🏗️ ArchDoc Generator

AI-powered architecture documentation generator for any codebase using LangChain and multi-agent workflows.

ArchDoc Generator is an intelligent tool that analyzes your codebase and generates comprehensive, accurate architectural documentation automatically. It supports any programming language and uses AI-powered agents to understand your project structure, dependencies, patterns, security, and data flows.

📋 Table of Contents

• Features
• Quick Start
• CLI Usage
• Programmatic Usage
• Configuration
• What Gets Generated
• Available Agents
• Architecture Highlights
• Supported Languages
• Contributing
• License

✨ Features

• 🤖 7 Specialized Agents: File Structure, Dependencies, Patterns, Flows, Schemas, Architecture, and Security.
• 🌍 Language Agnostic: Works with TypeScript, Python, Java, Go, and more.
• 🧠 AI-Powered: Uses LangChain with Claude 4.5, GPT-5, Gemini 2.5, or Grok 3.
• 📊 Comprehensive Analysis: Structure, dependencies, patterns, flows, schemas, and security.
• 📝 Markdown Output: Clean, version-controllable documentation.
• 🔄 Iterative Refinement: Self-improving analysis with quality checks.
• 🎨 Customizable: Prompt-based agent selection and configuration.
• 📈 LangSmith Tracing: Full observability of AI workflows.
• 🔒 Security Analysis: Vulnerability detection, authentication review, and crypto analysis.

🚀 Quick Start

Installation

# Using npm
npm install -g @techdebtgpt/archdoc-generator

# Using yarn
yarn global add @techdebtgpt/archdoc-generator

# Using pnpm
pnpm add -g @techdebtgpt/archdoc-generator

Interactive Setup (Recommended)

Run the interactive configuration wizard:

archdoc config --init

This will:

1. Prompt you to choose an LLM provider (Anthropic/OpenAI/Google).
2. Ask for your API key.
3. Create .archdoc.config.json with your configuration.
4. Validate your setup.

Basic Usage

# Analyze current directory
archdoc analyze

# Analyze specific project
archdoc analyze /path/to/your/project

# Focused analysis with prompt
archdoc analyze --prompt "analyze dependencies and security vulnerabilities"

# Custom output location
archdoc analyze --output ./docs

# Quick analysis (faster, less detailed)
archdoc analyze --depth quick

CLI Usage

archdoc analyze [path] [options]

Options:

🔧 Programmatic Usage

Use the library in your Node.js applications:

import {
  DocumentationOrchestrator,
  AgentRegistry,
  FileSystemScanner,
} from '@techdebtgpt/archdoc-generator';

// Setup registry with agents
const registry = new AgentRegistry();
const scanner = new FileSystemScanner();
const orchestrator = new DocumentationOrchestrator(registry, scanner);

// Generate documentation
const docs = await orchestrator.generateDocumentation('/path/to/project', {
  maxTokens: 100000,
  parallel: true,
  iterativeRefinement: {
    enabled: true,
    maxIterations: 5,
    clarityThreshold: 80,
  },
});

console.log('Generated:', docs.summary);

See the API Reference for complete programmatic documentation.

⚙️ Configuration

Environment Variables

See the Configuration Guide for detailed options.

🎨 What Gets Generated

The tool generates a multi-file documentation structure:

docs/
├── index.md
├── metadata.md
├── file-structure.md
├── dependencies.md
├── patterns.md
├── flows.md
├── schemas.md
├── architecture.md
├── security.md
└── recommendations.md

🤖 Available Agents

Each agent specializes in a specific analysis task:

🏗️ Architecture Highlights

Multi-Agent System

The orchestrator coordinates agents to perform analysis.

┌─────────────────────────────┐
│  Documentation Orchestrator │
└─────────────┬─────────────┘
              │
    ┌─────────┴─────────┐
    │  Agent Registry   │
    └─────────┬─────────┘
              │
┌───▼────┐  ┌───▼───┐  ┌───▼───┐
│ Agent 1│  │ Agent 2│  │ Agent N│
└────────┘  └───────┘  └───────┘

LangChain LCEL Integration

All agents use LangChain Expression Language (LCEL) for composable AI workflows with unified LangSmith tracing.

📊 Supported Languages

The tool is language-agnostic and works with:

• TypeScript/JavaScript
• Python
• Java/Kotlin
• Go
• C#/.NET
• Ruby
• PHP
• Rust (experimental)
• And more!

🤝 Contributing

We welcome contributions! See the Contributing Guide for details on:

• Development setup
• Creating custom agents
• Testing guidelines
• Code style and standards
• Pull request process

� Resources

• 🌐 Website: techdebtgpt.com
• 📦 GitHub: github.com/techdebtgpt/architecture-doc-generator
• 📚 Documentation: Full Documentation
• 💬 Discussions: GitHub Discussions
• 🐛 Issues: Report Issues

�📄 License

Apache License 2.0 - see the LICENSE file for details.

Made with ❤️ by TechDebtGPT