yek 命令

常用示例

说明

yek (Farsi for "one") is a fast Rust-based CLI tool that serializes code repositories into text optimized for LLM (Large Language Model) consumption. It combines files into a single output with intelligent ordering and automatic filtering. The tool respects .gitignore rules, uses Git history to prioritize important files, and automatically skips binary and large files. Output can be split into chunks based on token count or byte size. When output is piped, yek automatically streams content instead of writing to files. This enables workflows like yek | pbcopy to quickly copy a codebase to clipboard for pasting into an LLM chat. Configuration can be stored in yek.toml or yek.yaml files for project-specific settings.

参数

--tokens _count_

Use token counting mode instead of byte mode (e.g., 128k, 100)

--max-size _size_

Limit output by byte size (e.g., 10MB, 128K); default: 10MB

--json

Output results in JSON format

--output-dir _path_

Directory for output files; uses temp directory if not specified

--output-name _name_

Filename written to current directory

--output-template _template_

Custom format using FILE_PATH and FILE_CONTENT placeholders

--ignore-patterns _patterns_

Additional patterns to ignore (extends .gitignore)

--unignore-patterns _patterns_

Override built-in ignore rules

--line-numbers

Include line numbers in output

-t, --tree-header

Include directory tree at the start of output

--tree-only

Show only directory structure without file contents

--no-config

Skip loading configuration files

--config-file _path_

Use specific configuration file

--debug

Enable debug logging