lowfat is a lightweight CLI tool that reduces AI token costs by filtering unnecessary CLI output before it reaches your agent.
- Lightweight — Small single binary, small core; but extensible.
- Local-first — No telemetry; you own your data.
- Composable — UNIX-style pipes, mix built-ins and your own filters; not magic.
- User-owned —
lowfat historyshows what you run most; allow you to customize for your usecase.
| Command | Raw | Filtered | Saved |
|---|---|---|---|
git status |
115t | 5t | 96% |
git diff |
2,376t | 115t | 95% |
git log |
379t | 118t | 69% |
docker ps |
271t | 41t | 85% |
ls -la |
192t | 30t | 84% |
cargo install lowfat
# or
brew install zdk/tools/lowfatPre-built binaries on GitHub Releases.
Pick one of:
Claude Code hook — add to .claude/settings.json:
{
"hooks": {
"PreToolUse": [
{ "matcher": "Bash", "hooks": [{ "type": "command", "command": "lowfat hook" }] }
]
}
}Shell integration — auto-activates inside agent environments (CLAUDECODE=1, CODEX_ENV):
echo 'eval "$(lowfat shell-init zsh)"' >> ~/.zshrc # or ~/.bashrcDirect usage — prefix any command:
lowfat git status
lowfat docker ps
lowfat ls -lapi agent — in ~/.pi/agent/settings.json:
{ "shellCommandPrefix": "eval \"$(lowfat shell-init zsh)\"; " }# See what's configured and how loud each filter is being
lowfat info # status badge + active filters
lowfat info git # pipeline for `git`
lowfat info --config # full resolved config
# See what lowfat has saved you
lowfat stats # lifetime token savings
lowfat stats --audit # recent plugin executions
lowfat history # rank commands by potential savings
# Dial the aggressiveness
lowfat level ultra # max compression
LOWFAT_LEVEL=lite lowfat git log # one-off override
# Write a plugin
lowfat plugin new terraform # scaffold ~/.lowfat/plugins/terraform/
lowfat plugin doctor # check plugins (and pre-install any Python deps)
# Test a plugin against a sample without installing it
cat samples/git-diff-full.txt | lowfat filter --explain ./filter.lf --sub=diff --level=ultra- docs/CONFIG.md —
.lowfatfile, env vars, pipeline DSL, built-in processors, thehistoryranking - docs/PLUGINS.md —
.lfrule DSL, shell escape hatches, PEP 723 + uv, AI agent prompt
Apache-2.0
Multiple AI tools were used for this project
