear headings and concise bulleted lists
- Include code examples where relevant (especially in systemPatterns.md)
- Cross-reference related information between memory files
- Flag content as "Initial assessment based on codebase" where appropriate
- Prioritize information that would be most valuable for ongoing development
### Expected Format
For each file, use markdown with consistent structure:
- Clear main heading matching the file purpose
- Logical subheadings for different categories of information
- Bulleted lists for related items
- Code blocks for examples and patterns
- Brief, information-dense paragraphs
Once your rules and memory bank are populated:
The memory bank is a structured knowledge base for AI assistants with five key files:
projectbrief.mdContains high-level project information:
techContext.mdDetails the technical foundation:
systemPatterns.mdDocuments recurring patterns:
activeContext.mdTracks current development focus:
progress.mdRecords project milestones:
The rule system enforces project standards through both structural rules and automated checks.
Rules are stored as Markdown files with YAML front matter (.mdc) in the .cursor/rules/ directory:
naming_conventions.mdc: Standardizes naming across the project
ui_component_patterns.mdc: Defines UI development standards
memory_bank_enforcement.mdc: Validates memory bank structure
ADRs document important architectural decisions in a structured format:
A template is provided in doc-files/adr/template.md.
The project enforces a standardized commit message format:
<type>[scope]: <description>
[body]
[footer]
feat (feature), fix (bugfix), docs (documentation), style (formatting), refactor, perf (performance), test, build, ci, chore (maintenance), revert
Fixes #123), breaking changes (BREAKING CHANGE: description)For the best experience, use with:
If you encounter issues during installation or setup:
Symlink Creation: Some environments may require administrative privileges to create symlinks. Try running with elevated permissions if symlinks aren't created.
Missing Files: Use the --verbose flag to see detailed logs for debugging file copying issues.
Windows Users: On Windows, symlinks will be replaced with file copies due to permission restrictions.
Contributions are welcome! Please feel free to submit a Pull Request.
git checkout -b feature/amazing-feature)git commit -m 'feat: add some amazing feature')git push origin feature/amazing-feature)Distributed under the MIT License. See LICENSE for more information.
FAQs
Zero-dependency Next.js scaffolding tool for AI-assisted development
The npm package ai-init receives a total of 7 weekly downloads. As such, ai-init popularity was classified as not popular.
We found that ai-init demonstrated a not healthy version release cadence and project activity because the last version was released a year ago. It has 1 open source maintainer collaborating on the project.
Security News
The PHP Foundation says Chainguard broke a security embargo ahead of critical RCE patches, as leaks disrupted the coordinated release.
Security News
PHP releases emergency patches for two critical RCE vulnerabilities as agencies urge organizations to take unpatched sites offline.
Threat Research
/Security News
A supply chain attack compromised LiteLLM 1.107.0 on PyPI and Docker, spreading malware that steals cloud credentials, developer secrets, and AI provider keys.
