logoalt Hacker News

gvkhna • yesterday at 6:44 AM • 9 replies • view on HN

Pi is without contest the best harness. Because it’s yours, the total control is the only way to move from driving agents to orchestrating them.

My interruptions and frustration with llms has gone down a cliff. It’s amazing to see what just a few lines of system prompt really can do to keep agents doing the correct thing much more often.


Replies

regexorcist • yesterday at 7:56 AM

> Pi is without contest the best harness. Because it’s yours

You can do this with any harness. I really dislike the Node.js ecosystem and avoid Pi and the like. I started with another one written in Go that has all the basics and I can extend it in minutes for anything I need while keeping track of upstream.

➕ show 1 reply
CarlitosHighway • yesterday at 8:28 AM

Is OpenCode already passé? Especially with OpenChamber on top I don't see a reason to switch to PI.

➕ show 1 reply
mark_l_watson • yesterday at 3:14 PM

I tend to agree with you. I wrote 4 separate coding harnesses of my own earlier this year (in different programming languages, great learning experience), but pi running good local models like qwen 3.8 next flash, or a deepseek flash API from a vendor with decent privacy assurances is really the bedrock of my workflow. There are always exceptions: running pool harness with Laguna XS 2.1 6bit is a really nice local dev experience for code maintenance and quicker sessions. Also, I very occasionally really enjoy DeepSeek Harness with deepseek flash, CC with Opus 5.5 and agy with the latest Gemini Argon.

So there are many wonderful dev experiences, but generally relying on something relatively simple like pi makes a lot of sense, for my use cases.

julesrms • yesterday at 10:19 AM

> it’s yours, the total control is the only way to move from driving agents to orchestrating them

I wrote Juggler (https://github.com/juggler-ai/juggler) because I liked Pi's approach to everything being customisable and controllable, but I wanted a slick, navigable GUI rather than terminal hell.

...BUT: having gone to great pains to build an architecture around customisation, where every possible pluggable thing is a plugin, I'm starting to feel jaded on the whole "we need to customise it all" mentality. The models have got so good over the last year that I just don't think that tweaking the harness is something many people will need to do as things progress. The models only need a bare-bones set of tools to do everything they need, and I'm starting to think that UX and UI are the only really important things to focus on in an agent.

(Although from the perspective of coding a harness, making things plugins and having a plugin API does help to keep things clean and stops the codebase getting sloppy)

Rodmine • yesterday at 8:33 AM

>Pi is without contest the best harness.

There is contest.

https://frontierharness.org/

With minimal work, you can get DSH web to be exposed to your internet behind Cloudflare Access (or similar) and have a harness running on your computer at home from any browser, including your phone's.

➕ show 1 reply
neop1x • yesterday at 1:12 PM

Exactlty. I love that it works the way I want it to work. I can install and write extensions I want.

tonfreed • yesterday at 6:47 AM

Second this, I went from Claude code fighting me all the time and being insanely opaque with its internals to Pi with detailed telemetry about what my agents are actually spending time on. My entire harness is completely custom, and works exactly the way I want it to. Absolutely love Pi

deagle50 • yesterday at 7:41 PM

Which few lines of system prompt?

TheArcane • yesterday at 6:46 PM

[flagged]

➕ show 1 reply