201–210 of 307 posts
I’m going to go against the grain and say that Pi is a little too minimal by default. The emacs comparison is interesting, but default Pi is like emacs that can load files but you’ve got to extend it manually to save or search within a file. I’d argue that there’s a minimal set of functions that a coding harness needs to just enable a model to get stuff done, and they shouldn’t be an extra effort to set up. (Oh-my-pi…
Earlier quoted context omitted.
> For a program that's minimal it sure takes a long time to start up, the standard C-p and C-n bindings don't work, it doesn't follow the XDG Base Directory Specification and just pollutes my $HOME directory. This drives me mad, I believe Ollama and Claude Code also do this. Seems to be rife in the LLM world. IMO there's no excuse for new software sticking dotfiles in my homedir in 2026.
The problem with the XDG spec is that it now forces you to have different paths on different platforms. It just increases the complexity and at the end of the day unless all software adheres to it, you still end up with a “polluted HOME”. I’m not a fan of config directories being in different locations on different platforms because it’s now one extra thing everyone needs to handle. (Disclaimer: I work on Pi but I di…
Lots of praise for Pi in this thread, so I'll offer up a diverging opinion. Given all the hype, I was a bit underwhelmed by Pi. It definitely has some good ideas around customization, but it annoyed me in many little ways. For a program that's minimal it sure takes a long time to start up, the standard C-p and C-n bindings don't work, it doesn't follow the XDG Base Directory Specification and just pollutes my $HOME d…
I don’t know what the standard C-p and C-n bindings are. Could you share? The startup time is a known issue and scales badly with extensions. We’re aware of it but fixing it is tricky.
Philosophically, pi.dev is exactly what I'm looking for. Minimalist and explicit (YOLO by default, we know it can be trouble but we tell you so). Anyone here using the Rust rewrite of pi.dev as their daily driver? It's endorsed by the author of pi.dev and looks pretty attractive to me being both minimalist and not having npm attached. Any info "from the trenches" are appreciated (setup with sandboxing, extra niceties…
Earlier quoted context omitted.
I don’t know what the standard C-p and C-n bindings are. Could you share? The startup time is a known issue and scales badly with extensions. We’re aware of it but fixing it is tricky.
C-p and C-n (aka Ctrl-P and Ctrl-N) are the Emacs-style keybindings for previous (line) and next (line), very commonly encountered on the command line and in terminal applications. For example, most shells can use this in addition to up-arrow and down-arrow to cycle thru command history. Many, many more examples exist of applications (not just terminal-based, there are plenty of GUI apps too) that use this convention…
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?
The /tree feature is incredible for context management. It's really surprising the other harnesses haven't slurped it up yet. It lets you rewind back to any previous message and fork the conversation from there, removing your 'side quest' (e.g. where you dig into something the agent said) from the context. Some other harnesses have a 'rewind' feature, but this lets you maintain the previous conversation history in a…
Lots of praise for Pi in this thread, so I'll offer up a diverging opinion. Given all the hype, I was a bit underwhelmed by Pi. It definitely has some good ideas around customization, but it annoyed me in many little ways. For a program that's minimal it sure takes a long time to start up, the standard C-p and C-n bindings don't work, it doesn't follow the XDG Base Directory Specification and just pollutes my $HOME d…
I know it's little, but this was the first thing I noticed and it made me think, "Maybe this app isn't for me."
EDIT: FWIW, I just complained to pi and it added the keybinds for me in 10 seconds.
Earlier quoted context omitted.
C-p and C-n (aka Ctrl-P and Ctrl-N) are the Emacs-style keybindings for previous (line) and next (line), very commonly encountered on the command line and in terminal applications. For example, most shells can use this in addition to up-arrow and down-arrow to cycle thru command history. Many, many more examples exist of applications (not just terminal-based, there are plenty of GUI apps too) that use this convention…
Ctrl+P in most coding agents is bound to bringing up a command bar. You should be able to bind both hotkeys to the functionality you want already.
I was expecting an article about Pi constant or maybe raspberry Pi computer. "My Disappointment Is Immeasurable And My Day Is Ruined!"
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
So unless it’s been fixed or someone knows a work around, Pi is DOA - I’ve found that on a MULTI tool call (ie one prompt firing off multiple tool calls until it prompts you again) that’s close to hitting the auto-compaction limit (default compactor or extension) it will either keep going until your context spills over and you OOM, or it interrupts itself to compact but then loses the context.
From reading issue after issue on GitHub, I think it’s because Pi doesn’t let extension writers (nor the built-in compactor) hook in between each tool call and so the only place to check if it can compact is when it finishes a request and is about to wait for the next prompt - too late by then