Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
3 days ago (github.com)
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!
I would like to have deeper comparison with alternatives like rtk, which are already fast and written in rust, also the previous comments mentioned something that has been a know problem with rtk that it sometimes strips the thing that the llm needs (or expects, causing more work to need to happan not less)
None of these tools measure how effective they are...
It's a massive red flag to me when you could get decent data to see if your thing actually works, and they don't even attempt to...
Have the LLM use your tool, run it on several of the coding benchmarks. If you're stingy, run it on the ones that don't cost much.
Otherwise, I'm going to assume it doesn't actually work. If it did - Claude, Antigravity, Codex, Pi, or some major player would bundle tools like this into the CLI / harness.
AFAIK, none of the major players do. That's a sign to me these don't work in general.
I've tried building some tools specific to bug fixing. Intelligently feeding context massively helps smaller models. But, what I've found - surprisingly - is that a smaller, much better focused, including a lot of helpful data as well, has almost no impact on larger models compared to what they do by default.
You do save some tokens, though, which is what they're claiming - but not ~99%...
> otherwise, popular solutions would integrate the idea
None of the major players are incentivized to care about this, especially not over other opportunities. Why would you expect them to integrate it?
One of the biggest wins you can institute for your own codebase if you use agents is writing your own harness, by a huge margin. The defaults are fine, but you can do better.
7 replies →
It's too hard to define what "works" even means in this case. Look at the example savings output. A lot of it is kubectl output.
Your suggestion to using coding benchmarks doesn't really capture the whole picture. I haven't seen a benchmark using kubectl.
> AFAIK, none of the major players do. That's a sign to me these don't work in general.
It's a lose/lose for major players. If it works well, it will lower their revenue. Also there's a high risk it'll significantly worsen results for some people, even if it improves results for others.
I don't think frontier model providers are going to be incentivized to invest in this much, yet. Once inference gets more competitive, sure. I haven't looked lately, but won't be surprised if tools like OpenCode do do what you're suggesting, though. Third-party coding harnesses ARE aligned to deliver this type of feature and optimization.
My partial solution to this was to store the full response in a file and prompt the agent to read that if the condensed version had stuff missing.
> I'm going to assume it doesn't actually work. If it did - Claude, Antigravity, Codex, Pi, or some major player would bundle tools like this into the CLI / harness.
VS Code launched it as a feature in their bundled AI functionality last month: https://code.visualstudio.com/updates/v1_121
1 reply →
So often we will burn 20% of limit in a single ill conceived agent tool call that we're simply not going to be able to or want to be able to intercept. Where I see a tool like this being a real step forward is to add a decision point. it does not have to bubble up to hard-require user to provide permission, but it can let the LLM have an intermediate checkpoint to say that it's about to get blasted with 30k tokens and here is roughly the shape of it and do you wanna adjust or whittle it down if you know what you're looking for etc.?
There is definitely tons of value to extract from this line of thinking.
You can't measure effectiveness, because you never know what kind of model will process your prompt. One request you might get full e.g. Opus and another they'll downgrade it to Sonnet or something more basic. I have this with "Opus 4.8" all the time.
This is the reason, when I built a tool in the same space, I chose to benchmark with cost per correct answer.
Reducing tokens and also turns is quite worthless if the LLM doesn’t solve what you put it to do.
5 replies →
[dead]
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
I have just put the comparison in the repo in case you want to checkout.
Yeah I use rtk and would love to see a comparison.
The docs are missing any examples of what this does, instead showing _how_ it works - and only for the codebase itself, rather than the behavior of the app.
What would be useful:
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.
I have to agree. I’m interested in the project, so congrats. It’s something I might really like using.
But the one thing I expected to see in the Readme was an example of: takes this tool run output: XXXXXX and converts it to: XX for a savings of 40% of tokens.
This looks like a nice (and useful) project, so thanks for sharing!
Thanks for your effort! I also think having examples of raw output before vs after using lowfat would be useful as well
1 reply →
[dead]
I've tried rtx and lean-ctx and these tools seem to end up confusing the agent more than helping. Any saving is irrelevant if the agent decides to work around the tool and makes even more calls than it would otherwise.
I don't know about cost saving, but if it's keeping the context size down I've had a lot better results using subagents to keep a higher order conversation clean for longer.
I looked into lean-ctx and decided not to use it. It has a very specific use case, and it's good when your interaction with the repository is read-only. When you want to edit, then the model has to read the whole file anyway. It's a cool tool, but it has a very narrow use case where it delivers the performance it claims.
Subagents help with costs too, as they can run on much cheaper models.
Also, most of the time when I'm having an agent look through logs or output, it's grepping for the bits of data relevant to its actions.
