contextualize

Python library & composable CLI for reproducible prompt assembly; a differentiated early entrant in a quickly-saturated (and in my experience, deeply valuable) utility class


external: README

contextualize

contextualize is a CLI for assembling files and other text snippets for use with LLMs.

Installation

pip install contextualize

or with uv:

uv tool install contextualize

Commands

command purpose
cat gather file contents (e.g. for piping to llm, or pasting elsewhere)
map survey file/folder structure(s) with aider
shell capture output from arbitrary shell commands
payload compose text and file blocks from a YAML manifest
paste capture staged clipboard snippets

All commands work with the global flags --prompt, --wrap, --copy, --count, and --write-file.

Sample invocations (cat):

# gather files and copy (individually wrapped + labelled, prefixed by '--prompt') to clipboard
contextualize cat src/ README.md --prompt "how does this work?" --copy

# fetch a single file from a remote repo (cached under ~/.local/share/contextualize/cache/git/)
contextualize cat gh:jmpaz/contextualize:README.md

# gather multiple files/folder(s) from a repo
contextualize cat https://git.sr.ht/~cismonx/bookmarkfs:README.md,doc

# fetch a single hosted UTF-8 file
contextualize cat https://modelcontextprotocol.io/llms.txt

Details and more examples are available in docs/usage.md.