Hacker News: zdkaster

Linux 7.1-rc7: give rc7 a whirl and keep testing

zdkaster — Mon, 08 Jun 2026 03:10:21 +0000

Article URL: https://lwn.net/Articles/1076834/

Comments URL: https://news.ycombinator.com/item?id=48440922

Points: 4

# Comments: 0

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Sat, 06 Jun 2026 16:54:18 +0000

I have just put the comparison in the repo in case you want to checkout.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Sat, 06 Jun 2026 14:45:42 +0000

Afaik, caveman does shorten sentences in coversation but lowfat is picking up what matter from cli ouput. That's a different output target.

Making Claude a Chemist

zdkaster — Sat, 06 Jun 2026 05:00:20 +0000

Article URL: https://www.anthropic.com/research/making-claude-a-chemist

Comments URL: https://news.ycombinator.com/item?id=48421552

Points: 6

# Comments: 1

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Sat, 06 Jun 2026 02:46:39 +0000

You can control what you want to feed to the agent. Keep what it needs, discard what it doesn't.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Sat, 06 Jun 2026 01:35:01 +0000

I have just been using it for 2 months, so... lmao. might need a year and with more users to test out how it will go.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Sat, 06 Jun 2026 01:31:17 +0000

Understood. Didn't mean as a click-bait or something. Just sharing my cli report summarize.

Target user here in HN should be tech-savy and this tool is not designed for non-tech because it is required highly customized from user to get the result user want.

Anway, would you mind putting the correct title here ? I will consider to update.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 15:19:24 +0000

Got it! thanks for your feedback.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 15:16:11 +0000

Understood. Let me give some examples, most of the time we don't need spaces between table output, git diff produce bunch of unnessary info we just need filename and actual diff lines, kubectl describe we would mostly check for events, image etc etc. This is the reason why I make it as composable filters as it very depends on your specific ops to optimize the token.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 15:04:40 +0000

Interesting approach. Thanks for sharing.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 14:24:34 +0000

To be safe if you need a full json, would make conditonal passthrough as the original raw output. Or, need to handle selective object using python via the filter plugin.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 14:19:40 +0000

Can you elaborate more on why would it so ?

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 14:11:10 +0000

Frankly, not at all.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 14:09:05 +0000

Thanks for your feedback. Will put this in place. Meanwhile, please checkout architecture doc and plugin. The plugin doc could a little bit giving insight of what it does.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 14:04:26 +0000

I simply use LLM to create filter for my personal use. I have already put that specific instruction in the plugin doc in case you are interested.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 13:18:35 +0000

In term of token saving performance, it should be on par with rtk since it is basically the same idea. The major different is rtk bundled hundreds of filter logic and no room for user to adjust without maintaing user owned fork or opening the pull request while lowfat is using opposite architectural approach by removing almost all filter logic in the binary and seperate user filters as a plugin system

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 13:10:13 +0000

It requires a bit effort in doing long-term adjustment and tuning for your agent common cli tools commands called. kinda need to evolve on day-to-day basis. But, agent itself can be useful to help tuning this.

New comment by zdkaster in "Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens"

zdkaster — Fri, 05 Jun 2026 13:06:00 +0000

It has the strip aggressiveness level suport. You can tune up 3 levels for each template output of your stacktrace using lowfat-filter dsl, shellscript or python.

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

zdkaster — Fri, 05 Jun 2026 09:10:42 +0000

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

Comments URL: https://news.ycombinator.com/item?id=48409955

Points: 156

# Comments: 80

Garmin: The more miles ridden, the higher avg VO2 max and FTP

zdkaster — Thu, 04 Jun 2026 14:13:51 +0000

Article URL: https://www.garmin.com/en-US/blog/fitness/the-beat-on-bikes-the-latest-global-trends-from-garmin-cyclists/

Comments URL: https://news.ycombinator.com/item?id=48398978

Points: 3

# Comments: 0