I have my own llm wrapping harness, which does this and has a few more tricks. For example, it doesn’t have a lot of mcp but it does have search_mcp and load_mcp tools (and search_skills) so the llm can find what it needs when it needs it without bloating the normal baseline context. The LLMs have proved really good at using them. There is also a waypoint tool they can use to record their thinking in the context without it being the final output. Am thinking about a search_expert to find colleagues it can bring into conversations too. And a lot of other stuff.
Pro tip they worked well for me with response truncation: in the truncated output, say that the full text is available in /tmp/whereever.txt - that way, the llm will be able to query and read more using built in tools without reissuing the big tool call.
great approach. I did that with my opencode based setup as well, it's neat and fun to tune skills and mcp loaders and stuff. Then i got fed up with opencode's design limitations. And then, my own harness work is on hold in favor of a harness-puppeteer paradigm, but that one has also been on hold! I'm mostly currently pulling on the thread of making it easier just to review the voluminous conversation turns!
Interesting approach. Thanks for sharing.
How do you handle the risk of stripping out the exact stack trace the agent needed? That seems like the hard tradeoff here.
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.
gonna ask the same... do far it's has been manually choosing what's useful in each command for the agents?
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.
In a perfect world the LLM needs to be very explicit on what it wants to read
The LLMs already do that themselves with `tail` all the time. There's a lot of room for improvement on top of that. Though they usually figure it out after a few tries. I often just paste manual runs errors myself anyway.
Have terms been established to describe these types of tools? How do I refer to small utilities to perform specific transformations to LLM behavior? CLI filter seems pretty good to describe this tool conversationally but not so much when searching, they some low cardinality keywords.
Great idea. I'm thinking if it could make sense to send the output to a cheap / local model to filter out only the bits that "matter" and pass that through - for the cost some extra time, but maybe it's worth it for saving tokens in the larger model.
Tbh I'll wait for first party LLM providers to build this kind of stuff. If they're not first class citizens they end up corrupting the workflow more than enriching it.
I am thinking that a small tool that simply refuses to pass large CLI output to the LLM and warns it to filter the results before reading would achieve this better as the LLM would be forced into thinking and writting the filter itself.
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.
I think GP is basically saying, bitter lesson applies here.
This is a nice little project but I’m weary of sensationally inaccurate titles for stuff like this and the infamous caveman mode. It doesn’t save 91% of tokens: it reduced in one user case 91% of output tokens on the raw CLI output. I am being pedantic about this because these sorts of claims go viral and are inaccurate.
A proper benchmark will compare a large sample of identical prompting with and without the tool, against a specific harness. Once you apply Amdahl’s law, there is no way this saves 91% of tokens holistically, which the title implies.
I work in a non-tech company and these sorts of things keep going viral, with no understanding and with no comprehension of what is actually going on. Engineering is gone and cargo cult magical incantations are in.
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.
Wait, do the coding agents fire `kubectl get -o yaml`??? Most of the harness agents, like CC or codes, are very precise about command construction. For example, the harness add - o and look for the status, for example.
Tools that remove the fat seem like a good idea, but I’m highly suspicious of their effect on the LLM’s reasoning.
LLMs were trained in the typical full-fat output found everywhere on the internet, and all of sudden they get a slightly different response that may look like nothing they have seen before.
Does that really save tokens in the long run?
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.
Still learning myself, but I've seen MCP tools just lightly wrap upstream json-body REST APIs. Works. But not only is the json structure more tokens but often the model just needs a small subset of fields in the payload.
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.
Do you have any insight if LLMs sometimes get confused by your filters?
He says he adds an output message, but I've tried this myself and I find that quite a lot of the time the agent prefers its own internal monologue over the output of a command.
I'm glad this class of tool exists.
But it'll be a case of measuring first, then perhaps a staged integration of a tool like this.
the bigger problem is agents defaulting to the broadest command possible. kubectl get -o yaml when a jsonpath query would give 1/50th the tokens. filtering after the fact works, but you're still paying for the round trip. better to teach the agent to ask narrow questions in the first place.
Hooks are great for this.
Add a comparison table between your repo and alternatives like rtk. I’m interested.
Great! Now, you should slap a logo to this, boostrap this as a service, and get you some YC funding. [0]
[0] https://thetokencompany.com
Would be interested to see what kind of eval results you get from this
Would this have any impact on the response quality from the agent?
Yes, and never for the better.
Can you elaborate more on why would it so ?
2 replies →
Frankly, not at all.
I have a suspicion that the model would miss more context unless you are very precise about what FAT means in each context. However, loved the idea.
2 replies →
Is this different from caveman?
Afaik, caveman does shorten sentences in coversation but lowfat is picking up what matter from cli ouput. That's a different output target.
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[dead]
[flagged]