Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Pi's Minimalism Is Its Advantage

earendil.com

Post reply on HN
Print view View original

61–70 of 307 posts

Re: Pi's Minimalism Is Its Advantage

#61

Post by TheRoque »

rahimnathwani wrote: post #58
TheRoque wrote: post #36

Earlier quoted context omitted.

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,…

Pi has auto compaction enabled by default: https://pi.dev/docs/latest/compaction

Ok my bad. I remember hearing that it was a criticism of common harnesses and that the creator of Pi wanted more control over that feature, so I assumed it wasn't enabled by default. Thank for pointing it out !

Re: Pi's Minimalism Is Its Advantage

#62

Post by rahimnathwani »

TheRoque wrote: post #61
rahimnathwani wrote: post #58

Earlier quoted context omitted.

Pi has auto compaction enabled by default: https://pi.dev/docs/latest/compaction

Ok my bad. I remember hearing that it was a criticism of common harnesses and that the creator of Pi wanted more control over that feature, so I assumed it wasn't enabled by default. Thank for pointing it out !

It was introduced in late 2025:

https://github.com/earendil-works/pi/issues/92

Re: Pi's Minimalism Is Its Advantage

#63

Post by tosh »

sebmellen wrote: post #54
tosh wrote: post #51

i also found re context window: less is more at least with GPT 5.6 Sol fwiw https://smolenv.com/t/nested-template-includes-60636/ sh is all you need

Do you use smol? How do you find it compares to other harnesses for things like MCP connections? I’m tempted to use it since I’m a fan of the philosophy.

I use it for smaller changes (no compaction yet)

If I have agents.md or other context I want it to read I mention it at the beginning of the session

re MCP: I am not using an MCP with smol

but there are ways to convert MCPs into CLI tools or typed js

I imagine that would work well/more token efficient with smol (or most harnesses actually)

The best thing I found so far re smol is that it fits into the context window with plenty of room to spare

So it is easy to adapt (and add stuff to it, even stuff you only need specifically for just 1 project)

Whereas adapting a more complex harness is more error prone

Re: Pi's Minimalism Is Its Advantage

#64

Post by tosh »

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 few examples:

1) system prompt in pi is quite small (way smaller than the one from OpenCode)

2) when your agents.md file changes pi does not re-spam it (preserves cache, good trade-off!)

3) only 4 tools, every tool comes with a description for how to use it and causes reasoning overhead (fewer tools is good)

all of these things add up

here are pi, opencode and smol working on the same tasks in 9 fresh runs

https://smolenv.com/t/nested-template-includes-60636/

you can step through the traces and see how the system prompt + tools steer the agent in a certain way

with GPT 5.6 Sol you can even get away without a system prompt (see smol) and only 1 tool (sh)

Re: Pi's Minimalism Is Its Advantage

#65

Post by sebmellen »

tosh wrote: post #63
sebmellen wrote: post #54

Earlier quoted context omitted.

Do you use smol? How do you find it compares to other harnesses for things like MCP connections? I’m tempted to use it since I’m a fan of the philosophy.

I use it for smaller changes (no compaction yet) If I have agents.md or other context I want it to read I mention it at the beginning of the session re MCP: I am not using an MCP with smol but there are ways to convert MCPs into CLI tools or typed js I imagine that would work well/more token efficient with smol (or most harnesses actually) The best thing I found so far re smol is that it fits into the context window…

I didn't realize you were the author. Super cool! I'll be trying it out.

I do like the grug-brain approach of keeping things extremely simple and easy to reason about.

One thing that I don't like about Pi is that it's almost too extensible, in the sense that I can add a lot of shit into it without really understanding what a given extension is doing. And both from a security and token efficiency standpoint, I like the premise of converting things like MCPs into CLIs. It might be worth investing in tooling that works nicely with the agent harness, but that is not directly integrated with it. I'd be glad to work on that for smol if I can get a workflow going.

Re: Pi's Minimalism Is Its Advantage

#67

Post by mw888 »

I like Pi, but I didn't end up using it. I tried OpenCode, Pi, Zed Editor and some NVIM packages. I wanted open source, featureful and easy to use. Specifically I wanted to easily edit the agent prompt.

I ended up on VS Code. I'm very critical of Microsoft generally, but VS Code is a very good editor and my favorite agent harness.

For headless, Pi might be the way.

Re: Pi's Minimalism Is Its Advantage

#68

Post by throw10920 »

hakunin wrote: post #17
suprjami wrote: post #16

Earlier quoted context omitted.

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.

We probably differ a lot in what we consider "basic". Are subagents basic? I found them only useful in very few situations. Is LSP support basic? There are mixed results on whether it helps or hurts. Are multiple choice asking tools basic? I found that they add extra unnecessary ceremony, eat extra context, and I almost never answer with one of the choices exactly. And if you try vanilla Pi, you will also find out th…

> Are subagents basic? I found them only useful in very few situations.

I've found them to be extraordinarily helpful, because they allow me to much more carefully control context and reduce token spend by using a smart model for the parent agent and cheap models for the subagents. Do you just have a big token budget?

Re: Pi's Minimalism Is Its Advantage

#69

Post by CharlieDigital »

impulser_ wrote: post #35
CharlieDigital wrote: post #9

Earlier quoted context omitted.

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.

how many extensions do you need for browsing the web? Adblocker. Not much else because the browser already does the important work.

Same with any of the off the shelf harnesses.

Go build something useful instead of tweaking the minutiae of the harness.

Re: Pi's Minimalism Is Its Advantage

#70

Post by klooney »

Onavo wrote: post #14

The biggest issue with Pi is that they don't have proper sandboxing with auto approval. Most solutions are third party and half baked. You have to either choose between just auto approval (no sandboxing), or a Claude/Codex style sandbox but manual approval.

I don't really want to do approvals though. Either I put stuff into a real sandbox, or #yolo
Post reply on HN