Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens

Name: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
Availability: InStock
Author: zdkaster

by zdkaster·Jun 5, 2026·22 points·8 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemCozy

Claude Code hooks that cut token costs, but only matters if you're burning through CLI agent budgets.

Strengths

•Plugin system lets you customize filters per command without touching core code.
•Real savings tracking with history commands shows actual token reduction over time.
•Local-first single binary with zero telemetry respects privacy and stays offline.

Weaknesses

•Niche use case—only valuable if you're already running AI agents on CLI output heavily.
•No Windows binaries mentioned, and OpenCode integration is the only non-CLAIDE option.

Post Description

Hi HN,

Not sure if anyone would be interested.

But, just wanted to share that I've been maintaining my small tool called 'lowfat' that helps me filters some of my verbose CLI output.

It's a single binary, works as an agent hook or a shell wrapper. It has a plugin system to customize filters per command.

The idea is pretty simple: agents don't need the full kubectl get -o yaml or any 10k-line dump to make decisions. So that lowfat sits in between, strips the noise, and passes through what matters.

Here's my real report after 2 months of personal use:

lowfat history --all

lowfat plugin candidates ─────────────────────────────────────────────────────────

# command 1 kubectl get 2 grep 3 git diff 4 kubectl 5 docker 6 ls 489x 7 find 8 git show 9 git 177x 10 git log 11 kubectl logs 12 git status 13 docker ps 14 kubectl describe 15 docker images 16 k get 17 terraform 18 git commit 19 docker build 20 docker compose runs avg raw cost savings source status 101x 14.4K 1.5M 93.9% plugin good 103x 13.5K 1.4M 96.2% plugin good 81x 995 80.6K 57.9% built-in good 90x 485 43.6K 33.6% plugin good 127x 5.5K 693.6K 96.1% built-in good 117 57.3K 56.2% built-in good 30x 16.5K 495.0K 95.5% plugin good 63x 490 30.9K 38.0% built-in good 368 65.2K 76.1% built-in good 86x 556 47.8K 78.5% built-in good 5x 3.6K 17.8K 43.0% plugin good 86x 152 13.1K 58.0% built-in good 20x 467 9.3K 52.8% plugin good 6x 656 3.9K 1.2% plugin weak 9x 940 8.5K 61.8% built-in good 2x 2.1K 4.2K 35.9% plugin good 10x 395 3.9K 32.1% plugin good 32x 77 2.5K 0.0% built-in weak 8x 487 3.9K 37.6% built-in good 22x 979 21.5K 89.4% built-in good

total: 4.4M raw → 4.1M saved (91.8%)

My toolset above is kind limited, but it works pretty well for my usecase without any interruption Kinda help me not reaching the token limit for my company Bedrock limit usage and keep optimizing the saving on the go for later usage.

But, why not alternatives (https://github.com/zdk/lowfat#alternatives) ? The answers are: - My goal is to make the core lightweight but extensible via plugins i.e. not trying to bundle every command in the installed binary so that people own their output filters. - Customizable per usecase via plugin or filter pipelines as I am using my own toolset. - Customizable for non-public CLI tools, for example, some enterprise might have their interal CLI tools that public won't have access. - People should own their data. So the design is local-first, No telemetry forever. - I kinda love UNIX-style composible pipes, so lowfat-filter has implemented this style. - Be able to adjust aggressiveness of the filter, so we can control that we won't strip something the agent needed.

GitHub: https://github.com/zdk/lowfat

Anyway, if anyone is interested, feedbacks and questions are welcome!

Thanks!