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

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

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.

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.

Interesting approach. Thanks for sharing.

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.

Can you elaborate more on why would it so ?

Because it could discard things the agent needs.

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

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.

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.

Yes, it also depends on how a model harness uses a tool.

Harness: I'm about to commit. Good use case Harness: What has changed from X to Y. Bad use case NO?

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!

Agreed, try to use OpenHop to create the data flow diagram

Thanks for your effort! I also think having examples of raw output before vs after using lowfat would be useful as well

Got it! thanks for your feedback.

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.