Every few weeks Pi hits #1 here and I quietly grumble "mine does that too, but with lovely graphics.", so I'm saying it out loud: <a href="https://github.com/juggler-ai/juggler" rel="nofollow">https://github.com/juggler-ai/juggler
Like Pi, it's plugins all the way down, provider-agnostic, minimal system prompts, threaded sub-agents, code-mode, multi-client remote sessions, worktrees, a context window you can actually see and edit, etc etc
Where Pi is way ahead is the plugin ecosystem, and that takes people, which is hard to get amid the current deluge of agent action. So if there's any spare oxygen trailing off this thread, I'd love any Pi-heads who fancy a bit of GUI action to come and kick the tyres..
My personal quiet grumbling is that everyone got on the TUI bandwagon without any rational reason. I find it borderline psychotic. Or maybe humans are much more like sheep than we care to admit: we just follow the flock into the (UI) ravine. So your GUI is a nice escape.
> And to be honest: what do you even need from a harness\agent for it to have a gui?
Oh, it's just so much nicer! Personally I'm a graphics/typography nerd, so just having nice fonts, smooth movement, use of sizes, colours and graphics to differentiate and display types of information...
Some people obviously don't care about this kind of look and feel nicety, but even so a GUI has so many more opportunities for displaying information in a clear but dense way.
You can choose any font you want for your terminal, but only one at a time!
The native format of LLM interactions is markdown, and showing that in a terminal is a poor imitation of what it looks like rendered properly.
An interesting thing you can do in juggler is ask the LLM to reply in HTML instead of markdown, and they can then do things like illustrate points visually for you. LLMs are actually great at being able to express things visually to the user, but being stuck in terminals so much, people haven't really leaned on that very much
I won't say Pi looks particularly impressive, but for example OpenCode looks beautiful to me and I prefer it to any graphical interface. The screenshots of your tool are nice but they feel like too much. With a good TUI like OpenCode and even Pi (which is decent) I fell like the code is front and foremost.
> And to be honest: what do you even need from a harness\agent for it to have a gui?
Nothing absolute that I couldn't live without. But TUI is essentially a design written for the lowest common denominator. It doesn't matter that I have had high resolution displays for years, average TUI is designed as if I'm using computer older than me.
I live in an office when I'm at work. Doesn't mean it's a great experience.
I love the terminal for terminal things. I'm not convinced agenetic coding is best implemented in a terminal - for it to work well, you're basically reinventing a toolkit wheel. Why not just use a nice graphical toolkit? It feels a bit like the current trend for pixelated graphics - both retro and worse.
julesrms · · focus · HN ↗
Like Pi, it's plugins all the way down, provider-agnostic, minimal system prompts, threaded sub-agents, code-mode, multi-client remote sessions, worktrees, a context window you can actually see and edit, etc etc
Where Pi is way ahead is the plugin ecosystem, and that takes people, which is hard to get amid the current deluge of agent action. So if there's any spare oxygen trailing off this thread, I'd love any Pi-heads who fancy a bit of GUI action to come and kick the tyres..
jonenst · · focus · HN ↗
konart · · focus · HN ↗
I hardly use anything aside from neovim and a browser. (okay corporate Mattermost fork and video terminal too).
For me switching between different cli\tui tools feels like a continuation of whatever I was doing, while going to something GUIsh is not.
And to be honest: what do you even need from a harness\agent for it to have a gui?
julesrms · · focus · HN ↗
Oh, it's just so much nicer! Personally I'm a graphics/typography nerd, so just having nice fonts, smooth movement, use of sizes, colours and graphics to differentiate and display types of information... Some people obviously don't care about this kind of look and feel nicety, but even so a GUI has so many more opportunities for displaying information in a clear but dense way.
konart · · focus · HN ↗
They can even show images these days.
Some of the elements can't be recreated 1 to 1 ofc, like borders with delicate margin\padding adjustment, but this is about it I think.
To each his own, yeah. From my experiment GUIs tend to overcomplicate things and display too much info you didn't need in the first place.
konart · · focus · HN ↗
experience
voakbasda · · focus · HN ↗
albondiga90210 · · focus · HN ↗
julesrms · · focus · HN ↗
The native format of LLM interactions is markdown, and showing that in a terminal is a poor imitation of what it looks like rendered properly.
An interesting thing you can do in juggler is ask the LLM to reply in HTML instead of markdown, and they can then do things like illustrate points visually for you. LLMs are actually great at being able to express things visually to the user, but being stuck in terminals so much, people haven't really leaned on that very much
maupin · · focus · HN ↗
flaunf221 · · focus · HN ↗
Nothing absolute that I couldn't live without. But TUI is essentially a design written for the lowest common denominator. It doesn't matter that I have had high resolution displays for years, average TUI is designed as if I'm using computer older than me.
epihelix · · focus · HN ↗
I love the terminal for terminal things. I'm not convinced agenetic coding is best implemented in a terminal - for it to work well, you're basically reinventing a toolkit wheel. Why not just use a nice graphical toolkit? It feels a bit like the current trend for pixelated graphics - both retro and worse.