An AI-powered system that modernizes technical documentation using LangGraph agents and Claude.
- Fetches documentation from any URL
- Identifies outdated content and practices
- Researches current best practices
- Generates modernized markdown documentation
- Provides quality assessment
-
Install UV package manager:
curl -LsSf https://astral.sh/uv/install.sh | sh -
Clone and setup:
git clone <repo> cd doc-modernizer uv sync
-
Configure environment:
cp .env.example .env # Add your GEMINI_API_KEY to .env -
Run the application:
uv run python src/app.py
-
Open browser to http://localhost:7860
The system uses a LangGraph state machine with these agents:
- Fetcher: Retrieves and converts HTML to markdown
- Analyzer: Identifies outdated sections and issues
- Researcher: Finds current best practices
- Generator: Creates modernized documentation
- Quality Checker: Validates output quality
- Enter a documentation URL
- Click "Modernize"
- Review the analysis, modernized content, and quality report
- Download the modernized markdown
Run tests:
uv run pytestFormat code:
uv run ruff check src/