Turn code into Markdown for LLMs with one simple terminal command

Recursively fetches all code files in the current directory, ignoring what's in .gitignore and .codefetchignore, then outputs them into a single Markdown file with line numbers.

Basic usage with output file and tree

npx codefetch -o my-complete-source.md -t

With token limit (useful for AI models):

npx codefetch --max-tokens 20000 -o output.md

Filter by file extensions:

npx codefetch -e .ts,.js -o typescript-files.md

Include or exclude specific files and directories:

# Exclude node_modules and public directories
npx codefetch --exclude-dir node_modules,public -o output.md

# Include only TypeScript files
npx codefetch --include-files "*.ts" -o typescript-only.md

# Include src directory, exclude test files
npx codefetch --include-dir src --exclude-files "*.test.ts" -o src-no-tests.md

If no output file is specified (-o or --output), it will print to stdout.

All options that accept multiple values use comma-separated lists. File patterns support simple wildcards:

• * matches any number of characters
• ? matches a single character

You can run directly with npx:

npx codefetch

Or install globally:

npm install -g codefetch
codefetch -o output.md

You can generate a visual tree representation of your project structure:

# Generate tree with default depth (2 levels)
npx codefetch --project-tree

# Generate tree with custom depth
npx codefetch -t 3

# Generate tree and save code to file
npx codefetch -t 2 -o output.md

Example output:

Project Tree:
└── my-project
    ├── src
    │   ├── index.ts
    │   ├── types.ts
    │   └── utils
    ├── tests
    │   └── index.test.ts
    └── package.json

codefetch supports two ways to ignore files:

1. .gitignore - Respects your project's existing .gitignore patterns
2. .codefetchignore - Additional patterns specific to codefetch

The .codefetchignore file works exactly like .gitignore and is useful when you want to ignore files that aren't in your .gitignore.

By default, it includes:

• test/ - All test files and directories
• vitest.config.ts - Vitest configuration file

You can add more patterns to ignore additional files:

# Default patterns (automatically added)
test/
vitest.config.ts

# Your additional patterns
*.css # all css files
docs/ # documentation directory

Both files support standard gitignore patterns including:

• Exact matches (file.txt)
• Directories (dir/)
• Wildcards (*.log)
• Negation (!important.log)

Codefetch uses a set of default ignore patterns to exclude common files and directories that typically don't need to be included in code reviews or LLM analysis.

You can view the complete list of default patterns in default-ignore.ts.

By default, when using the -o or --output option, codefetch will:

1. Create a codefetch/ directory in your project
2. Store all output files in this directory
3. Create a .codefetchignore file (if it doesn't exist) that includes test files and configuration

This ensures that:

• Your fetched code is organized in one place
• Test files and configuration are excluded by default
• The output directory can be safely ignored in version control

We recommend adding codefetch/ to your .gitignore file to avoid committing the fetched codebase.

You can use this command to create code-to-markdown in bolt.new, cursor.com, ... and ask the AI chat for guidance about your codebase. The -tok option helps ensure your output stays within AI model token limits.

The --verbose or -v option supports different levels of output:

# No verbose output (just results)
npx codefetch -o output.md

# Basic progress information (level 1)
npx codefetch -v -o output.md
# or
npx codefetch -v 1 -o output.md

# Detailed debug information (level 2)
npx codefetch -v 2 -o output.md

Verbose levels:

• Level 0: Only shows essential output (final results)
• Level 1: Shows basic progress (file counts, processing stages)
• Level 2: Shows detailed debug information (individual file processing, skipped files, etc.)

MIT

• X/Twitter: @kregenrek
• Bluesky: @kevinkern.dev
• Ultimate Cursor AI Course: Instructa.ai

This project was inspired by

• codetie CLI made by @kevinkern & @timk
• sitefetch CLI made by @egoist. While sitefetch is great for fetching documentation and websites, codefetch focuses on fetching local codebases for AI analysis.