Pi's Minimalism Is Its Advantage • Hacker News Board

Re: Pi's Minimalism Is Its Advantage

#31

Post by HDBaseT » Wed, Aug 05, 2026, 2:04 AM UTC

malisper wrote: post #3

Having tried all the coding harnesses, I find that using Pi is exactly like using Emacs. For anything you want to build you can ask your agent and it will build it. There's tons of existing code to help you configure it. At the same time half the code is buggy, UI elements will try to overlap one another, and you'll periodically get crashes. If you're willing to put in the work to master the learning curve and push t…

I don't really get this philosophy, at least with coding harnesses.

I don't want to spend 2 hours prompting, configuring and fixing features that I need which are standard in every other harness. I don't really want to be wasting my tokens to make an application function like every other harness. I don't really want to have to repeat the cycle on every machine I want to work with. Every VM, every server, every laptop.

Re: Pi's Minimalism Is Its Advantage

#32

Post by NamlchakKhandro » Wed, Aug 05, 2026, 2:06 AM UTC

hakunin wrote: post #11

I often find it reductive when people say "just tell Pi to build you an extension". Having used it as my one and only harness for a few months now, it's easy to get an extension, but hard to get a good one, that actually works well and helps. My advice: focus on getting work done and slowly adapt Pi with small augmentations as you go. You can start getting work done on vanilla setup. When the right idea comes along,…

skills as memory is a great idea

Re: Pi's Minimalism Is Its Advantage

#33

Post by alasano » Wed, Aug 05, 2026, 2:08 AM UTC

pornel wrote: post #18

I'm enjoying the maximal version: https://omp.sh

I find omp funny because it's the opposite of why Iike Pi.

Re: Pi's Minimalism Is Its Advantage

#34

Post by deadbabe » Wed, Aug 05, 2026, 2:13 AM UTC

suprjami wrote: post #16

hakunin wrote: post #11

I often find it reductive when people say "just tell Pi to build you an extension". Having used it as my one and only harness for a few months now, it's easy to get an extension, but hard to get a good one, that actually works well and helps. My advice: focus on getting work done and slowly adapt Pi with small augmentations as you go. You can start getting work done on vanilla setup. When the right idea comes along,…

I have the same opinion as your first paragraph, but I don't want to spend weeks or months vibe-coding basic features which come built into almost every other agent. Yeah maybe Claude/OpenCode/KiloCode/Hermes/whatever are not as minimal as Pi but they also work right now.

You don't actually need those features. Initially I began using Pi thinking I would customize the hell out of it. I've installed one extension for guardrails and that's about it. I've been able to do everything I did before just with vanilla pi.

Re: Pi's Minimalism Is Its Advantage

#35

Post by impulser_ » Wed, Aug 05, 2026, 2:16 AM UTC

CharlieDigital wrote: post #9

p1necone wrote: post #2

I love hacking away at pi extensions. I realised how use case dependent harness behaviour is when I tried to use my customised-for-a-side-project pi config at work and realised I needed to tweak it significantly to be useful - I would not be surprised if tools like Claude Code needing to be all things for all people is hurting their peak usefulness.

End up building Pi extensions instead of actual product. Doesn't make sense to me, but to each their own.

Yeah, but the future will essentially be building extensions for agents. Agents will become the new web browser and extensions will be the new apps. We are already seeing the early stages of this.

Re: Pi's Minimalism Is Its Advantage

#36

Post by TheRoque » Wed, Aug 05, 2026, 2:24 AM UTC

swingboy wrote: post #27

Aside from the minimal system prompt, how does it handle context better than other agents? It still has to send the system prompt (which includes AGENTS.md and skill definitions) along with the full conversation every request, no?

A lot of harnesses compress the context when it becomes massive, Pi doesn't do that out of the box (EDIT: that's wrong, as pointed out below). It can be both good and bad. Also since it doesn't have a lot of tools out of the box, the context is not polluted with external tool call descriptions that the agent has to be aware of.

Basically, it doesn't handle the context "better", it barely does anything special to it, which can actually be better for cost efficiency.

Re: Pi's Minimalism Is Its Advantage

#37

Post by Yiling-J » Wed, Aug 05, 2026, 2:26 AM UTC

Pi is really good. For people who want to build their own agent with even more minimal and extensible, the underlying agent harness is also worth looking: https://github.com/earendil-works/pi/tree/main/packages/agen...

Re: Pi's Minimalism Is Its Advantage

#38

Post by langs » Wed, Aug 05, 2026, 2:29 AM UTC

Pi’s minimalism reveals a simple truth: the LLM is the core of any agent harness. Consequently, much of current harness tuning will become redundant(or even a hindrance) with next-gen models.

Re: Pi's Minimalism Is Its Advantage

#39

Post by JSR_FDED » Wed, Aug 05, 2026, 2:30 AM UTC

alasano wrote: post #33

pornel wrote: post #18

I'm enjoying the maximal version: https://omp.sh

I find omp funny because it's the opposite of why Iike Pi.

It’s more like a curated config. Like using Astro or Lunar instead of starting with a plain Neovim and crafting your own configuration.

Re: Pi's Minimalism Is Its Advantage

#40

Post by yogthos » Wed, Aug 05, 2026, 2:39 AM UTC

I found the nice part of Pi was the plugin system and the ability to hook into any part of the agentic loop. But minimalism is a net negative in my experience. What you really want is a harness that meets the expectations of the model and steers it in the right direction.

There are also a ton of small mechanical things a harness can handle that make the whole process much smoother. A really simple example is auto balancing parens. Even frontier models like Claude still struggle with this. Often the model will end up writing a python script to figure out where the mismatch is, and then generate a new version of the code. All of that simply wastes tokens and eats up context on a task that could've been accomplished completely mechanically.

The approach I took with dirge, is to put the model in a loop where it has clearly defined tasks, and the harness handles any repairs that can be done automatically. And I used Janet to provide a plugin system based on what Pi is doing. You get a batteries included experience out of the box, and you can customize it to fit a specific project using plugins if needed.

https://yogthos.net/posts/2026-06-08-dirge-code.html