xcaeser/cm
🤖 cumul concatenates all files in a directory into a single text file to provide context to Large Language Models (LLMs).
v4.2.0.tar.gzcm is a fast CLI tool that concatenates text files in a directory into one output file, ideal for LLM context.
It respects .gitignore, skips binaries, dotfiles, and non-text formats (e.g., images).
Executable name: cm.
curl -fsSL https://raw.githubusercontent.com/xcaeser/cm/main/install.sh | bash
Updating is as simple as (linux/macos):
cm update
for windows (powershell): WIP, for now download the binary from the releases page.
cm [directory]
Generates <directory-name>-cumul.txt with file headers
running only
cmscans the current directory
-p, --prefix <string>: Prefix output filename (e.g., cm -p my → my-<dir>-cumul.txt).-e, --exclude <string>: Comma-separated exclusions (e.g., cm -e .json,.md,LICENSE,.sh,lib/utils.ts etc...).-h, --help: Show help.Outputs summary: files cumulated, lines, size.
.gitignore (wildcards supported).zig build install
Installs cm to $HOME/.local/bin.