I agree. I don't necessarily "trust" Anthropic and OpenAI when it comes to CC/Codex respectively, but I respect that they have immense internal resources and telemetry to be able to understand what features move the needle and nudge traces in the right direction. I don't understand how non-labs judge feature inclusion? Just vibes?

Classification models have been around for literally almost a century at this point. I think it's safe to say they are a proven technology.

The only thing that makes Jev and the likes particularly interesting is that it is a general purpose classifier. In the past, classification tasks meant training a new model to solve your problem. Now you can just use an off the shelf general purpose model and hit the ground running.

> but MCP has been growing for nearly 2 years, and it only gets support now?

I don't know if you were aware, but not shipping with MCP was one of its "features":

https://mariozechner.at/posts/2025-11-02-what-if-you-dont-ne...

They let you have it via a plugin/extension.

the latest 07-28 MCP spec is quite different than the previous iterations of MCP, so I understand the delay there tbh.

Armin from Earendil here. I think the question is fair, and quite frankly the answer is pretty disappointing: we look at what the models are doing. They are trained on their respective harnesses and we're not here to fight their behavior.

Codex in particular is using responses lite internally and relies on codemode for parallel tool calling. So codemode was a given.

Jev on the other hand is new but it's not the first type of model we had troubles with supporting in Pi and we looked at how to make that make sense. The internal pi-ai SDK supports image generation and classifier models, but without building an extension it was never possible for you to utilize it.

So there was a while functionality of Pi that few people used, because there were no obvious ways to hook it up with the coding agent. Codemode also allows us to close that gap.

And once you have codemode, modern MCP can work quite well if the servers cooperate.

I tried Pi a while ago and found it a bit tough to use, OpenCode was pretty simple, but oh-my-pi is really head and shoulders above the two others. Really great.

Paseo is great and has mobile notifications but it’s not as polished as omp web.

I don't use Pi very much for actual writing code. I have some specific use-cases where I do, but I'm admittedly just not a person who can reasonably juggle a lot of tools or a super personalized setup. I mostly just use Codex or CC from the terminal, though I've recently dabbled with some GUIs. Basically, once I find something that works, I'm pretty reticent to spend any time tinkering unless I feel a real need.

But what I do use Pi a lot for is as a base for agents. I much prefer it to using an agent SDK. I find its minimalism and extensibility to be a really nice substrate for new projects.

I could easily imagine someone getting to a really productive personal setup with it as well, for the same reasons as above.

And you're probably more productive than the people using Pi. Although you'd be even better off using a GUI agent multiplexer of some kind rather than juggling terminal tabs.

I love open source. I love the terminal. I spent the last 20+ years in a terminal w/vim every single day, and then claude/codex TUIs, and yet I care more about my own productivity so I don't use any of that now.

I’m also looking for tips. I feel like I get the gist, but if I sat down to use it, I don’t know what I want to start with. Like, I know it’s customizable, but what’s the on-ramp so I can figure out what that looks like?

I use claude code and codex in a terminal like a caveman too.

then i use pi in a terminal like a caveman to try the open models like deepseek etc.

I also have pi running on a VPS. I have a custom Django app that calls out to it for a bunch of stuff. I don't know how the full system works because the agents built it but basically I think one pi uses a whatsapp wrapper to constantly listen to a whatsapp group and find bills. Then those get added to the Django Database which triggers a second pi + deepseek to OCR them, parse out the data like amount, due date, reference etc, and update the database with that. I have a trigger to 'merge duplicate', which is also just a prompt and pi.

Yes you can do all this without a harness and just the model APIs directly but the harness means it can use linux tools to crop the PDFs etc, so when I also wanted a new feature that crops out the bank details and lets me hover over and see the original before making the payment for a bill that's just another tweak to pi's prompt (or more meta, me prompting my agent to update pi's prompt).

It's been pretty useful for experimenting with local models due to its more light-weight approach. Though I respect the creators a ton, OpenCode has not seemed to work as well with models that run on consumer hardware

I believe this is the popular "batteries included" kit: https://github.com/can1357/oh-my-pi

You just type "pi" in the command prompt and you're good to go!

The only thing I've configured is the default model.

Vanilla Pi is great. I have a subagent/ Ralph loop extension I coded and that's basically it. It works very well. I'm about 75% pi, 20% autolith, and 5% my own harness

I built my own based off another popular harness. I figure most of the edge cutters are doing the same.

Pi is great overall. I ended up deploying a GUI wrapper because TUI isn't as friendly to new adopters.

Using models from multiple providers via aws bedrock

I use workmux with pi plus some neovim plug-ins

the main thing i use it for that seems like a pain with other coding agents is my sandboxing workflow: i have a custom extension which allows the pi process to run on my laptop, keeping all my transcripts in one searchable place, while delegating all the bash and file system commands to a VM.

i haven't gotten around to it yet, but i'd also like to change how `Bash` functions on a basic level (and subagents), where rather than the agent picking a fixed timeout, it just gets notified with exponential backoff about commands that aren't done and then gets a turn to decide what to do with it.

having said that, i find it annoying and not empowering that basic things like subagents and web search aren't built in. the ideal to me seems to be an agent with polished extensions for all the common use cases that can be disabled if you do want to rewrite them. but i put up with the pain because i really want my pet feature ¯\_(ツ)_/¯

> Here I am with Claude Code and Codex in a terminal like a caveman

There's definitely a class of folks who like to "polish their tools" per se vs tools just being as a means to an end.

It's fine and cool, sort of like the desktop ricers do with Hyperland, Niri, etc showing off desktops, but never seem to do anything with this cool tech.

Frankly you are not losing much. I've used everything under the sun, for work and fun. I just use Claude now again for work, and I use Pi for any openrouter model I'm using.

Just keep using Claude or Codex.

It's all window dressing and some delta in token usage, but again who cares really?

This really only matters when you're productizing "AI" for your end users, that's when you need to see which agent uses tools better, has more support for MCPs, headless mode, sessions, etc. \

I use it headless for reviews in CI.

Not what we stand for: https://earendil.com/values/

the exception to prove the rule I guess

Full screen hides distractions from other applications. Seems reasonable as something minimal.

Minimalism is a difficult subject. In art, minimalists tried to strive for something that is universally minimal. But if you look in nature for straight lines or perfect circles, you end up disappointed. Turns out minimalism found things that were minimal with respect to how some humans think about minimalism. For all we know, pure chaos may be more universally minimal than an empty vacuum.

Can you explain your workflow a bit please? Do any of these tools work with Claude/Codex subscriptions or are they API only?

I actually built my own tool that maintains a work graph (DAG-like) with task leases. It allows me to copy and paste pre-written prompts into Claude Code, Codex, or OpenCode and all the agents self-coordinate through MCP calls.

I built this after trying hermes and Openclaw but not liking the lack of human-in-the-loop judgement. So I'm wondering if I should keep refining my tool, or evaluate something like pi?

Claude is not but codex is. Which is why I switched.

You can use it with oai subscriptions

Local Qwen 3.5 on CPU was good enough for small tasks.

What would be a better language? Most of the harness apps will be spending most of their time waiting for the models response and tool calling rather than running their code.

Languages with less opensource footprint or too verbose are at the losing side in a llm-driven world.